Patent Application
20210188253
Vehicles may undergo certain cornering situations during operation. These situations include entering or exiting parking spots, and other low speed cornering situations in which the vehicle is moving and also turning. Vehicles may perform cornering in the forward or reverse directions in some examples.
A method for assisting in the exit of a vehicle from a parking spot, according to an example of this disclosure, includes obtaining one or more images of an object near the parking spot, sensing a path of the vehicle as the vehicle exits the parking spot, determining whether a collision between the vehicle and the object is imminent based on the sensed path and the one or more images, and initiating a vehicle response if the collision is imminent.
In a further example of the foregoing, the vehicle response includes one or more of a vibration in a seat of the vehicle, an audiovisual response, a steering correction, a pulse in a steering wheel of the vehicle, and a brake activation.
In a further example of any of the foregoing, the method includes determining that the vehicle is located in a parking area.
In a further example of any of the foregoing, the method includes sensing a path of a trailer of the vehicle as the vehicle exits the parking spot and determining whether a collision between the trailer and the object is imminent based on the sensed trailer path and the one or more images.
In a further example of any of the foregoing, the object is an adjacent vehicle.
In a further example of any of the foregoing, the object is a curb.
In a further example of any of the foregoing, one or more images of an object near the vehicle are obtained. The example method includes obtaining one or more images of an object near the vehicle as the vehicle pulls into the parking spot.
In a further example of any of the foregoing, the method stores one or more images obtained as the vehicle pulls into the parking spot on a memory device.
A system for assisting in the exit of a vehicle from a parking spot, according to an example of this disclosure, includes at least one camera on the vehicle for obtaining one or more images of an object near the parking spot. A sensor is configured to sense a path of the vehicle as the vehicle exits the parking spot. A controller is configured to determine whether a collision between the vehicle and the object is imminent based on the sensed path and the one or more images and initiating a vehicle response if the collision is imminent.
In a further example of the foregoing, the camera is disposed on or adjacent a side view mirror of the vehicle.
In a further example of any of the foregoing, the camera includes a fish eye lens.
In a further example of any of the foregoing, the system includes a memory device for storing the one or more images.
In a further example of any of the foregoing, one or more images are obtained as the vehicle pulls into the parking spot.
In a further example of any of the foregoing, the controller is an electronic control unit (ECU).
In a further example of any of the foregoing, the vehicle response includes one or more of a vibration in a seat of the vehicle, an audiovisual response, a steering correction, a pulse in a steering wheel of the vehicle, and a brake activation.
In a further example of any of the foregoing, the controller is configured to determine that the vehicle is located in a parking area.
These and other features may be best understood from the following specification and drawings, the following of which is a brief description.
In general, this disclosure pertains to systems and methods for assisting the cornering in a vehicle. In some example applications, the systems and methods pertain to assisting in parking situations.
The example system 10 includes a sensor 16 for sensing an object 18 at a periphery of the vehicle parking spot 12. A sensor 19 senses a path of the vehicle 14 as the vehicle 14 exits the parking spot 12. A controller 20 in communication with the sensors 16, 19 may be programmed to determine whether a collision between the vehicle 14 and the object 18 is imminent based on the information received from the sensors 16, 19 and initiate a vehicle response if the collision is imminent.
In some examples, the sensor 16 may include one or more of a camera, radar sensor, laser, LIDAR sensor and ultrasonic sensor. In some examples, the camera is a surround view camera. Although one sensor 16 is shown in the schematic example of
In some examples, the sensor 19 may include one or more of a camera, radar sensor, laser, LIDAR sensor and ultrasonic sensor. Although one sensor 19 is shown in the schematic example of
In some examples, the controller 20 may be an electronic control unit (ECU) that may include one or more individual electronic control units that control one or more electronic systems or subsystems within the vehicle 14. The controller 20, in some examples, may include one or more computing devices, each having one or more of a computer processor, memory, storage means, network device and input and/or output devices and/or interfaces. The controller 20 may be programmed to implement one or more of the methods or processes described herein.
In some examples, the controller 20 may be programmed with an algorithm used to detect corners or edges of the object 18 for determining whether a collision between the vehicle 14 and the object 18 is imminent. In some examples, knowing the host vehicle dimensions and/or those of a potentially attached trailer, and then using the current host vehicle's steering angle and velocity, a path trajectory can be calculated by the controller 20. The controller may then utilize this data for determining whether a collision between the vehicle 14 and the object 18 is imminent.
In some examples, the object 18 may include one or more of a vehicle, a wall, a curb, a barrier, a pillar, a construction object, and a garage object, such as a shelving unit or snowblower. In some examples, the object 18 is stationary.
In some examples, the vehicle response includes one or more of a vibration in a seat of the vehicle, an audiovisual response, a steering correction, a pulse in a steering wheel of the vehicle, blind spot alert, and a brake activation. In some examples, if the vehicle path shows a collision path with the object, an audio indicator that decreases as the driver adjusts to an appropriate steering angle can be used.
In some examples, the camera 116 is disposed on or adjacent a side view mirror 122 of the vehicle. In some examples, the camera 116 includes a fish eye lens facing outward from the vehicle 114. In some examples, the camera 116 is located below the side view mirror 122 of the vehicle. In some examples, the camera 116 may be utilized with additional sensors for sensing the vehicle surroundings, including the examples disclosed herein. In some examples multiple cameras 116 may be utilized. In some examples, a camera 116 may be disposed on or adjacent each side view mirror (driver and passenger side) of the vehicle 114.
The system 110 may include a memory device 124 for storing images obtained from the camera 116. In some examples, the memory device 124 may be of any type capable of storing information, including a computing device-readable medium, or other medium that stores data that may be read with the aid of an electronic device, such as a hard-drive, memory card, ROM, RAM, DVD or other optical disks, as well as other write-capable and read-only memories. In some examples, the camera 116 obtains one or more images as the vehicle pulls into the parking spot. The images are then saved on the memory device 124 for providing information about the vehicle's surroundings when the vehicle 114 exits the parking spot 112. In some examples, the camera 116 may obtain one or more images as the vehicle 114 pulls into a parking spot 112, the vehicle 114 is then turned off, and, when the vehicle 114 is turned back on, the images obtained when the vehicle 114 pulled into the parking spot 112 and saved on the memory device 124 may be utilized to assist the vehicle 114 in exiting the parking spot 112.
In some examples, the controller 120 is configured to determine that the vehicle 114 is located in a parking area. In some examples, this is done when the vehicle transmission is shifted to or from “park.” In some examples, this is done when the vehicle 114 is turned on. In some examples, this is done by communication with a global positioning system. In some examples, this is done by sensing vehicle speed or other parameters. In some examples, this is done by sensing the ignition has been turned on.
In some examples, the systems and method disclosed may be utilized outside of parking environments, such as in low-speed cornering situations. In some examples, the controller 120 may sense that the vehicle has come to a stop or a near stop and may begin cornering assistance.
Although one sensor 119 is shown in the example, multiple sensors 119 may be utilized in some examples.
In some examples, the controller 120 is programmed to utilize a structure from motion algorithm to estimate the three-dimensional structure of the object 118 based on a plurality of images obtained by the camera 116. Structure from motion is a photogrammetric range imaging technique for estimating three-dimensional structures from two-dimensional image sequences that may be coupled with local motion signals.
In some examples, the controller 120 may be programmed to utilize a semantic segmentation algorithm to detect the object 118 and/or calculate drivable surface on each side of the vehicle 114. Semantic segmentation utilizes image frames camera frames are to recognize various classifications in the vehicle environment, such as the driving surface, cars, pedestrians, curbs and sidewalks, at the pixel level. Semantic segmentation utilizes neural network based detection for image classification at the pixel level. In some examples, semantic segmentation utilizes every pixel of an image within an object class, which may include a specific type of object 118 or the surface between the object 118 and the vehicle 114 in some examples.
In some examples, the method 200 includes determining that the vehicle is located in a parking area. In some examples, the method 200 includes sensing a path of a trailer of the vehicle as the vehicle exits the parking spot. In some examples, the method 200 includes determining whether a collision between the trailer and the object is imminent based on the sensed trailer path and the one or more images.
In some examples, the step 202 includes obtaining one or more images of an object near the vehicle as the vehicle pulls into the parking spot. In some examples, the method 200 includes storing the one or more images obtained as the vehicle pulls into the parking spot on a memory device.
In some examples disclosed herein, the systems and methods assist drivers to achieve an appropriate turning radius if a collision is predicted to be highly likely.
Although the different examples are illustrated as having specific components, the examples of this disclosure are not limited to those particular combinations. It is possible to use some of the components or features from any of the examples in combination with features or components from any of the other examples.
The foregoing description shall be interpreted as illustrative and not in any limiting sense. A worker of ordinary skill in the art would understand that certain modifications could come within the scope of this disclosure. For these reasons, the following claims should be studied to determine the true scope and content of this disclosure.
