This application claims the benefit under 35 USC § 119(a) of Korean Patent Application No. 10-2021-0121201 filed on Sep. 10, 2021, and Korean Patent Application No. 10-2021-0152830 filed on Nov. 9, 2021, in the Korean Intellectual Property Office, the entire disclosures of which are incorporated herein by reference for all purposes.
The following description relates to a method and apparatus for estimating a position of a moving object.
Autonomous driving refers to driving to a destination without the intervention of a driver by recognizing surrounding environment, determining driving situation, and controlling a vehicle. With the recent use of vehicles and small-sized mobility devices such as mobile robots for smart delivery and security, the demand for autonomous vehicles or moving objects supporting advanced driver-assistance systems (ADAS) is increasing.
Estimating the position of the vehicle that is being driven is important for success in autonomous driving, and various techniques may be used to estimate the position. For example, a map may be generated in advance using a device such as a LiDAR or a camera and a position on the map may be estimated using sensor data measured during driving. In another method, satellite signals are received using a precise global positioning system (GPS) device and an absolute position is estimated.
This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
In one general aspect, there is provided an processor-implemented method of operating an electronic device, the method including generating two-dimensional (2D) feature point information in a landmark-based probability map from a surrounding image acquired by a capturing device mounted on a moving object, obtaining landmark-based three-dimensional (3D) feature point information from high-definition (HD) map data of a vicinity of the moving object, converting one of the 2D feature point information of the surrounding image to 3D or the 3D feature point information of the HD map data to 2D, determining a similarity between the converted feature point information and one of the feature point information of the surrounding image and the feature point information of the HD map data that is not converted, and estimating a position of the moving object based on the similarity.
The 2D feature point information of the surrounding image may be obtained according to a landmark, based on deep neural network (DNN)-based semantic segmentation.
The obtaining of the 3D feature point information from the HD map data of the vicinity of the moving object may include receiving 3D feature point information on a world domain for a landmark in the vicinity of the moving object from a HD map database based on position information of the moving object, and converting the 3D feature point information on the world domain to a local domain for the capturing device.
The converting of the 2D feature point information of the surrounding image may include converting the 2D feature point information of the surrounding image to the form of a 3D probability map based on inverse perspective mapping.
The converting of the dimension of the 3D feature point information of the HD map data may include projecting the 3D feature point information of the HD map data onto a 2D probability map obtained from the surrounding image, based on perspective mapping.
The determining of the similarity between the feature point information of the surrounding image and the feature point information of the HD map data may include summing probabilities of the feature point information of the HD map data corresponding to each landmark, in a probability map obtained from the surrounding image, and calculating the similarity by multiplying summed probabilities corresponding to each landmark.
The estimating of the position of the moving object based on the similarity may include updating a result of estimating the position of the moving object according to a particle filter or a maximum likelihood (ML) optimization scheme, based on the similarity.
The moving object may be an autonomous vehicle or a vehicle supporting advanced driver-assistance systems (ADAS).
The landmark may include any one or any combination of a white lane line, a yellow lane line, a crosswalk, a speed bump, a traffic light, and a traffic sign.
In another general aspect, there is provided a method of estimating a position of a moving object based on a particle filter, the method including generating two-dimensional (2D) feature point information in a landmark-based probability map from a surrounding image acquired by a capturing device mounted on a moving object, obtaining landmark-based three-dimensional (3D) feature point information from high-definition (HD) map data of a vicinity of the moving object, predicting positions of particles corresponding to candidate positions of the moving object, projecting, for each of the positions of the particles, the 3D feature point information onto the probability map obtained from the surrounding image, determining, for each of the positions of the particles, a similarity between the 3D feature point information projected onto the probability map and the 2D feature point information of the probability map, and estimating a position of the moving object by rearranging the particles based on the similarity.
The 2D feature point information may be obtained according to a landmark, based on deep neural network (DNN)-based semantic segmentation.
The obtaining of the 3D feature point information from the HD map data of the vicinity of the moving object may include receiving 3D feature point information on a world domain for a landmark in the vicinity of the moving object from a HD map database based on position information of the moving object, and converting the 3D feature point information on the world domain to a local domain for the capturing device.
The predicting of the positions of the particles may include predicting the positions of the particles based on position information of particles rearranged at a previous point in time and a displacement of the moving object from the previous point in time.
The 3D feature point information may be projected onto a 2D probability map obtained from the surrounding image based on perspective mapping.
The determining of the similarity between the 3D feature point information projected onto the probability map and the 2D feature point information of the probability map may include summing probabilities of the projected 3D feature point information corresponding to each landmark, in the probability map, and multiplying summed probabilities corresponding to respective landmarks.
The estimating of the position of the moving object by rearranging the particles based on the similarity may include setting weights for the respective positions of the particles according to the similarity, rearranging the particles according to the weights, and estimating the position of the moving object by calculating a mean value of the rearranged particles.
The moving object may be an autonomous vehicle or a vehicle supporting advanced driver-assistance systems (ADAS).
In another general aspect, there is provided an electronic device, including a communication module configured to receive high-definition (HD) map data of a vicinity of a moving object and a surrounding image acquired by a capturing device mounted on the moving object, a memory configured to store computer-executable instructions, the HD map data, and the surrounding image, and a processor configured to execute the computer-executable instructions to configure the processor to generate two-dimensional (2D) feature point information of a landmark-based probability map from the surrounding image, obtain landmark-based three-dimensional (3D) feature point information from the HD map data, convert one of the 2D feature point information of the surrounding image to 3D or the 3D feature point information of the HD map data to 2D, determine a similarity between the converted feature point information and one of the feature point information of the surrounding image and the feature point information of the HD map data that is not converted, and estimate a position of the moving object based on the similarity.
The processor may be configured to sum probabilities of the feature point information of the HD map data corresponding to each landmark, in a probability map obtained from the surrounding image, and calculate the similarity by multiplying summed probabilities corresponding to respective landmarks.
Other features and aspects will be apparent from the following detailed description, the drawings, and the claims.
Throughout the drawings and the detailed description, unless otherwise described or provided, the same drawing reference numerals will be understood to refer to the same elements, features, and structures. The drawings may not be to scale, and the relative size, proportions, and depiction of elements in the drawings may be exaggerated for clarity, illustration, and convenience.
The following detailed is provided to assist the reader in gaining a comprehensive understanding of the methods, apparatuses, and/or systems described herein. However, various changes, modifications, and equivalents of the methods, apparatuses, and/or systems described herein will be apparent after an understanding of the disclosure of this application. For example, the sequences of operations described herein are merely examples, and are not limited to those set forth herein, but may be changed as will be apparent after an understanding of the disclosure of this application, with the exception of operations necessarily occurring in a certain order.
The features described herein may be embodied in different forms and are not to be construed as being limited to the examples described herein. Rather, the examples described herein have been provided merely to illustrate some of the many possible ways of implementing the methods, apparatuses, and/or systems described herein that will be apparent after an understanding of the disclosure of this application.
Although terms such as “first,” “second,” and “third” , A, B, C, (a), (b), (c), or the like may be used herein to describe various members, components, regions, layers, or sections, these members, components, regions, layers, or sections are not to be limited by these terms. Rather, these terms are only used to distinguish one member, component, region, layer, or section from another member, component, region, layer, or section. Thus, a first member, component, region, layer, or section referred to in the examples described herein may also be referred to as a second member, component, region, layer, or section without departing from the teachings of the examples.
It should be noted that if it is described that one component is “connected”, “coupled”, or “joined” to another component, a third component may be “connected”, “coupled”, and “joined” between the first and second components, although the first component may be directly connected, coupled, or joined to the second component. On the contrary, it should be noted that if it is described that one component is “directly connected”, “directly coupled”, or “directly joined” to another component, a third component may be absent. Expressions describing a relationship between components, for example, “between”, directly between”, or “directly neighboring”, etc., should be interpreted to be alike.
The singular forms “a”, “an”, and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, components or a combination thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
Unless otherwise defined, all terms used herein including technical or scientific terms have the same meaning as commonly understood by one of ordinary skill in the art to which examples belong. It will be further understood that terms, such as those defined in commonly-used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The use of the term “may” herein with respect to an example or embodiment (e.g., as to what an example or embodiment may include or implement) means that at least one example or embodiment exists where such a feature is included or implemented, while all examples are not limited thereto.
The examples may be implemented as various types of products, such as, for example, a personal computer (PC), a laptop computer, a tablet computer, a smartphone, a television (TV), a smart home appliance, an intelligent vehicle, a kiosk, a navigation device, a vehicle, an automated vehicle, and a wearable device. Hereinafter, examples will be described in detail with reference to the accompanying drawings. In the drawings, like reference numerals are used for like elements.
Referring to
For example, the feature point information 121 may correspond to the yellow lane line 111, the feature point information 123 may correspond to the white lane line 113, and the feature point information 125 may correspond to the curb 115, in the image of
According to an example, the surrounding image of the moving object, acquired through the capturing device as in
Referring to
The feature point information obtained from the HD map data may be three-dimensional (3D) coordinates in space and may be divided by landmarks. For example, referring to
According to an example, world domain information on landmarks in the vicinity of the moving object may be transmitted from a HD map database to an electronic device for estimating a position of a moving object, according to position information of the moving object. The world domain information may be converted into local domain information on a capturing device.
To estimate the position of the moving object, a process of comparing feature point information (e.g., the feature point information 121 of
According to an example, when an extended Kalman filter (EKF) is used for estimating the position of the moving object, information on an error between position information predicted based on previous position information and position information measured by a sensor may be needed, and to calculate the error a degree of similarity (hereinafter, a similarity)(or, likelihood) between the two information may be needed. For example, the feature point information 121 of
As described above with reference to
Hereinafter, a method of calculating a similarity(or likelihood) between 2D feature point information obtained from an input image, described with reference to
Referring to
The electronic device 101 may be mounted on a moving object whose position is to be estimated, or included in the moving object, or positioned separately from the moving object. The electronic device 101 may estimate a position of the moving object. In an example, the moving object refers to any mode of transportation, delivery, or communication such as, for example, for example, an automobile, a truck, a tractor, a scooter, a motorcycle, a cycle, an amphibious vehicle, a snowmobile, a boat, a public transit vehicle, a bus, a monorail, a train, a tram, an autonomous vehicle, an unmanned aerial vehicle, a bicycle, a drone, and a flying object such as an airplane. The moving object may be an autonomous vehicle or a vehicle supporting advanced driver-assistance systems (ADAS).
The memory 130 may store a variety of data used by components (e.g., the processor 120) of the electronic device 101. A variety of data may include, for example, computer-readable instructions and input data or output data for an operations related thereto. The memory 130 may include any one or any combination of a volatile memory and a non-volatile memory.
The volatile memory device may be implemented as a dynamic random-access memory (DRAM), a static random-access memory (SRAM), a thyristor RAM (T-RAM), a zero capacitor RAM (Z-RAM), or a twin transistor RAM (TTRAM).
The non-volatile memory device may be implemented as an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic RAM (MRAM), a spin-transfer torque (STT)-MRAM, a conductive bridging RAM(CBRAM), a ferroelectric RAM (FeRAM), a phase change RAM (PRAM), a resistive RAM (RRAM), a nanotube RRAM, a polymer RAM (PoRAM), a nano floating gate Memory (NFGM), a holographic memory, a molecular electronic memory device), or an insulator resistance change memory. Further details regarding the memory 130 is provided below.
The processor 120 may control an overall operation of the electronic device 101 and may execute corresponding processor-readable instructions for performing operations of the electronic device 101. The processor 120 may execute, for example, software, to control one or more hardware components, such as other components described below in
In an example, as at least a part of data processing or operations, the processor 120 may store instructions or data in the memory 130, execute the instructions and/or process data stored in the memory 130, and store resulting data obtained therefrom in the memory 130. The processor 120 may be a data processing device implemented by hardware including a circuit having a physical structure to perform desired operations. For example, the desired operations may include code or instructions included in a program.
The hardware-implemented data processing device may include, for example, a main processor (e.g., a central processing unit (CPU), a field-programmable gate array (FPGA), or an application processor (AP)) or an auxiliary processor (e.g., a GPU, a neural processing unit (NPU), an image signal processor (ISP), a sensor hub processor, or a communication processor (CP)) that is operable independently of, or in conjunction with the main processor. Further details regarding the processor 120 is provided below.
As described above with reference to
The HD map database 210 may be a database including HD map (HD map) information, and may transmit HD map information on the vicinity of the moving object to the electronic device 101 through the communication module 190 in response to a request from the electronic device 101. As described with reference to
The communication module 190 may support establishing a direct (e.g., wired) communication channel or wireless communication channel between the electronic device 101 and an external electronic device (or server) and performing communication through the established communication channel. The communication module 190 may include one or more communication processors that operate independently of the processor 120 (e.g., an application processor) and support direct (e.g., wired) communication or wireless communication. According to an example, the communication module 190 may include a wireless communication module (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (e.g., a local area network (LAN) communication module, or a power line communication (PLC) module). A corresponding one of these communication modules may communicate with the external electronic device via ashort-range communication network (e.g., BluetoothTM, wireless-fidelity (Wi-Fi) direct, or infrared data association (IrDA)) or a long-range communication network (e.g., a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or a wide area network (WAN)). These various types of communication modules may be implemented as a single component (e.g., a single chip), or may be implemented as multi components (e.g., multi chips) separate from each other.
The wireless communication module may support a 5G network after a 4G network, and a next-generation communication technology, e.g., a new radio (NR) access technology. The NR access technology may support enhanced mobile broadband (eMBB), massive machine type communications (mMTC), or ultra-reliable and low-latency communications (URLLC). The wireless communication module may support a high-frequency band (e.g., a mmWave band) to achieve, e.g., a high data transmission rate. The wireless communication module may support various technologies for securing performance on a high-frequency band, such as, e.g., beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), an array antenna, analog beam-forming, or a large scale antenna. The wireless communication module may support various requirements specified in the electronic device 101, the external electronic device, or a network system. According to an example, the wireless communication module may support a peak data rate (e.g., 20 Gbps or more) for implementing eMBB, loss coverage (e.g., 164 dB or less) for implementing mMTC, or U-plane latency (e.g., 0.5 ms or less for each of downlink (DL) and uplink (UL), or a round trip of 1 ms or less) for implementing URLLC.
A method of the communication module 190 communicating with the capturing device 230 to obtain 2D feature point information may be the same as or different from a method of the communication module 190 communicating with the HD map database 210 to obtain 3D feature point information.
According to an example, the processor 120 may obtain 2D feature point information in the form of a landmark-based probability map from a surrounding image acquired by the capturing device 230 mounted on the moving object. As described above with reference to
According to another example, a process of extracting the 2D feature point information from the surrounding image of the moving object may be performed by the external electronic device or server, and the processor 120 may receive the extracted 2D feature point information in the form of a landmark-based probability map.
According to an example, the processor 120 may obtain landmark-based 3D feature point information in a HD map of the vicinity of the moving object. As described above with reference to
According to an example, feature point information stored in the HD map database 210 may be coordinates in a world domain, and the processor 120 may convert feature point information on landmarks in the vicinity of the moving object, received from the HD map database 210, into a local domain for the capturing device. The process of conversion from the world domain to the local domain will be described in detail with reference to Equation 1 below.
According to another example, the conversion from the world domain to the local domain may be performed by the external electronic device or server, and the 3D feature point information in the form of a local domain may be transmitted to the processor 120.
To calculate the similarity between the 2D feature point information and the 3D feature point information, the processor 120 may convert the dimension of one of the 2D feature point information of the surrounding image and the 3D feature point information of the HD map data into the other dimension.
For example, the processor 120 may project the 3D feature point information of the HD map data onto a 2D probability map obtained from the surrounding image based on perspective mapping. The 3D feature point information of the HD map data may be projected onto the 2D probability map obtained from the surrounding image based on Equation 1 and Equation 2 below.
According to an example, based on Equation 1, the 3D feature point information of the HD map data may be converted into a local domain which is based on the capturing device on the world domain. This may correspond to the operation of conversion from the world domain to the local domain described above in relation to the HD map database 210.
denotes coordinates of 3D feature point information on the world domain of the HD map data. For example,
may be coordinates of one of the by-landmark feature points 131, 133, and 135 of
may be a rotation transformation matrix of the moving object to the world domain.
may be a rotation transformation matrix of the capturing device 230 to the moving object.
may be a relative distance of the capturing device 230 to the moving object. Based on Equation 1, components X,Y,Z of the 3D feature point information on the local domain with respect to the capturing device 230 may be obtained.
According to an example, based on Equation 2, the 3D feature point information converted into the local domain with respect to the capturing device may be projected onto a 2D probability map.
Based on Equation 2 above, the 3D feature point information X,Y,Z obtained by Equation 1 above may be projected onto the 2D probability map, and 2D coordinates pc = [u v]T may be obtained. fx and fy may be a horizontal focal length and a vertical focal length of the capturing device, respectively.
As another example, the processor 120 may convert the 2D feature point information of the surrounding image to the form of a 3D probability map based on inverse perspective mapping. Depth information may be required for conversion from 2D into 3D. Thus, in this case, the capturing device 230 may be a stereo vision camera.
According to an example, the processor 120 may match the dimensions of the two feature point information and then, calculate a similarity between the feature point information, and estimate the position of the moving object based on the similarity. The processor 120 may sum probabilities of the feature point information of the HD map data corresponding to each landmark, in the probability map obtained from the surrounding image, and calculate the similarity by multiplying summed probabilities.
As an example, in response to matching the dimensions to 2D as described above, probabilities corresponding to projected 2D coordinates when the 3D feature point information is projected onto the 2D probability map may be summed for each landmark, and a similarity may be calculated by multiplying summed probabilities. As another example, in response to matching the dimensions to 3D, the 2D probability map may be converted to the form of a 3D probability map according to inverse perspective mapping. Probabilities of correspondence of the 3D feature point information on the converted 3D probability map may be summed for each landmark, and a similarity may be calculated by multiplying summed probabilities.
The processor 120 may estimate the position of the moving object or update an estimation result according to a particle filter or a maximum likelihood (ML) optimization scheme, based on the calculated similarity.
Various examples of calculating the similarity and estimating the position of the moving object based on the similarity by the processor 120 will be described in detail with reference to
As described above with reference to
The dimensions may be matched to 3D as described above with reference to
As described above with reference to
Referring to
Calculating a similarity by simply summing probabilities of corresponding to projected 3D feature points, without calculating a similarity with dividing by landmarks, may drop the accuracy of the similarity. For example, since the stop line has no match at all, but the lane lines having a relatively greater number of feature points have good match, a relatively high overall similarity may be calculated.
According to an example, the processor 120 of the electronic device 101 may calculate the similarity by summing probabilities for each landmark and multiplying summed probabilities, whereby the accuracy of the similarity may improve. The process of calculating the similarity by dividing according to landmarks, as in the processor 120 of the electronic device 101, will be described in detail with reference to
Referring to
The situations 340 and 360 of
Referring to the situation 340 of
Referring to the situation 360 of
The processor 120 of the electronic device 101 may sum, for each of the landmarks, probabilities of correspondence of the projected 3D feature points on the probability map, and calculate a similarity by multiplying summed probabilities for the respective landmarks. Referring to the situation 340 of
Unlike the description provided with reference to
In another example, the similarity calculated for different types of landmark and feature points may be assigned weights, and the processor 120 may calculate the similarity by multiplying weighted sum of probabilities for respective landmarks.
According to an example, the processor 120 may calculate the similarity by dividing by landmarks, thereby calculating a more accurate similarity, which leads to an increase in the uniqueness of similarity. The process of calculating the similarity will be described in further detail with reference to
Referring to
The dimensions may be matched to 3D as described above with reference to
Referring to
Referring to
The processor 120 may estimate the position of the moving object based on the similarity. According to an example, the processor 120 may set a higher weight for a candidate position with a relatively high similarity, corresponding to
For example, operations 510 to 550 may be performed by the processor 120 of the electronic device 101 described above with reference to
According to an example, in operation 510, the processor 120 may obtain 2D feature point information in the form of a probability map from a surrounding image of a moving object. As described above with reference to
According to an example, in operation 520, the processor 120 may obtain 3D feature point information from HD map data of a vicinity of the moving object. As described above with reference to
According to an example, in operation 530, the processor 120 may convert the dimension of one of the 2D feature point information and the 3D feature point information into another dimension. As described above with reference to
According to an example, in operation 540, the processor 120 may calculate a similarity between the feature point information of the surrounding image and the feature point information of the HD map data. As described above with reference to
According to an example, in operation 550, the processor 120 may estimate a position of the moving object based on the similarity. According to an example, as described with reference to
According to an example, operations 610 and 620 may correspond to the operation of calculating the similarity between the feature point information of the surrounding image and the feature point information of the HD map data described with reference to
According to an example, in operation 610, the processor 120 may sum probabilities of the feature point information of the HD map data corresponding to each landmark, in the probability map obtained from the surrounding image. As described with reference to
According to an example, in operation 620, the processor 120 may calculate the similarity by multiplying summed probabilities corresponding to respective landmarks. As described with reference to
Operations 610 and 620 of the processor 120 may be expressed by Equation 3 below. Equation 3 may be a similarity calculation method in the case where the 3D feature point information of the HD map is projected onto the 2D probability map based on Equation 1 and Equation 2 described above.
p may be the 3D feature point information of the HD map data projected onto the 2D probability map in Equation 2 described above. All coordinates in the 2D probability map may have probabilities of correspondence, which may be probabilities of corresponding to the coordinates in the 2D probability map. As an example, Pi (·) may be a Gaussian blur filter. m may be an index of a feature point. i may be an index of a landmark.
Referring to Equation 3, in operation 610, the processor 120 may sum (∑) probabilities of corresponding to all feature points, which are landmarks i , for example, feature points with index numbers m to M in Equation 3. Referring to
Referring back to Equation 3, in operation 620, the processor 120 may multiply (⊓) summed probabilities of the landmarks i to I. As described above with reference to
According to an example, the processor 120 may calculate a similarity between feature points with different dimensions through operations 610 to 620.
For example, operations 710 to 760 may be performed by the processor 120 of the electronic device 101 described above with reference to
Operations 710 to 760 may correspond to a method of estimating a position of a moving object by the processor 120 of the electronic device 101 based on a particle filter. Operations 710 to 760 may be detailed operations based on the particle filter, in relation to the operations described above with reference to
A “particle” is arranged on a digital indoor map and has one or more properties. Each particle preferably has at least two properties, “direction” and “position”. Each particle is moved by reflecting a relative movement of a moving object, and is deleted when it is moved to an unreachable position on the digital indoor map. In addition, when the total number of particles falls below a reference value as a result of particle movements, new particles having the same properties as those of the existing particles, except for positions, may be regenerated. The particle-based position estimation method largely includes a process of arranging particles at candidate positions, a process of calculating similarities for respective particles, and a process of rearranging (resampling) the distribution of the particles based on the calculated similarities. Measurement using “particle filtering” may be used based on one of generally available methods without departing from the spirit and scope of the illustrative examples described.
Operations 710 and 720 correspond to operations 510 and 520 described with reference to
According to an example, in operation 730, the processor 120 may predict positions of a plurality of particles corresponding to candidate positions of the moving object. According to an example, the processor 120 may predict the positions of the plurality of particles corresponding to current candidate positions of the moving object based on position information of particles rearranged at a previous point in time and a displacement of the moving object from the previous point in time up to the present time. In an example, the displacement of the moving object from the previous point in time up to now may be obtained based on wheel speed information.
According to an example, in operation 740, the processor 120 may project, for each of the positions of the plurality of particles, 3D feature point information onto a 2D probability map. That is, there may be a single 2D probability map corresponding to each of the predicted positions of the particles, and 3D feature points of the HD map projected onto the 2D probability map. As an example,
According to an example, in operation 750, the processor 120 may calculate, for each of the positions of the plurality of particles, a similarity between the 3D feature point information projected onto the probability map and the 2D feature point information of the probability map. Operation 750 is as described with reference to
According to an example, in operation 760, the processor 120 may estimate a position of the moving object by rearranging the plurality of particles based on the similarity. The detailed operation of estimating the position of the moving object based on the particle filter will be described in detail with reference to
According to an example, operations 810 to 840 may correspond to the operation of estimating the position of the moving object based on the particle filter described with reference to
According to an example, in operation 810, the processor 120 may set weights for the respective positions of the particles according to similarities. As an example, for the positions of two particles corresponding to two candidate positions of the moving object, 2D probability maps and 3D feature points projected thereon may be obtained as shown in
According to an example, in operation 820, the processor 120 may rearrange (resample) the plurality of particles according to the weights. A high weight is set for the position of a particle corresponding to
According to an example, in operation 830, the processor 120 may estimate the position of the moving object by calculating an average value of the rearranged particles. As an example, the processor 120 may estimate the position of the moving object based on maximum a posteriori (MAP).
A position estimation method of estimating a position of an autonomous vehicle on a world domain includes a method of utilizing fusion of a GPS and an inertial navigation system (INS) 930. However, the GPS may not guarantee accuracy in a complex urban environment due to multi-path reception and signal interruption caused by high-rise buildings. The system 900 proposes a new position estimation method that fuses an inertial measurement unit (IMU) 920, a wheel odometry 910, and a HD map 940 to eliminate GPS dependency.
The extended Kalman Filter (EKF) 990 of the fusion part 902 is a filter generally used to fuse different sensors having a non-linear relationship, and a system model and a measurement model may be defined to use the extended Kalman filter 990. In the system 900, the system model and the measurement model may be defined based on the wheel odometry 910, the IMU 920, and the position information. The system model predicts state variables and covariance based on a mathematical model, and the predicted state variables and covariance are compensated by a difference between a measurement and a predicted measurement.
However, in the case of a probability map, it may be ambiguous to calculate the difference between the measurement and the predicted measurement. As described above with reference to
As described above with reference to
The operation of the electronic device 101 described with reference to
Referring to
The vehicle 1000 recognizes the driving environment and generates an autonomous driving route appropriate for the driving environment. The autonomous vehicle controls internal and external mechanical elements to follow the autonomous driving route. The vehicle 1000 may periodically generate an autonomous driving route.
According to another aspect, the vehicle 1000 may assist a driver with driving using advanced driver-assistance systems (ADAS). ADAS may include an automatic emergency braking system (AEB) that in case of detecting a risk of collision, automatically reduces the speed or stops the vehicle even when the driver does not step on the brake, a lane keep assist system (LKAS) that steers the vehicle to keep its lane when the vehicle moves out of the lane, an advanced smart cruise control (ASCC) that automatically controls the vehicle to maintain a distance to vehicles ahead or to drive at a predetermined speed, an active blind spot detection (ABSD) that detects a risk of collision in a blind spot and thereby helps the driver to change lanes safely, and an around view monitor (AVM) that visually displays the surrounding circumstances of the vehicle.
The electronic device 101 included in the vehicle 1000 may control the mechanical devices of the vehicle 1000 to autonomously drive or assist the driver with driving, and may be used for an ECU, VCU, and various types of controllers or sensors other than the described example.
According to an example, the electronic device 101 described with reference to
In the examples described above, the memory 130 may store a variety of information generated in the processing process of the processor 120 described above. In addition, the memory 130 may store a variety of data and programs. The memory 130 may include a high-capacity storage medium such as a hard disk to store a variety of data.
The processor 120 may execute a program and control the electronic device. Program code to be executed by the processor may be stored in the memory.
The electronic device 101, the capturing device 230, the communication module 190, system 900, the fusion part 902, the map matching part 901, the particle filter 980, the DNN-based semantic segmentation 970, and other apparatuses, devices, units, modules, and components described herein are implemented by hardware components. Examples of hardware components that may be used to perform the operations described in this application where appropriate include controllers, sensors, generators, drivers, memories, comparators, arithmetic logic units, adders, subtractors, multipliers, dividers, integrators, and any other electronic components configured to perform the operations described in this application. In other examples, one or more of the hardware components that perform the operations described in this application are implemented by computing hardware, for example, by one or more processors or computers. A processor or computer may be implemented by one or more processing elements, such as an array of logic gates, a controller and an arithmetic logic unit, a digital signal processor, a microcomputer, a programmable logic controller, a field-programmable gate array, a programmable logic array, a microprocessor, or any other device or combination of devices that is configured to respond to and execute instructions in a defined manner to achieve a desired result. In one example, a processor or computer includes, or is connected to, one or more memories storing instructions or software that are executed by the processor or computer. Hardware components implemented by a processor or computer may execute instructions or software, such as an operating system (OS) and one or more software applications that run on the OS, to perform the operations described in this application. The hardware components may also access, manipulate, process, create, and store data in response to execution of the instructions or software. For simplicity, the singular term “processor” or “computer” may be used in the description of the examples described in this application, but in other examples multiple processors or computers may be used, or a processor or computer may include multiple processing elements, or multiple types of processing elements, or both. For example, a single hardware component or two or more hardware components may be implemented by a single processor, or two or more processors, or a processor and a controller. One or more hardware components may be implemented by one or more processors, or a processor and a controller, and one or more other hardware components may be implemented by one or more other processors, or another processor and another controller. One or more processors, or a processor and a controller, may implement a single hardware component, or two or more hardware components. A hardware component may have any one or more of different processing configurations, examples of which include a single processor, independent processors, parallel processors, single-instruction single-data (SISD) multiprocessing, single-instruction multiple-data (SIMD) multiprocessing, multiple-instruction single-data (MISD) multiprocessing, multiple-instruction multiple-data (MIMD) multiprocessing, a controller and an arithmetic logic unit (ALU), a DSP, a microcomputer, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a programmable logic unit (PLU), a central processing unit (CPU), a graphics processing unit (GPU), a neural processing unit (NPU), or any other device capable of responding to and executing instructions in a defined manner.
The methods that perform the operations described in this application are performed by computing hardware, for example, by one or more processors or computers, implemented as described above executing instructions or software to perform the operations described in this application that are performed by the methods . For example, a single operation or two or more operations may be performed by a single processor, or two or more processors, or a processor and a controller. One or more operations may be performed by one or more processors, or a processor and a controller, and one or more other operations may be performed by one or more other processors, or another processor and another controller. One or more processors, or a processor and a controller, may perform a single operation, or two or more operations.
The Instructions or software to control a processor or computer to implement the hardware components and perform the methods as described above are written as computer programs, code segments, instructions or any combination thereof, for individually or collectively instructing or configuring the processor or computer to operate as a machine or special-purpose computer to perform the operations performed by the hardware components and the methods as described above. In one example, the instructions or software include machine code that is directly executed by the processor or computer, such as machine code produced by a compiler. In an example, the instructions or software includes at least one of an applet, a dynamic link library (DLL), middleware, firmware, a device driver, an application program storing the method of operating an electronic device. In another example, the instructions or software include higher-level code that is executed by the processor or computer using an interpreter. Programmers of ordinary skill in the art can readily write the instructions or software based on the block diagrams and the flow charts illustrated in the drawings and the corresponding descriptions in the specification, which disclose algorithms for performing the operations performed by the hardware components and the methods as described above.
The instructions or software to control a processor or computer to implement the hardware components and perform the methods as described above, and any associated data, data files, and data structures, are recorded, stored, or fixed in or on one or more non-transitory computer-readable storage media. Examples of a non-transitory computer-readable storage medium include read-only memory (ROM), random-access programmable read only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random-access memory (RAM), magnetic RAM (MRAM), spin-transfer torque(STT)-MRAM, static random-access memory (SRAM), thyristor RAM (T-RAM), zero capacitor RAM (Z-RAM), twin transistor RAM (TTRAM), conductive bridging RAM(CBRAM), ferroelectric RAM (FeRAM), phase change RAM (PRAM), resistive RAM(RRAM), nanotube RRAM, polymer RAM (PoRAM), nano floating gate Memory(NFGM), holographic memory, molecular electronic memory device), insulator resistance change memory, dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROMs, CD-Rs, CD+Rs, CD-RWs, CD+RWs, DVD-ROMs, DVD-Rs, DVD+Rs, DVD-RWs, DVD+RWs, DVD-RAMs, BD-ROMs, BD-Rs, BD-R LTHs, BD-REs, blue-ray or optical disk storage, hard disk drive (HDD), solid state drive (SSD), flash memory, a card type memory such as multimedia card micro or a card (for example, secure digital (SD) or extreme digital (XD)), magnetic tapes, floppy disks, magneto-optical data storage devices, optical data storage devices, hard disks, solid-state disks, and any other device that is configured to store the instructions or software and any associated data, data files, and data structures in a non-transitory manner and providing the instructions or software and any associated data, data files, and data structures to a processor or computer so that the processor or computer can execute the instructions. In an example, the instructions or software and any associated data, data files, and data structures are distributed over network-coupled computer systems so that the instructions and software and any associated data, data files, and data structures are stored, accessed, and executed in a distributed fashion by the one or more processors or computers.
While this disclosure includes specific examples, it will be apparent after an understanding of the disclosure of this application that various changes in form and details may be made in these examples without departing from the spirit and scope of the claims and their equivalents. The examples described herein are to be considered in a descriptive sense only, and not for purposes of limitation. Descriptions of features or aspects in each example are to be considered as being applicable to similar features or aspects in other examples. Suitable results may be achieved if the described techniques are performed in a different order, and/or if components in a described system, architecture, device, or circuit are combined in a different manner, and/or replaced or supplemented by other components or their equivalents. Therefore, the scope of the disclosure is defined not by the detailed description, but by the claims and their equivalents, and all variations within the scope of the claims and their equivalents are to be construed as being included in the disclosure.
Number | Date | Country | Kind |
---|---|---|---|
10-2021-0121201 | Sep 2021 | KR | national |
10-2021-0152830 | Nov 2021 | KR | national |