Patent Grant
11353879
Priority is claimed on Japanese Patent Application No. 2019-063140, filed Mar. 28, 2019, the content of which is incorporated herein by reference.
The present invention relates to a vehicle control device, a vehicle control method, and a storage medium.
In recent years, studies of automated vehicle control have been conducted. In relation to this technology, the invention of a travel road shape recognition device that includes a plurality of travel road shape recognizers with different recognition principles and recognizes shapes of travel roads in accordance with comprehensive determination of a plurality of recognition results of the plurality of travel load shape recognizers was disclosed. The travel road shape recognition device includes a determiner that determines reliability of the recognition of each travel road shape recognizer, excludes the recognition result of the travel road shape recognizer of which the reliability is low, and uses the recognition results of the remaining travel road shape recognizers for the comprehensive determination (see Japanese Unexamined Patent Application, First Publication No. H11-296799). In this device, to perform lane maintenance control, three information resources of a map, a camera, and a yaw rate are used to switch the information source by priority in this order.
In the technology of the related art, consideration of an event occurring in the switching of the information source is insufficient. For example, when the technology is applied to a task of detecting a vehicle, there is a possibility of discovery of a vehicle being delayed or erroneous detection occurring at high frequency.
The present invention is devised in view of such circumstances and an objective of the present invention is to provide a vehicle control device, a vehicle control method, and a storage medium capable of realizing early discovery of a target vehicle and suppression of erroneous detection.
A vehicle control device, a vehicle control method, and a storage medium according to the present invention adopt the following configurations.
(1) According to an aspect of the present invention, a vehicle control device includes: a recognizer configured to recognize a surrounding situation of a vehicle; a target vehicle specifier configured to specify a target vehicle which is a control target of the vehicle within a set reference range based on a recognition result of the recognizer; and a driving controller configured to control at least one of an acceleration or deceleration speed and steering of the vehicle based on a position of the specified target vehicle. The target vehicle specifier includes a first target vehicle specifier configured to specify the target vehicle in a reference range based on lane information and output first target vehicle information, a second target vehicle specifier configured to operate in parallel with the first target vehicle specifier, specify the target vehicle in a reference range based on a behavior of the vehicle, and output second target vehicle information, and an arbitrator configured to select one of the first target vehicle information and the second target vehicle information and output the selected target vehicle information to the driving controller.
(2) In the vehicle control device according to the aspect (1), the lane information input to the first target vehicle specifier may include lane information based on a position of a road demarcation line detected by an on-board sensor and lane information based on map information and vehicle position information.
(3) In the vehicle control device according to the aspect (1), the first target vehicle specifier may specify the target vehicle based on the lane information based on map information and specify the target vehicle based on the lane information based on an output of an on-board sensor in some cases. The vehicle control device may further include a determiner configured to compare standard information based on the map information with standard information based on the behavior of the vehicle and output information indicating non-use of the first target vehicle information based on the map information when a difference between the standard information based on the map information and the standard information based on the behavior of the vehicle is large or configured to compare standard information based on the output of the on-board sensor with the standard information based on the behavior of the vehicle and output information indicating non-use of the first target information based on the output of the on-board sensor when a difference between the standard information based on the output of the on-board sensor and the standard information based on the behavior of the vehicle is large.
(4) In the vehicle control device according to the aspect (1), the first target vehicle specifier may specify the target vehicle based on the lane information based on map information and specify the target vehicle based on the lane information based on an output of an on-board sensor in some cases. The arbitrator may cause the first target vehicle information to be more easily selected in a case in which the first target vehicle information does not match the second target vehicle information when the target vehicle is specified based on the lane information based on the map information than when the target vehicle is specified based on the lane information based on the output of the on-board sensor.
(5) In the vehicle control device according to the aspect (1), the arbitrator may preferentially select the vehicle information with which the same vehicle is continuously specified when the first target vehicle information does not match the second target vehicle information.
(6) In the vehicle control device according to the aspect (1), the arbitrator may preferentially select the vehicle information with which a vehicle closer to the vehicle is specified when the first target vehicle information does not match the second target vehicle information.
(7) In the vehicle control device according to the aspect (1), the first target vehicle specifier may specify the target vehicle based on the lane information based on an output of an on-board sensor. The arbitrator may acquire reliability of the output of the on-board sensor and preferentially select the second target vehicle information when the reliability is lower than a standard.
(8) According to another aspect of the present invention, there is provided a vehicle control method causing a computer: to recognize a surrounding situation of a vehicle; to specify a target vehicle which is a control target of the vehicle within a set reference range based on a recognition result; to control at least one of an acceleration or deceleration speed and steering of the vehicle based on a position of the specified target vehicle; to perform a process of specifying the target vehicle in a reference range based on lane information and outputting first target vehicle information and a process of specifying the target vehicle in a reference range based on a behavior of the vehicle and outputting second target vehicle information in parallel when the target vehicle is specified; and to select one of the first target vehicle information and the second target vehicle information.
(9) According to still another aspect of the present invention, a storage medium that stores a program causing a computer: to recognize a surrounding situation of a vehicle; to specify a target vehicle which is a control target of the vehicle within a set reference range based on a recognition result; to control at least one of an acceleration or deceleration speed and steering of the vehicle based on a position of the specified target vehicle; to perform a process of specifying the target vehicle in a reference range based on lane information and outputting first target vehicle information and a process of specifying the target vehicle in a reference range based on a behavior of the vehicle and outputting second target vehicle information in parallel when the target vehicle is specified; and to select one of the first target vehicle information and the second target vehicle information.
According to the aspects (1) to (9), it is possible to realize early discovery of a target vehicle and suppression of erroneous detection.
Hereinafter, embodiments of a vehicle control device, a vehicle control method, and a storage medium according to the present invention will be described with reference to the drawings.
The vehicle system 1 includes, for example, a camera 10, a radar device 12, a finder 14, an object recognition device 16, a communication device 20, a human machine interface (HMI) 30, a vehicle sensor 40, a navigation device 50, a map positioning unit (MPU) 60, a driving operator 80, an automated driving control device 100, a travel driving power output device 200, a brake device 210, and a steering device 220. The devices and units are connected to one another via a multiplex communication line such as a controller area network (CAN) communication line, a serial communication line, or a wireless communication network. The configuration shown in
The camera 10 is, for example, a digital camera that uses a solid-state image sensor such as a charged coupled device (CCD) or a complementary metal oxide semiconductor (CMOS). The camera 10 is mounted on any portion of a vehicle in which the vehicle system 1 is mounted (hereinafter referred to as an own vehicle M). When the camera 10 images a front side, the camera 10 is mounted on an upper portion of a front windshield, a rear surface of a rearview mirror, and the like. For example, the camera 10 repeatedly images the surroundings of the own vehicle M periodically. The camera 10 may be a stereo camera.
The radar device 12 radiates radio waves such as millimeter waves to the surroundings of the own vehicle M and detects radio waves (reflected waves) reflected from an object to detect at least a position (a distance and an azimuth) of the object. The radar device 12 is mounted on any portion of the own vehicle M. The radar device 12 may detect a position and a speed of an object in conformity with a frequency modulated continuous wave (FM-CW) scheme.
The finder 14 is a light detection and ranging (LIDAR) finder. The finder 14 radiates light to the surroundings of the own vehicle M and measures scattered light. The finder 14 detects a distance to a target based on a time from light emission to light reception. The radiated light is, for example, pulsed laser light. The finder 14 is mounted on any portions of the own vehicle M.
The object recognition device 16 performs a sensor fusion process on detection results from some or all of the camera 10, the radar device 12, and the finder 14 and recognizes a position, a type, a speed, and the like of an object. The object recognition device 16 outputs a recognition result to the automated driving control device 100. The object recognition device 16 may output detection results of the camera 10, the radar device 12, and the finder 14 to the automated driving control device 100 without any change. The object recognition device 16 may be excluded from the vehicle system 1.
The communication device 20 communicates with other vehicles around the own vehicle M using, for example, a cellular network, a Wi-Fi network, Bluetooth (registered trademark), dedicated short range communication (DSRC) or the like or communicates with various server devices via a wireless base station.
The HMI 30 presents various types of information to occupants of the own vehicle M and receives input operations by the occupants. For example, the HMI 30 includes various display devices, speakers, buzzers, touch panels, switches, and keys.
The vehicle sensor 40 includes a vehicle speed sensor that detects a speed of the own vehicle M, an acceleration sensor that detects acceleration, a yaw rate sensor that detects angular velocity around a vertical axis, and an azimuth sensor that detects a direction of the own vehicle M.
The navigation device 50 includes, for example, a global navigation satellite system (GNSS) receiver 51, a navigation HMI 52, and a route determiner 53. The navigation device 50 retains first map information 54 in a storage device such as a hard disk drive (HDD) or a flash memory. The GNSS receiver 51 specifies a position of the own vehicle M based on signals received from GNSS satellites. The position of the own vehicle M may be specified or complemented by an inertial navigation system (INS) using an output of the vehicle sensor 40. The navigation HMI 52 includes a display device, a speaker, a touch panel, and a key. The navigation HMI 52 may be partially or entirely common to the above-described HMI 30. The route determiner 53 determines, for example, a route from a position of the own vehicle M specified by the GNSS receiver 51 (or any input position) to a destination input by an occupant using the navigation HMI 52 (hereinafter referred to as a route on a map) with reference to the first map information 54. The first map information 54 is, for example, information in which a road shape is expressed by links indicating roads and nodes connected by the links. The route on the map is output to the MPU 60. The navigation device 50 may perform route guidance using the navigation HMI 52 based on the route on the map. The navigation device 50 may be realized by, for example, a function of a terminal device such as a smartphone or a tablet terminal possessed by an occupant. The navigation device 50 may transmit a present position and a destination to a navigation server via the communication device 20 to acquire the same route as the route on the map from the navigation server.
The MPU 60 includes, for example, a recommended lane determiner 61 and retains second map information 62 in a storage device such as an HDD or a flash memory. The recommended lane determiner 61 divides the route on the map provided from the navigation device 50 into a plurality of blocks (for example, divides the route in a vehicle movement direction for each 100 [m]) and determines a recommended lane for each block with reference to the second map information 62. The recommended lane determiner 61 determines in which lane the vehicle travels from the left. When there is a branching location in the route on the map, the recommended lane determiner 61 determines a recommended lane so that the own vehicle M can travel in a reasonable route to move to a branching destination.
The second map information 62 is map information that has higher precision than the first map information 54. The second map information 62 includes, for example, information regarding the middles of lanes or information regarding boundaries of lanes. The second map information 62 may include road information, traffic regulation information, address information (address and postal number), facility information, and telephone number information. The second map information 62 may be updated frequently by communicating with another device using the communication device 20.
The driving operator 80 includes, for example, an accelerator pedal, a brake pedal, a shift lever, a steering wheel, a heteromorphic steering wheel, a joystick, and other operators. A sensor that detects whether there is an operation or an operation amount is mounted in the driving operator 80 and a detection result is output to the automated driving control device 100 or some or all of the travel driving power output device 200, the brake device 210, and the steering device 220.
The automated driving control device 100 includes, for example, a first controller 120 and a second controller 190. Each of the first controller 120 and the second controller 190 is realized, for example, by causing a hardware processor such as a central processing unit (CPU) to execute a program (software). Some or all of the constituent elements may be realized by hardware (a circuit unit including circuitry) such as a large scale integration (LSI), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a graphics processing unit (GPU) or may be realized by software and hardware in cooperation. The program may be stored in advance in a storage device (a storage device including a non-transitory storage medium) such as an HDD or a flash memory of the automated driving control device 100 or may be stored in a detachably mounted storage medium (a non-transitory storage medium) such as a DVD, a CD-ROM, or the like so that the storage medium (a non-transitory storage medium) is mounted on a drive device to be installed on the HDD or the flash memory of the automated driving control device 100.
The recognizer 130 includes, for example, an object recognizer 131, a map matcher 132, a first standard range setter 133, a second standard range setter 134, and a target vehicle specifier 140.
The object recognizer 131 recognizes states of a position, a speed, acceleration, and the like of an object near the own vehicle M based on information input from the camera 10, the radar device 12, and the finder 14 via the object recognition device 16. The recognizer 130 recognizes an inter-vehicle distance or the like for each vehicle when a plurality of vehicles are in front of the own vehicle M. For example, the position of the object is recognized as a position of an absolute coordinate system (for example, a vehicle coordinate system) in which is a representative point (a center of gravity, a driving axis center, or the like) of the own vehicle M is the origin and is used for control. The position of the object may be represented as a representative point such as a center of gravity of the object, a middle portion of the front end of the object in the vehicle with direction, or a middle portion, a corner, a side end portion, or the like of the rear end of the object in the vehicle width direction or may be represented as an area. Positions of a plurality of points may be recognized as necessary. The object recognizer 131 may output reliability of the recognition of the object in association with each of the recognized objects. The object recognizer 131 calculates the reliability of the recognition of the object based on a dispersion of distribution of an edge obtained from an image of the camera 10, intensity of a reflected wave detected by the radar device 12, a dispersion of distribution of the intensity of light detected by the finder 14, continuity of recognition of the object, or the like. In the following description, the reliability associated with the object is referred to as object reliability in some cases. The object reliability is output as, for example, quantized information (rank information) such as High, Intermediate, and Low.
The map matcher 132 compares the position of the own vehicle M specified by the navigation device 50, an image captured by the camera 10, an output of an azimuth sensor included in the vehicle sensor 40, or the like with the second map information 62 and recognizes on which road and in which lane the own vehicle M is traveling in the map. Further, based on the foregoing various kinds of information, the map matcher 132 recognizes at which position the representative point of the own vehicle M is in the width direction of the lane (hereinafter referred to as a side position). The side position may be derived as an offset amount from a road demarcation line on one of the right and the left of the lane or may be derived as an offset amount from the middle of the lane. The map matcher 132 recognizes an angle at which a travel direction of the own vehicle M at that time is inclined with respect to the extension direction of the lane (hereinafter referred to as a yaw angle) based on the foregoing various kinds of information. When there is no sufficient matching reliability as a result of the comparison of the position of the own vehicle M specified by the navigation device 50, the image captured by the camera 10, the output of the azimuth sensor included in the vehicle sensor 40, or the like with the map information 62, the map matcher 132 outputs information indicating a matching failure to the first standard range setter 133. A case in which “the comparison cannot be made” also includes a case in which there is no map corresponding to the position of the own vehicle M specified by the navigation device 50.
The first standard range setter 133, the second standard range setter 134, and a predicted runway setter 135 set standard information for setting a range in which the own vehicle M travels from now, that is, a range in which another vehicle has to be particularly monitored after control, in accordance with each different technique. For example, the standard information is used to specify a target vehicle traveling in front of the own vehicle M and is used for control by the own vehicle M. The target vehicle is, for example, a vehicle which is a target following and traveling at intervals of a given inter-vehicle distance. The present invention is not limited thereto and the target vehicle may be a vehicle or the like of which the degree of monitoring is the highest in the front monitoring. The standard information includes, for example, three pieces of information, a first standard range AR1ref, a second standard range AR2ref, and a predicted runway ETJ. For example, each piece of standard information is virtually set to a range on the vehicle coordinate system.
The first standard range setter 133 sets the first standard range AR1ref based on a recognition result of the map matcher 132.
The second standard range setter 134 sets a second standard range AR2ref by analyzing an image IM captured by the camera 10.
The predicted runway setter 135 sets the predicted runway ETJ based on a speed V output by the vehicle speed sensor and a yaw rate Yr output by the yaw rate sensor included in the vehicle sensor 40.
In each of the first standard range AR1ref, the second standard range AR2ref, and the predicted runway ETJ, there are advantages and disadvantages in the standard of the searching range. The first standard range AR1ref can be set precisely up to a distant location. However, since it is assumed that there is a map, measures for a new road cannot be taken. When a recognition result of the map matcher 132 is erroneous despite presence of a map, the range may be erroneous in some cases.
Since the second standard range AR2ref is based on a result obtained by analyzing the image IM of the camera 10, the second standard range AR2ref can be set even in a place where there is no map, but an error occurs in image analysis in some cases. Since the predicted runway ETJ is set based on the yaw rate Yr at the time of setting, the predicted runway ETJ can be set with the degree of precision that there is no map and precision of image analysis degrades due to severe weather in some cases. However, when a start spot or an end spot of a curve is in front of the own vehicle M, it is difficult to set the predicted runway ETJ appropriately on the side more away than that spot.
In view of such circumstances, in the automated driving control device 100 according to the embodiment, the recognizer 130 and the action plan generator 180 can set a searching range within an appropriate range, monitor surroundings, and appropriately specify a target vehicle in cooperation. The details will be described later.
A standard range use determiner 136 determines whether to use the first standard range AR1ref and determine whether to use the second standard range AR2ref.
The target vehicle specifier 140 includes a first target vehicle specifier 142, a second target vehicle specifier 144, and an arbitrator 146. The target vehicle specifier 140 specifies a target vehicle which is a standard of control by the action plan generator 180. For example, a following travel controller 182 of the action plan generator 180 maintains a set distance as a principle of an inter-vehicle distance from the target vehicle and performs so-called following travel in which the own vehicle M travels at a side position with the target vehicle. The set distance may be variable in congestion or the like. The present invention is not limited thereto. The target vehicle may be treated as a main monitoring target which is in front of the own vehicle M. The details of the target vehicle specifier 140 will be described later.
The action plan generator 180 generates a target trajectory along which the own vehicle M travels in future automatedly so that the own vehicle M is traveling along a recommended lane determined by the recommended lane determiner 61 and can handle a surrounding situation of the own vehicle M in principle. The target trajectory includes, for example, a speed component. For example, the target trajectory is expressed by arranging spots (trajectory points) at which the own vehicle M will arrive in sequence. The trajectory point is a spot at which the own vehicle M will arrive for each predetermined travel distance (for example, about several [m]) in a distance along a road. Apart from the trajectory points, target acceleration and a target speed are generated as parts of the target trajectory for each of predetermined sampling times (for example, about a decimal point of a second). The trajectory point may be a position at which the own vehicle M will arrive at the sampling time for each predetermined sampling time. In this case, information regarding the target acceleration or the target speed is expressed according to an interval between the trajectory points.
The action plan generator 180 may set an automated driving event when the target trajectory is generated. As the automated driving event, there are a constant speed traveling event, a following travel event performed by the following travel controller 182, a lane changing event, a branching event, a joining event, a takeover event, and the like. The action plan generator 180 generates the target trajectory in accordance with an activated event.
The second controller 190 controls the travel driving power output device 200, the brake device 210, and the steering device 220 so that the own vehicle M passes along the target trajectory generated by the action plan generator 180 at a scheduled time.
The second controller 190 includes, for example, an acquirer 192, a speed controller 194, and a steering controller 196. The acquirer 192 acquires information regarding the target trajectory (trajectory points) generated by the action plan generator 180 and stores the information in a memory (not illustrated). The speed controller 194 controls the travel driving power output device 200 or the brake device 210 based on a speed element incidental to the target trajectory stored in the memory. The steering controller 196 controls the steering device 220 in accordance with a curve state of the target trajectory stored in the memory. Processes of the speed controller 194 and the steering controller 196 are realized, for example, by combining feed-forward control and feedback control. For example, the steering controller 196 performs the feed-forward control in accordance with a curvature of a road in front of the own vehicle M and the feedback control based on separation from the target trajectory in combination.
The travel driving power output device 200 outputs a travel driving force (torque) for traveling the vehicle to a driving wheel. The travel driving power output device 200 includes, for example, a combination of an internal combustion engine, an electric motor and a transmission, and an electronic control unit (ECU) controlling these units. The ECU controls the foregoing configuration in accordance with information input from the second controller 190 or information input from the driving operator 80.
The brake device 210 includes, for example, a brake caliper, a cylinder that transmits a hydraulic pressure to the brake caliper, an electronic motor that generates a hydraulic pressure to the cylinder, and a brake ECU. The brake ECU controls the electric motor in accordance with information input from the second controller 190 or information input from the driving operator 80 such that a brake torque in accordance with a brake operation is output to each wheel. The brake device 210 may include a mechanism that transmits a hydraulic pressure generated in response to an operation of the brake pedal included in the driving operator 80 to the cylinder via a master cylinder as a backup. The brake device 210 is not limited to the above-described configuration and may be an electronic control type hydraulic brake device that controls an actuator in accordance with information input from the second controller 190 such that a hydraulic pressure of the master cylinder is transmitted to the cylinder.
The steering device 220 includes, for example, a steering ECU and an electric motor. The electric motor works a force to, for example, a rack and pinion mechanism to change a direction of a steering wheel. The steering ECU drives the electric motor to change the direction of the steering wheel in accordance with information input from the second controller 190 or information input from the driving operator 80.
Hereinafter, specifying of a target vehicle will be described.
Information regarding positions or the like of objects (hereinafter referred to as other vehicles), the first standard range AR1ref, the second standard range AR2ref, a non-use flag, and feedback of first target vehicle information output by the first target vehicle specifier 142 at a previous process cycle are input to the first target vehicle specifier 142. The first target vehicle specifier 142 outputs the first target vehicle information based on the information. The first target vehicle information is information for specifying one of the other vehicles of which the positions or the like are input to the target vehicle specifier 140.
Information regarding positions or the like of the other vehicles, the predicted runway ETJ, the non-use flag, and feedback of second target vehicle information output by the second target vehicle specifier 144 at a previous process cycle are input to the second target vehicle specifier 144. The second target vehicle specifier 144 outputs the second target vehicle information based on the information. The second target vehicle information is information for specifying one of the other vehicles of which the positions or the like are input to the target vehicle specifier 140.
The first target vehicle information, the second target vehicle information, previous interruption target vehicle information, and a use or non-use flag are input to the arbitrator 146. The arbitrator 146 selects one of the first target vehicle information and the second target vehicle information and outputs the selected information to the following travel controller 158.
Each of the first target vehicle specifier 142 and the second target vehicle specifier 144 uniquely sets a reference range and specifies a target vehicle within the reference range. As the reference range, there are an initial searching range and a tracking range. The initial searching range is a range that is applied to other vehicles (target vehicle candidates) recognized initially at a current process cycle among processes of specifying the target vehicle repeatedly. The tracking range is a range that is applied to vehicles recognized at a previous process cycle. As the initial searching range, there are a first initial searching range, a second initial searching range, and a third initial searching range. As the tracking range, there are a first tracking range, a second tracking range, and a third tracking range. The first initial searching range or the first tracking range is an example of a “first reference range, the second initial searching range or the second tracking range is an example of a “second reference range, and the third initial searching range or the third tracking range is an example of a “third reference range.”
The first target vehicle specifier 142 performs one of setting the first initial searching range AR1-1 and the first tracking range AR1-2 based on the first standard range AR1ref and setting of a second initial searching range AR2-1 and a second tracking range AR2-2 based on the second standard range AR2ref. When the first standard range AR1ref is input and the non-use flag is not input (hereinafter this case is referred to as a case of “map presence”), the first target vehicle specifier 142 sets the first initial searching range AR1-1 and the first tracking range AR1-2. On the other hand, when the first standard range AR1ref is not input or when the first standard range AR1ref is input and the non-use flag is input (hereinafter this case is referred to as a case of “map absence”), the first target vehicle specifier 142 sets the second initial searching range AR2-1 and the second tracking range AR2-2 based on the second standard range AR2ref. Hereinafter, a case in which the first standard range AR1ref is input and the non-use flag is input is referred to as a “case of non-use of the first standard range” in some cases.
As described above, the lengths of the first initial searching range AR1-1 and the first tracking range AR1-2 is set to X1 [m] and the lengths of the second initial searching range AR2-1 and the second tracking range AR2-2 are set to X2 [m]. Both X1 and X2 are values set in accordance with a speed of the own vehicle M and are values that are larger when the speed is larger. X1 and X2 are set so that X1>X2 are satisfied. In X1 and X2, lower limits may be provided.
The length of the third initial searching range AR3-1m in the case of “map presence” is X3 and the length of the third tracking range AR3-2m is a range obtained by adding the tracking margin TMX to X3. X3 is a function of the predicted radius of curvature R and the speed V, is longer as the predicted radius of curvature R is larger, and is longer as the speed V is faster. Here, X3 is set so that X1>(X3+TMX) is satisfied. In X3, a lower limit may be provided.
The length of the third initial searching range AR3-1c in the case of “map absence” is X4 and the length of the third tracking range AR3-2c is a range obtained by adding the tracking margin TMX to X4. X4 is a function of the predicted radius of curvature R and the speed V, is longer as the predicted radius of curvature R is larger, and is longer as the speed V is faster. When the input predicted radius of curvature R and the speed V are the same, X4 is greater than X3. Here, X4 is set so that X1>(X4+TMX) is satisfied. In X4, a lower limit may be provided.
As described above, the target vehicle specifier 140 sets the reference range to a more distant location when the reference range is set based on map information (for example, the second map information 62) than when the reference range is set irrespective of the map information. The fact that “the reference range is set based on the map information” is that, for example, “the reference range is set based on the first standard range AR1ref set based on the map information.” Through the process, the target vehicle specifier 140 monitors up to a distant location when the reference range is set using the map information of which an error is relatively small, and limits monitoring of the distant location when the reference range is set using a camera image or a yaw rate of which an error is relatively large. Therefore, it is possible to realize early discovery of a target vehicle and suppression of erroneous detection.
Next, a width of each reference range will be described. The width of the first initial searching range AR1-1 is set to a width obtained by adding a tracking margin to a lane width on a map and a width of the first tracking range AR1-2 is set to a width obtained by adding the tracking margin to the lane width on the map. A width of the second initial searching range AR2-1 is set to a width obtained by adding the tracking margin to a lane width converted from a camera image and a width of the second tracking range AR2-2 is set to a width obtained by adding the tracking margin to a lane width converted from a camera image.
In the case of “map presence,” a width of the third initial searching range AR3-1m is set to Y1 and the width of the third tracking range AR3-2m is set to Y3. Y1<Y3 is satisfied. In the case of “map absence,” a width of the third initial searching range AR3-1c is set to Y2 and a width of the third tracking range AR3-2c is set to Y4. Y2<Y4 is satisfied. Y3<Y4 is satisfied and Y4 is set to a value greater than a general lane width.
In this way, the second target vehicle specifier 144 sets the width of the third reference range to be larger when the first target vehicle specifier 142 sets the second reference range irrespective of map information (for example, the second map information 62) than when the first target vehicle specifier 142 sets the first reference range based on the map information. Thus, it is possible to specify a target vehicle in accordance with a complementary relation in which an influence of a specifying result in the third reference range on the control is caused to be small when the target vehicle is specified based on a map with high precision and the influence of the specifying result in the third reference range on the control is caused to be large when the target vehicle is specified based on a camera image with low precision.
Hereinafter, complementary monitoring control performed under the setting will be described.
The first target vehicle specifier 142 searches for other vehicles which have not been recognized at a previous process cycle within the first initial searching range AR1-1 and traces other vehicles which have been recognized at the previous process cycle within the first tracking range AR1-2. Then, of another vehicle newly found within the first initial searching range AR1-1 and still another vehicle captured within the first tracking range AR1-2, the other vehicle close to the own vehicle M in a length direction of a road is specified as a first target vehicle. In the drawing, a vehicle mA1 is another vehicle newly found within the first initial searching range AR1-1. At a subsequent process cycle, the vehicle mA1 is traced within the first tracking range AR1-2 broader than the first initial searching range AR1-1. In this way, the target vehicle specifier 140 first performs initial searching for a vehicle in a narrow range and traces a vehicle which has been found once in a broader range, and thus it is possible to suppress inconvenience of control due to erroneous detection and to take flexible measure for wandering or the like of a target vehicle.
In parallel, the second target vehicle specifier 144 searches for another vehicle which has not been recognized at the previous process cycle within the third initial searching range AR3-1m and captures still another vehicle which has been recognized at the previous process cycle within the third tracking range AR3-2m. Then, of another vehicle which has newly been found within the third initial searching range AR3-1m and still another vehicle which has been captured within the third tracking range AR3-2m, the other vehicle close to the own vehicle M in the length direction of the road is specified as a second target vehicle. In the example of
In parallel, the second target vehicle specifier 144 searches for another vehicle which has not been recognized at the previous process cycle within the third initial searching range AR3-1c and captures still another vehicle which has been recognized at the previous process cycle within the third tracking range AR3-2c. Then, of another vehicle has newly been found within the third initial searching range AR3-1c and still another vehicle captured within the third tracking range AR3-2c, the other vehicle close to the own vehicle M in the length direction of the road is specified as the second target vehicle. This operation is similar to the operation in the case of “map presence.” However, to compensate for the second initial searching range AR2-1 and the second tracking range AR2-2 less than the first initial searching range AR1-1 and the first tracking range AR1-2, respectively, the third initial searching range AR3-1c and the third tracking range AR3-2c in the case of “map absence” are set to be greater than the third initial searching range AR3-1c and the third tracking range AR3-2c in the case of “map presence” when a condition such as the speed VM or the predicted radius of curvature R is the same. Thus, the first target vehicle specifier 142 and the second target vehicle specifier 144 can improve specifying precision of the target vehicle in the complementary relation. In the example of
As described above, the first target vehicle specifier 142 and the second target vehicle specifier 144 operate in parallel. The first target vehicle specifier 142 outputs the first target vehicle information and the second target vehicle specifier 144 outputs the second target vehicle information. The first target vehicle information and the second target vehicle information include identification information (an object ID), a position, and a speed of the specified target vehicle. The object ID is information serving as a label of information such as the position of the object input to the target vehicle specifier 140. When the first target vehicle information matches the second target vehicle information, the target vehicle specifier 140 outputs the matched information as target vehicle information. When the first target vehicle information does not match the second target vehicle information, the arbitrator 146 performs the following process to select any target vehicle information.
When the first target vehicle information differs from the second target vehicle information in the case of “map presence,” the arbitrator 146 performs a first arbitration flow in which the first target vehicle information is preferred under a predetermined condition. When no target vehicle is confirmed in the first arbitration flow, a target vehicle is confirmed in a third arbitration flow. When the first target vehicle information differs from the second target vehicle information in the case of “map absence,” the arbitrator 146 performs a second arbitration flow in which a target vehicle is confirmed in a case in which there is only one. When no target vehicle is confirmed in the second arbitration flow, a target vehicle is confirmed in accordance with the third arbitration flow.
First, the arbitrator 146 determines whether the non-use flag is input from the standard range use determiner 136 (step S100). When the non-use flag is input, the arbitrator 146 determines the second target vehicle information as target vehicle information and outputs the target vehicle information to the action plan generator 180 (step S110).
When the non-use flag is not input, the arbitrator 146 determines whether the first target vehicle information is the same as the second target vehicle information (step S102). When the first target vehicle information is the same as the second target vehicle information, the arbitrator 146 determines the first target vehicle information as target vehicle information and outputs the target vehicle information to the action plan generator 180 (step S108).
When the first target vehicle information is not the same as the second target vehicle information, the arbitrator 146 determines whether the position of the first target vehicle is located to be more distant than the length of the third initial searching range or the third tracking range (step S104). When the position of the first target vehicle is located to be more distant from the length of the third initial searching range or the third tracking range, the arbitrator 146 determines the first target vehicle information as the target vehicle information and outputs the target vehicle information to the action plan generator 180 (step S108).
When the position of the first target vehicle is not located to be more distant than the length of the third initial searching range or the third tracking range, the arbitrator 146 determines whether the first target vehicle is a vehicle (a previous interruption target) selected as the first target vehicle for the first time at the previous process cycle (step S106). When the first target vehicle is the previous interruption target, the arbitrator 146 determines the first target vehicle information as the target vehicle information and outputs the target vehicle information to the action plan generator 180 (step S108). When the first target vehicle is not the previous interruption target, the process proceeds to the third arbitration flow.
When the non-use flag is not input, the arbitrator 146 determines whether the first target vehicle information is the same as the second target vehicle information (step S122). When the first target vehicle information is the same as the second target vehicle information, the arbitrator 146 determines the first target vehicle information as target vehicle information and outputs the target vehicle information to the action plan generator 180 (step S128).
When the first target vehicle information is not the same as the second target vehicle information, the arbitrator 146 determines whether there is only the first target vehicle (the first target vehicle is specified and information is output) (step S124). When there is only the first target vehicle, the arbitrator 146 determines the first target vehicle information as the target vehicle information and outputs the target vehicle information to the action plan generator 180 (step S128).
When there is only no first target vehicle, the arbitrator 146 determines whether there is only the second target vehicle (the second target vehicle is specified and information is output) (step S126). When there is only the second target vehicle, the arbitrator 146 determines the second target vehicle information as the target vehicle information and outputs the target vehicle information to the action plan generator 180 (step S130). When there is only no second target vehicle, the process proceeds to the third arbitration flow.
In comparison between the process of the flowchart of
Subsequently, the arbitrator 146 determines whether the second target vehicle is the same vehicle continuously n2 times (n2 cycle) or more (step S146). When the second target vehicle is the same vehicle continuously n2 times or more, the arbitrator 146 sets an inter-vehicle distance with the second target vehicle as a second inter-vehicle distance (step S148). When the second target vehicle is not the same vehicle continuously n2 times or more, the arbitrator 146 sets an inter-vehicle distance MAX value 2 as a second inter-vehicle distance (step S150).
The thresholds n1 and n2 may be the same values or may be different values. For example, about several values or tens of values may be set in advance in n1 and n2. Inter-vehicle MAX value 1 and the inter-vehicle MAX value 2 are values sufficiently larger than an inter-vehicle distance with a vehicle recognized within a reference range. Inter-vehicle MAX value 1 and the inter-vehicle MAX value 2 may be the same value or may be different values.
Subsequently, the arbitrator 146 determines which is smaller between the first inter-vehicle distance and the second inter-vehicle distance (step S152). When the first inter-vehicle distance is smaller, the arbitrator 146 determines the first target vehicle information as the target vehicle information and outputs the target vehicle information to the action plan generator 180 (step S154). When the second inter-vehicle distance is smaller, the arbitrator 146 determines the second target vehicle information as the target vehicle information and outputs the target vehicle information to the action plan generator 180 (step S156).
The arbitrator 146 may acquire reliability of the second standard range AR2ref output by the second standard range setter 134 and change content of the process so that it is easy to select the second target vehicle in the case of “map absence” when the reliability is lower than a standard. For example, by changing the threshold n2 to a smaller value, changing the threshold n1 to a larger value, changing inter-vehicle distance MAX value 2 to a smaller value, or changing inter-vehicle distance MAX value 1 to a larger value, it is possible to easily select the second target vehicle.
The second target vehicle specifier 144 may exceptionally expand the length of the reference range and cause the length of the reference range to be longer than that of the first target vehicle specifier 142 in accordance with the speed VM when the own vehicle M continuously moves straight in a state in which a yaw rate is continuously equal to or less than a predetermined value near zero, that is, in a state in which a degree of turning is within a standard in the case of “map absence.” Hereinafter, the operation is referred to as expansion at the time of straight travel.
According to the above-described first embodiment, it is possible to realize early discovery of a target vehicle and suppression of erroneous detection.
Hereinafter, a second embodiment will be described.
The interruption vehicle specifier 150 performs interruption to a travel lane from a lateral side (a road width direction) of the travel lane in which there is the own vehicle M and specifies another vehicle which is a future target vehicle as an interruption vehicle. The interruption vehicle specifier 150 includes a first interruption vehicle specifier 160 and a second interruption vehicle specifier 170. For example, the first interruption vehicle specifier 160 operates regardless of a speed of the own vehicle M and the second interruption vehicle specifier 170 operates when the speed of the own vehicle M is less than a predetermined speed Vth (for example, about 20 [km/h]), that is, at the time of low-speed travel such as the time of congestion. Accordingly, when the speed of the own vehicle M is less than the predetermined speed Vth, both the first interruption vehicle specifier 160 and the second interruption vehicle specifier 170 operate. When the speed of the own vehicle M is equal to or greater than the predetermined speed Vth, the first interruption vehicle specifier 160 operates and the second interruption vehicle specifier 170 stops operating.
The first interruption vehicle specifier 160 includes, for example, an interruption vehicle candidate extractor 161, a side position recognizer 162, a threshold determiner 163, a first determiner 164, and a first control transition ratio deriver 165. The first interruption vehicle specifier 160 performs preliminary determination (determination of a first stage) and main determination (determination of a second stage). A vehicle determined as an interrupt vehicle in the preliminary determination is referred to as a preliminary interruption vehicle and a vehicle determined as an interruption vehicle in the main determination is referred to as an interruption vehicle.
The interruption vehicle candidate extractor 161 extracts another vehicle which is in a lateral side reference range extending to the lateral side of a travel lane as a preliminary interruption vehicle or a candidate vehicle of the interruption vehicle (an interruption vehicle candidate).
The interruption vehicle candidate extractor 161 determines whether another vehicle is extracted as an interruption vehicle candidate based on presence or absence of a lane in a range of an interruption source (a range corresponding to the lane L2 in the example of
In the second embodiment, the non-use flag output by the standard range use determiner 136 may be input to the first interruption vehicle specifier 160. Thus, the interruption vehicle candidate extractor 161 may not extract the interruption vehicle candidate when the non-use flag is input in both the case of “map presence” and the case of “map absence.”
The side position recognizer 162 recognizes a side position of the vehicle extracted as the interruption vehicle candidate. Referring back to
The first interruption vehicle specifier 160 specifies the interruption vehicle candidate as a preliminary interruption vehicle or an interruption vehicle when a side movement amount by which the interruption vehicle candidate in the lateral side reference range ARs heads for the lane L1 in the road width direction exceeds a threshold during a predetermined period. At this time, the first determiner 164 determines whether the side movement amount exceeds the threshold during each of a plurality of predetermined periods in which a traceback amount from the observation time point to the past is different. “How much the cycle goes back,” as described above, is an example of “the traceback amount from the observation time point to the past.” EY0, EY1, . . . , EYn are examples of “the side movement amount by which the interruption vehicle candidate in the lateral side reference range ARs heads for the lane L1 in the road width direction during the plurality of predetermined periods in which the traceback amount from the observation time point to the past is different.”
iEYn=EYn−EY0 (1)
For example, the side position recognizer 162 calculates iEYn in each of n=2, 3, and 5. That is, iEY2, iEY3, and iEY5 are calculated. A method of selecting the numbers is merely exemplary. Any natural number equal to or greater than 2 may be selected from natural numbers. In the following description, 2, 3, and 5 are assumed to be selected.
The threshold determiner 163 determines a threshold for each of n=2, 3, and 5. Further, the threshold determiner 163 sets a threshold α (an example of a first threshold) for the preliminary determination (the determination of the first stage) and a threshold β (an example of a second threshold) for the main determination (the determination of the second stage). Six kinds of thresholds are set to set the thresholds α and β for n=2, 3, and 5 to correspond to the preliminary determination and the main determination. Hereinafter, a threshold corresponding to the preliminary determination and n=2, a threshold corresponding to the preliminary determination and n=3, and a threshold corresponding to the preliminary determination and n=5 are defined as α2, α3, and α5, respectively. A threshold corresponding to the main determination and n=2, a threshold corresponding to the main determination and n=3, and a threshold corresponding to the main determination and n=5 are defined as β2, β3, and β5, respectively.
The first determiner 164 determines whether iEY is equal to or greater than a threshold αn for each of n=2, 3, and 5 as a specifying process of the first stage. When a predetermined number k or more indicates that “a side movement amount iEYn is greater than the threshold αn” among a plurality of determination results, the first determiner 164 specifies the interruption vehicle candidate as a preliminary interruption vehicle. The first determiner 164 determines whether iEYn is equal to or greater than a threshold βn for each of n=2, 3, and 5 as a specifying process of the second stage. When a predetermined number k or more indicates that “a side movement amount iEYn is greater than the threshold βn” among a plurality of determination results, the first determiner 64 specifies the interruption vehicle candidate as an interruption vehicle. The predetermined number k is, for example, 1, but may be 2 or more.
For another vehicle specified as the preliminary interruption vehicle, the following travel controller 182 generates trajectory points so that, for example, weak braking is performed. For another vehicle specified as the interruption vehicle, the following travel controller 182 determines a target speed and outputs the target speed to the second controller 190 so that braking stronger than that of the preliminary interruption vehicle is performed. The details thereof will be described later.
The threshold determiner 163 determines the thresholds α and β using a threshold determination map 167.
The threshold determination map 167 shows the following tendency as a whole.
(1) The characteristic lines Lα and Lβ rise to the right. Accordingly, in a case in which the interruption vehicle candidate is traveling at a position close to the lane L1 in the road width direction, that is, EY0 is small, the threshold determiner 163 determines the thresholds as the smaller threshold than when EY0 is large. As a result, when the interruption vehicle candidate is traveling at the position close to the lane L1 in the road width direction, it is easier to specify the preliminary interruption vehicle or the interruption vehicle despite a small change amount of the side position more than when the interruption vehicle candidate is traveling at a position away from the lane L1. Thus, it is possible to take quick measures for a change in the side position with respect to another vehicle traveling close to the own lane. For the other vehicle traveling at the position away from the own lane, the preliminary interruption vehicle or the interruption vehicle is specified only when a change in the side position is large. Therefore, it is possible to reduce an occasion of occurrence of unnecessary control.
(2) The characteristic lines Lα and Lβ are both shifted upward as n increases. Accordingly, the threshold determiner 163 causes a threshold (a threshold when n is large) during a predetermined period in which a traceback amount to the past is large to be greater than a threshold (a threshold when n is small) during a predetermined period in which the traceback amount to the past is small. Thus, the preliminary interruption vehicle or the interruption vehicle can be specified quickly when a change in the side position occurs in the other vehicle (when iEYn in which n is small increases). In a gentle change in the side position, the preliminary interruption vehicle or the interruption vehicle is not specified when there is no continuity to some extent. Therefore, it is possible to reduce an occasion of occurrence of unnecessary control.
(3) The characteristic lines Lα and Lβ are separated to the side in which EY0 is small when n is small. As a result, in a case in which the interruption vehicle candidate is traveling at a position close to the lane L1 in the road width direction, the preliminary interruption vehicle is specified quickly. As a result, it is possible to take quick measures for a behavior of a vehicle close to the own vehicle M.
(4) The characteristic lines Lα and Lβ are separated to the side in which EY0 is large when n is large. As a result, in a case in which the interruption vehicle candidate is traveling at a position away from the lane L1 in the road width direction, the interruption vehicle is not specified when a change amount of the side position is not large. As a result, it is possible to suppress frequent occurrence of unnecessary control on the vehicle away from the own vehicle M.
In this way, by obtaining a change amount of each side position during a predetermined period in which the traceback amount to the post is different and comparing each change amount with a different threshold, it is possible to appropriately specify another vehicle in which a pattern of a motion is different as an interruption vehicle.
The first control transition ratio deriver 165 derives a control transition ratio ξ to be given to the following travel controller 182. When there are a front vehicle and the preliminary interruption vehicle or the interruption vehicle, the following travel controller 182 determines a target speed so that braking power for the front vehicle and braking power for the preliminary interruption vehicle or the interruption vehicle are mixed and output at the control transition ratio ξ.
Rσ=1/{1+e{circumflex over ( )}{−κ×(λ×EYN−μ)}
EYN=(EYMAX−EY0)/EYMAX (2)
The following travel controller 182 derives, for example, a target speed for keeping an inter-vehicle distance to a set distance with regard to each of the front vehicle, the interruption vehicle, and the preliminary interruption vehicle. Hereinafter, the front vehicle, the interruption vehicle, and the preliminary interruption vehicle are denoted by mA, mB, and mC, respectively.
For example, the following travel controller 182 derives target speed V #1 for the front vehicle mA in accordance with Expression (3), derives target speed V #2 for the interruption vehicle mB in accordance with Expression (4), and derives target speed V #3 for the preliminary interruption vehicle mC in accordance with Expression (5). In the expressions, Vset denotes an upper limit speed, xset denotes a set distance, and VFB1 and VFB2 denote functions representing feedback control. xmA is a distance between the front end of the own vehicle M and the rear end of the front vehicle mA (a so-called inter-vehicle distance), xmB in a road length direction is a distance between the front end of the own vehicle M and the rear end of the interruption vehicle mB in the road length direction, and xmC is a distance between the front end of the own vehicle M and the rear end of the preliminary interruption vehicle mC in the road length direction. A feedback gain (particular, a gain of a proportional term and an integration term) when VFB1 is calculated is set to be larger than when VFB2 is calculated. Therefore, when the inter-vehicle distance is a distance less than the set distance xset, declaration for the front vehicle mA and the interruption vehicle mB is larger than deceleration for the preliminary interruption vehicle mC.
V#1=MAX{Vset,VFB1(xmA→xset)} (3)
V#2=MAX{Vset,VFB1(xmB→xset)} (4)
V#3=MAX{Vset,VFB2(xmC→xset)} (5)
Then, the following travel controller 182 derives a target speed V # of the own vehicle M by mixing each target speed at a control transition ratio. The following travel controller 182 obtains the target speed V # of the case in which there are the front vehicle and the interruption vehicle in accordance with Expression (6) and obtains the target speed V # of the case in which there are the front vehicle and the preliminary interruption vehicle in accordance with Expression (7). Thus, the speed of the own vehicle M is controlled at a ratio in accordance with the control transition ratio ξ. In preparation for the case in which the target speed V # is considerably less than the current speed VM, an upper limit guard for deceleration may be provided.
V#=(1−ξ)×V#1+ξ×V#2 (6)
V#=(1−ξ)×V#1+ξ×V#3 (7)
To perform relatively weak braking on the preliminary interruption vehicle by causing the feedback gain to be different is merely exemplary. The following travel controller 182 may obtain target deceleration to keep the inter-vehicle distance to the set distance with respect to each of the front vehicle, the interruption vehicle, and the preliminary interruption vehicle and mix the target deceleration at the control transition ratio ξ.
First, the interruption vehicle candidate extractor 161 sets the lateral side reference range ARs (step S200) and extracts the interruption vehicle candidate within the lateral side reference range ARs (step S202). The interruption vehicle candidate extractor 161 determines whether to extract one or more interruption candidate vehicles (step S204). When no interruption candidate vehicle can be extracted, the process of one cycle of the flowchart ends.
When one or more interruption vehicle candidates can be extracted, the side position recognizer 162 calculates the side position EY0 of the interruption candidate vehicle and the change amount iEYn of the side position (step S206). Subsequently, the threshold determiner 163 determines the thresholds αn and βn based on the side position EY0 (step S208).
Subsequently, the first determiner 164 compares the change amount iEYn of the side position for all of n to be noticed (in the above-described example, n=2, 3, and 5) with the threshold αn (step S210). The first determiner 164 determines whether the change amount iEYn of the side position in the determination of k times or more is equal to or greater than the threshold αn (step S212). As described above, k may be 1 or may be 2 or more. When the change amount iEYn of the side position in the determination of k times is not equal to or greater than the threshold αn, the process of one cycle of the flowchart ends.
When the change amount iEYn of the side position in the determination of k times is equal to or greater than the threshold αn, the first determiner 164 compares the change amount iEYn of the side position for all of n to be noticed with the threshold βn (step S214). The first determiner 164 determines whether the change amount iEYn of the side position in the determination of k times or more is equal to or greater than the threshold βn (step S216).
When the change amount iEYn of the side position in the determination of k times is equal to or greater than the threshold βn, the first determiner 164 specifies the interruption vehicle candidate as the interruption vehicle (step S218). When the change amount iEYn of the side position in the determination of k times is not equal to or greater than the threshold βn, the first determiner 164 specifies the interruption vehicle candidate as the preliminary interruption vehicle (step S220). Then, the first control transition ratio deriver 165 derives the control transition ratio ξ (step S222).
The first interruption vehicle specifier 160 according to the above-described second embodiment can specify the interruption vehicle more appropriately.
As described above, the thresholds α and β are set in accordance with only the side position of another vehicle, but at least one of the thresholds α and β may be determined based on a type or attribute of another vehicle. The type of vehicle is a two-wheeled vehicle, a four-wheeled vehicle, or a special vehicle and the attribute is a light duty vehicle, a passenger car, a heavy vehicle, a truck, or the like. In this case, the object recognizer 131 recognizes a type or an attribute of another vehicle based on content described in the size or a registration number of the other vehicle and delivers the type or the attribute of the other vehicle to the first interruption vehicle specifier 160. For example, the threshold determiner 163 causes the thresholds for a special vehicle or a heavy vehicle for which a sense or pressure felt by an occupant of the own vehicle M is large at the time of approach to be less than those for other vehicles. For example, the threshold determiner 163 causes the thresholds for a two-wheeled vehicle of which a behavior is more agile than a four-wheeled vehicle to be less than those of a four-wheeled vehicle.
At least one of the thresholds α and β may be determined based on a travel environment, a travel state, or a control state of the own vehicle M. The travel environment is a radius of curvature or a gradient of a road μ, or the like. The travel state includes, for example, a speed of the own vehicle M. The control state is, for example, a state indicating whether automated driving is performed or whether driving support is performed. For example, when the radius of curvature is small or the gradient or speed is large, the threshold determiner 163 causes the thresholds to be smaller than otherwise. When automated driving is performed, the threshold determiner 163 causes the thresholds to be smaller than otherwise. Further, a set range of the lateral side reference range may also be changed based on the travel environment, the travel state, or the control state of the own vehicle M.
As illustrated in
The interruption vehicle candidate extractor 171 extracts another vehicle which is in a lateral side reference range as a preliminary interruption vehicle or a candidate vehicle of the interruption vehicle (an interruption vehicle candidate) as in the interruption vehicle candidate extractor 161. A lateral side reference range set by the interruption vehicle candidate extractor 171 may be similar to or different from the lateral side reference range set by the interruption vehicle candidate extractor 161.
The vehicle posture recognizer 172 recognizes an angle formed between a direction of the body of an interruption vehicle candidate and a standard direction. The standard direction is, for example, an extension direction of the lane L1 in which there is the own vehicle M. The extension direction of the lane is, for example, a central line of a lane, but may be an extension direction of a road demarcation line of one of the right and left lines.
Instead of the above, the vehicle posture recognizer 172 may recognize an extension direction of a side surface mBss of the vehicle mB as the direction of the body of the vehicle mB or may recognize a direction going straight in an extension direction of a rear surface mBrs of the vehicle mB within the horizontal plane as the direction of the body of the vehicle mB. When the vehicle posture recognizer 172 recognizes the extension direction of the side surface mBss or the extension direction of the rear surface mBrs, the vehicle posture recognizer 172 may define an extension direction of a side surface in accordance with any conversion expression or recognize a straight line binding portions at symmetric positions in the case of the rear surface as the extension direction since the side surface or the rear surface of a general vehicle is roundish. The vehicle posture recognizer 172 may simply approximate a curved surface or a curved line to a planar surface or a straight line. The vehicle posture recognizer 172 outputs an angle ϕ between the recognized direction of the body and the central line CL of the lane to the preliminary operation determiner 173.
Based on the angle ϕ recognized by the vehicle posture recognizer 172, the preliminary operation determiner 173 determines whether the interruption vehicle candidate is a preliminary interruption vehicle. For example, when a state in which a change amount Δϕ of the angle ϕ between process cycles is equal to or greater than a threshold Thϕ continues at m cycles or more (an example of a “predetermined period or more”), the preliminary operation determiner 173 specifies the interruption vehicle candidate as a nominal interruption vehicle.
The prohibition range entrance determiner 174 sets a prohibition range in front of the own vehicle M. When the interruption vehicle candidate enters the prohibition range, the interruption vehicle candidate is specified as an interruption vehicle.
The prohibition range entrance determiner 174 sets the prohibition range BA, for example, using a range occupied by the lane L1 in which there is the own vehicle M as a standard. For example, the prohibition range BA is set to reach up to the lane L2 beyond a road demarcation line SLr by using a road demarcation line SL1 opposite to the lane L2 in which a lateral side reference range is set between the road demarcation lines SL1 and SLr demarcating the lane L1 as one end. Accordingly, a width Y5 of the prohibition range BA is greater than a general lane width and is set in advance to a value less than a double of the general vehicle width. When the lateral side reference range is on the right side of the lane L1 and the lane L2 is not present (when a range corresponding to the lane L2 is a shoulder of a road), the prohibition range entrance determiner 174 may reduce the width of the prohibition range BA to a width corresponding to the width of the lane L1.
In principle, the prohibition range entrance determiner 174 sets the length X5 of the prohibition range BA to a short length between a fixed length of about several [m] and a length from a rear end mAr of a front vehicle mA immediately before the own vehicle M in the lane L1 to a position shifted to the front side by a travel amount ΔXmA of the front vehicle mA. In
The prohibition range entrance determiner 174 specifies the interruption vehicle candidate of which a part of the body enters to the prohibition range BA as an interruption vehicle.
The second control transition ratio deriver 175 derives a control transition ratio η to be given to the following travel controller 182. When there are the front vehicle and the preliminary interruption vehicle or the interruption vehicle, the following travel controller 182 determines a target speed so that braking power for the front vehicle or braking power for the preliminary interruption vehicle or the interruption vehicle are mixed at the control transition ratio η to be output.
The following travel controller 182 derives, for example, a target speed for keeping an inter-vehicle distance to a set distance with regard to each of the front vehicle, the interruption vehicle, and the preliminary interruption vehicle. On the other hand, the content described for the first interruption vehicle specifier 160 is cited by replacing the control transition ratio ξ with the control transition ratio η.
Further, when there is a vehicle specified as the interruption vehicle by the second interruption vehicle specifier 170 and the own vehicle M is stopping, the following travel controller 182 may maintain the stop state of the own vehicle M (does not launch the own vehicle M) irrespective of the derived target speed. Thus, it is possible to realize automated driving gentle for nearby vehicles.
A case in which both the first interruption vehicle specifier 160 and the second interruption vehicle specifier 170 specify the same other vehicle as the preliminary interruption vehicle or the interruption vehicle can be considered. In this case, for example, the following travel controller 182 may adopt a lower speed between the target speeds derived based on results of both the first interruption vehicle specifier 160 and the second interruption vehicle specifier 170 or may adopt larger braking power between braking powers derived based on results of both the first interruption vehicle specifier 160 and the second interruption vehicle specifier 170.
First, the interruption vehicle candidate extractor 171 sets a lateral side reference range (step S300) and extracts an interruption vehicle candidate within the lateral side reference range (step S302). The interruption vehicle candidate extractor 171 determines whether one or more interruption candidate vehicles can be extracted (step S304). When no interruption candidate vehicles can be extracted, the process of one cycle in the flowchart ends.
When one or more interruption vehicle candidates can be extracted, the prohibition range entrance determiner 174 performs the processes of steps S306 and S308 and the preliminary operation determiner 173 performs the processes of steps S310 to S314 in parallel.
The prohibition range entrance determiner 174 determines whether the interruption vehicle candidate enters the prohibition range BA (step S306). When the interruption vehicle candidate enters the prohibition range BA, the prohibition range entrance determiner 174 specifies the interruption vehicle candidate as the interruption vehicle (step S308).
On the other hand, the preliminary operation determiner 173 recognizes the angle ϕ described above for the interruption vehicle candidate (step S310), derives the change amount Δϕ of the angle (step S312), and determines whether a state in which the change amount Δϕ is equal to or greater than the threshold Thϕ continues at m cycles or more (step S314). When the state in which the change amount Δϕ is equal to or greater than the threshold Thϕ continues at m cycles or more, the preliminary operation determiner 173 specifies the interruption vehicle candidate as the preliminary interruption vehicle (step S316).
Then, the second control transition ratio deriver 175 derives the control transition ratio η (step S318).
The second interruption vehicle specifier 170 according to the above-described second embodiment can specify the interruption vehicle more appropriately at the time of a low speed.
The vehicle posture recognizer 172 may recognize a difference between side positions of a first standard point and a second standard point of the interruption vehicle candidate instead of recognizing the above-described angle ϕ. For example, the first standard point is a middle of a front end and the second standard point is a center of gravity, a center of a rear wheel shaft, a middle of a rear end, or the like. The first standard point and the second standard point may be on a shaft line in the front and rear directions of the body. For example, the first standard point may be a front end of a left side surface and the second standard point may be a rear end of the left side surface in combination, or the first standard point may be a front end of a right side surface and the second standard point may be a rear end of the right side surface in combination.
In the foregoing description, a case in which there is no road demarcation line between a range of an interruption source and a runway in which the own vehicle M is traveling has not been mentioned. In this case, a virtual line may be set at a position corresponding to a road demarcation line and similar processes to the above-described processes may be performed.
In the foregoing description, it is assumed that the vehicle control device is applied to the automated driving control device. However, the vehicle control device may be applied to a driving support device or the like that mainly performs so-called adaptive cruise control (ACC), that is, inter-vehicle distance control or constant-speed travel control.
The above-described embodiment can be expressed as follows:
a vehicle control device including a storage device that stores a program and a hardware processor, the hardware processor reading the program from the storage device and executing the program,
to recognize a surrounding situation of a vehicle;
to specify a target vehicle which is a control target of the vehicle within a set reference range based on a recognition result of the recognizer; and
to control at least one of an acceleration or deceleration speed and steering of the vehicle based on a position of the specified target vehicle,
wherein, when the target vehicle is specified,
the target vehicle is specified in a reference range based on lane information and first target vehicle information is output,
specifying the target vehicle in a reference range based on a behavior of the vehicle and outputting second target vehicle information are performed in parallel, and
one of the first target vehicle information and the second target vehicle information is selected and the selected target vehicle information is output to the driving controller.
The embodiments for carrying out the present invention have been described above, but the present invention is not limited to the embodiments. Various modifications and substitutions can be made within the scope of the present invention without departing from the gist of the present invention.
| Number | Date | Country | Kind |
|---|---|---|---|
| JP2019-063140 | Mar 2019 | JP | national |
| Number | Name | Date | Kind |
|---|---|---|---|
| 20130131925 | Isaji et al. | May 2013 | A1 |
| 20160200320 | Nemoto | Jul 2016 | A1 |
| 20180154895 | Chae | Jun 2018 | A1 |
| 20210163004 | Wiberg | Jun 2021 | A1 |
| Number | Date | Country |
|---|---|---|
| 11-296799 | Oct 1999 | JP |
| 2010-086269 | Apr 2010 | JP |
| 2013-126854 | Jun 2013 | JP |
| 2015-051716 | Mar 2015 | JP |
| Entry |
|---|
| Japanese Office Action for Japanese Patent Application No. 2019-063140 dated Apr. 26, 2022. |
| Number | Date | Country | |
|---|---|---|---|
| 20200310454 A1 | Oct 2020 | US |
