Roadblock detection method and apparatus for a vehicle

Abstract

The present application relates to a method for barrier detection for a vehicle, the method comprising: receiving a sensor signal and detecting, based on the sensor signal, the presence of a specific barrier; and after the wheel has contacted the specific barrier, determining whether the vehicle has been blocked based on the torque of the vehicle and / or the number of bounces of the wheel. The present application also relates to a barrier detection device for a vehicle, a computer storage medium, a parking assistance system, an automatic parking or autonomous driving system and a vehicle.

Description

Technical Field

[0001] This invention relates to the field of road obstacle detection, and more specifically, to a road obstacle detection method and apparatus for vehicles, a computer storage medium, a parking assistance system, an automatic parking or automatic driving system, and a vehicle. Background Technology

[0002] With the continuous development of technology, road obstacle detection devices suitable for vehicles on the market can detect whether there are obstacles around the car while the vehicle is in motion, and can provide an alarm to the driver to protect the driver's driving safety.

[0003] Existing obstacle detection devices typically use cameras and / or ultrasonic radar to detect obstacles. However, because cameras cannot measure the size of obstacles, these existing obstacle detection devices cannot accurately detect obstacles, nor can they help formulate specific strategies for the next step when the vehicle is blocked during automatic parking or driving. Summary of the Invention

[0004] According to one aspect of the present invention, a road obstacle detection method for a vehicle is provided, the method comprising: receiving a sensor signal and detecting the presence of a specific road obstacle based on the sensor signal; and determining whether the vehicle is blocked based on the vehicle's torque and / or the number of wheel rebounds after a wheel contacts the specific road obstacle. A specific road obstacle refers to a road obstacle through which an electronic control unit (ECU) or other control unit cannot determine whether the vehicle can drive through based on the sensor detection results.

[0005] As a supplement or replacement to the above solution, in the above roadblock detection method, receiving sensor signals and detecting the existence of a specific roadblock based on the sensor signals includes: receiving signals from a camera / camera and detecting the boundary features of the roadblock based on the signals from the camera / camera to determine that the roadblock belongs to the specific roadblock.

[0006] As a supplement or replacement to the above scheme, in the above roadblock detection method, determining whether the vehicle has been blocked based on the vehicle's torque and / or the number of wheel rebounds after the wheel contacts the specific roadblock includes: when the vehicle is stationary, if the increase time of the vehicle's torque is greater than a first threshold, then it is determined that the vehicle has been blocked.

[0007] As a supplement or replacement to the above solution, in the above roadblock detection method, determining whether the vehicle has been blocked based on the vehicle's torque and / or the number of wheel rebounds after the wheel contacts the specific roadblock includes: determining that the vehicle has been blocked when the number of wheel rebounds after contacting the specific roadblock exceeds a second threshold.

[0008] As a supplement or replacement to the above solution, in the above obstacle detection method, determining whether the vehicle has been blocked based on the vehicle's torque and / or the number of wheel rebounds after the wheel contacts the specific obstacle includes: determining that the vehicle has been blocked when the target torque of the vehicle is greater than the calibrated maximum torque.

[0009] As a supplement or alternative to the above solution, the roadblock detection method may further include: sending a request to the electronic parking brake system when the vehicle is blocked.

[0010] As a supplement or alternative to the above solution, the roadblock detection method may further include: when the vehicle is blocked, feeding back the status of the vehicle to the driver and / or a remote server.

[0011] According to another aspect of the present invention, a road obstacle detection device for a vehicle is provided, the device comprising: a detection unit for receiving sensor signals and detecting the presence of a specific road obstacle based on the sensor signals; and a determination unit for determining whether the vehicle has been blocked based on the torque of the vehicle and / or the number of times the wheel rebounds after the wheel contacts the specific road obstacle.

[0012] As a supplement or alternative to the above solution, in the above device, the detection unit is configured to receive signals from a camera / camera and determine that the roadblock belongs to the specific roadblock based on the boundary features of the roadblock detected by the camera / camera signals.

[0013] As a supplement or replacement to the above solution, in the above device, the determining unit is configured to determine that the vehicle has been blocked when the vehicle is stationary and the increase time of the vehicle's torque is greater than a first threshold.

[0014] As a supplement or alternative to the above solution, in the above device, the determining unit is configured to determine that the vehicle has been blocked when the number of rebounds after the wheel contacts the specific road obstacle exceeds a second threshold.

[0015] As a supplement or replacement to the above solution, in the above device, the determining unit is configured to determine that the vehicle has been blocked when the target torque of the vehicle is greater than the calibrated maximum torque.

[0016] As a supplement or alternative to the above solution, the above device may further include: a transmitting unit, used to send a request to the electronic parking brake system when the vehicle is blocked.

[0017] As a supplement or replacement to the above solution, in the above device, the sending unit is further configured to feed back the status of the vehicle to the driver and / or a remote server.

[0018] According to another aspect of the present invention, a computer storage medium is provided, the medium including instructions that, when executed, perform the obstacle detection method as described above.

[0019] According to another aspect of the present invention, a parking assistance system is provided, the system comprising the road barrier device as described above.

[0020] According to another aspect of the present invention, an automatic parking or automatic driving system is provided, the system including the road barrier device as described above.

[0021] According to another aspect of the invention, a vehicle is provided, the vehicle including the parking assistance system or automatic parking or automatic driving system as described above.

[0022] The obstacle detection scheme for vehicles according to embodiments of the present invention can determine whether a vehicle is blocked based on the vehicle's torque and / or the number of wheel rebounds when a specific obstacle is detected. This scheme can further improve the accuracy of obstacle detection, and is particularly helpful in improving safety during automatic parking or autonomous driving processes. Attached Figure Description

[0023] The above and other objects and advantages of the present invention will become more fully clear from the following detailed description taken in conjunction with the accompanying drawings, wherein the same or similar elements are indicated by the same reference numerals.

[0024] Figure 1 A schematic flowchart of a road obstacle detection method for a vehicle according to an embodiment of the present invention is shown; Figure 2 A schematic diagram of a road obstacle detection device for a vehicle according to an embodiment of the present invention is shown; and Figure 3 A schematic diagram of a vehicle including a parking assistance system or an automatic parking or automatic driving system according to an embodiment of the present invention is shown. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it.

[0026] It should also be noted that, for ease of description, the accompanying drawings show only the parts relevant to the invention and not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but it may also have additional steps not included in the drawings. The process may correspond to a method, function, procedure, subroutine, subprogram, etc.

[0027] Although exemplary embodiments are described as using multiple units to perform exemplary processes, it should be understood that these exemplary processes may also be performed by one or more modules.

[0028] Furthermore, the control logic of the present invention can be included as executable program instructions on a computer-readable medium, which are implemented by a processor or the like. Examples of computer-readable media include, but are not limited to, ROM, RAM, optical discs, magnetic tapes, floppy disks, flash drives, smart cards, and optical data storage devices. The computer-readable recording medium can also be distributed across a networked computer system, enabling distributed storage and implementation of the computer-readable medium, for example, via in-vehicle telecommunications services or a Controller Area Network (CAN).

[0029] Unless specifically mentioned or obvious from the context, the term “approximately” as used herein shall be understood as being within the range of normal tolerances in the art, such as within 2 standard deviations of the mean.

[0030] It should be understood that the term "vehicle" or other similar terms used herein include motor vehicles in general, such as passenger cars (including SUVs, buses, trucks, etc.), various commercial vehicles, etc., and includes hybrid vehicles, electric vehicles, etc. A hybrid vehicle is a vehicle with two or more power sources, such as a gasoline-powered and an electric vehicle.

[0031] In the following, obstacle detection schemes for vehicles according to various exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0032] Figure 1 A schematic flowchart of a road obstacle detection method 1000 for a vehicle according to an embodiment of the present invention is shown. Figure 1 As shown, the obstacle detection method 1000 for vehicles includes the following steps: In step S110, a sensor signal is received, and the presence of a specific obstacle is detected based on the sensor signal; and In step S120, after the wheel contacts the specific obstacle, it is determined whether the vehicle has been blocked based on the vehicle's torque and / or the number of wheel rebounds.

[0033] In the context of this invention, the term "specific obstacle" refers to an obstacle that, based on sensor detection results, the electronic control unit (ECU) or other control unit cannot determine whether a vehicle can drive through. For example, an obstacle is detected based on sensor (e.g., camera and / or ultrasonic) signals, and the height of the obstacle is below the vehicle's minimum ground clearance (i.e., it will not collide with the vehicle), but a control unit such as a parking assist ECU cannot determine whether the obstacle will obstruct the normal movement of the vehicle. Such an obstacle is referred to as a "specific obstacle" in the context of this invention, and may also be called a "vague obstacle" or a "potential obstacle."

[0034] The aforementioned obstacle detection method 1000 for vehicles is particularly suitable for obstacle detection in automatic parking and / or automatic driving. In one embodiment, the obstacle detection method 1000 can detect suspected obstacles based on signals from sensors (e.g., proximity cameras / cameras, ultrasonic radar, etc.), and then use torque limiting to determine / confirm whether the suspected obstacle constitutes an obstacle blocking the vehicle. Thus, the obstacle detection method 1000 advantageously combines sensor detection with torque limiting, improving the accuracy of obstacle detection during automatic driving and automatic parking.

[0035] In one embodiment, step S110 includes: receiving signals from a camera or video camera, and determining that the obstacle belongs to a specific obstacle based on the boundary features of the obstacle detected by the signals from the camera or video camera. In one embodiment, the sensors include sensors capable of sensing surrounding objects, such as lidar, cameras, and millimeter-wave radar. In the context of autonomous driving environment perception, cameras are mainly used for: lane line detection; obstacle detection, which is equivalent to identifying and classifying obstacles; and traffic sign recognition, such as recognizing traffic lights and speed limit signs.

[0036] In one embodiment, step S120 includes: if the increase in torque of the vehicle is greater than a first threshold while the vehicle is stationary, then it is determined that the vehicle is blocked. That is, based on the sensor detecting a fuzzy obstacle, the increase in torque continues for a period of time (Ti) while the vehicle is stationary (standstill). B ) greater than the first threshold (Ti) Thod When the first threshold is reached, it can be determined that the current vehicle is blocked. In this embodiment, the first threshold can be a calibration value, which can be pre-calibrated based on the size, height, etc. of the roadblock.

[0037] In another embodiment, step S120 includes: determining that the vehicle is blocked when the number of rebounds after the wheel contacts the specific obstacle exceeds a second threshold. That is, based on the sensor detecting a blurred obstacle, when the number of rebounds after the wheel contacts the blurred obstacle exceeds a second threshold, it can be determined that the vehicle is blocked. In this embodiment, the second threshold can be a predetermined value, for example, 3, meaning that when the number of rebounds after the wheel contacts the blurred obstacle exceeds 3, it can be determined that the vehicle is blocked.

[0038] In yet another embodiment, step S120 may include: when the target torque of the vehicle is greater than the calibrated maximum torque (T) qMax When the vehicle is blocked, it is determined that the vehicle is obstructed. In one embodiment, the calibrated maximum torque is a maximum torque value calibrated based on the autonomous driving or automatic parking usage boundary, maximum gradient, and the height of the obstacle that can be traversed.

[0039] In one embodiment, although Figure 1 As not shown in the diagram, the road obstruction detection method 1000 may further include: sending a request to the electronic parking brake (EPB) system or feeding back the vehicle's status to the driver and / or a remote server when the vehicle is obstructed. In one embodiment, to ensure vehicle safety and provide redundant parking states, a request may be sent simultaneously to the electronic parking brake (EPB) and the P (Park) gear when the vehicle is obstructed. Additionally, in one embodiment, the obstruction status may be notified to the driver's mobile phone or a remote server (e.g., a cloud server / system).

[0040] Figure 2 A schematic diagram of a road obstacle detection device 2000 for a vehicle according to an embodiment of the present invention is shown. Figure 2 As shown, the obstacle detection device 2000 includes a detection unit 210 and a determination unit 220. The detection unit 210 receives sensor signals and detects the presence of a specific obstacle based on the sensor signals. The determination unit 220 determines whether the vehicle is blocked after the wheels contact the specific obstacle, based on the vehicle's torque and / or the number of wheel rebounds.

[0041] In the context of this invention, the term "specific obstacle" refers to an obstacle through which the electronic control unit (ECU) or other control unit cannot determine whether a vehicle can drive or pass, based on sensor detection results. For example, a sensor (e.g., a camera and / or ultrasound) detects an obstacle, but a control unit such as a parking assist ECU cannot determine whether the obstacle will obstruct the normal movement of the vehicle. Such an obstacle is referred to as a "specific obstacle" in the context of this invention, and may also be called a "vague obstacle" or a "potential obstacle."

[0042] The aforementioned obstacle detection device 2000 for vehicles is particularly suitable for obstacle detection in automated parking and / or automated driving. In one embodiment, the obstacle detection device 2000 detects suspected obstacles based on sensor signals (e.g., proximity camera / camera, ultrasonic radar, etc.) via a detection unit 210, and then uses a determination unit 220 to determine / confirm whether the suspected obstacle constitutes an obstacle blocking the vehicle by using torque limiting. Thus, the obstacle detection device 2000 advantageously combines sensor detection with torque limiting, improving the accuracy of obstacle detection during automated driving and automated parking.

[0043] In one embodiment, the detection unit 210 is configured to receive signals from a camera / camera and determine that the obstacle belongs to the specific obstacle based on the boundary features detected by the camera / camera signals. In one embodiment, the boundary features of the obstacle do not include the size of the obstacle. In one embodiment, the detection unit 210 receives sensor signals from sensors capable of sensing surrounding objects, including lidar, cameras, and millimeter-wave radar. In the context of autonomous driving environment perception, cameras are primarily used for: lane line detection; obstacle detection, which is equivalent to identifying and classifying obstacles; and traffic sign recognition, such as recognizing traffic lights and speed limit signs.

[0044] In one embodiment, the determining unit 220 is configured to determine the time (Ti) during which the vehicle's torque increases while the vehicle is stationary. B ) greater than the first threshold (Ti) Thod In the event that the vehicle is blocked, the first threshold can be a calibration value that can be pre-calibrated based on the size, height, etc. of the obstacle. In another embodiment, the determining unit 220 is configured to determine that the vehicle is blocked when the number of rebounds after the wheels contact the specific obstacle exceeds a second threshold (e.g., 3). In yet another embodiment, the determining unit 220 is configured to determine that the vehicle is blocked when the target torque (T) of the vehicle is... qtar The torque is greater than the rated maximum torque (T). qMax When the vehicle is blocked, it is determined that the vehicle is obstructed. In one embodiment, the calibrated maximum torque is a maximum torque value calibrated based on the autonomous driving or automatic parking usage boundary, maximum gradient, and the height of the obstacle that can be traversed.

[0045] In one embodiment, although Figure 2As not shown, the obstacle detection device 2000 may further include a sending unit for sending a request to the electronic parking brake system when the vehicle is blocked. In one embodiment, to ensure vehicle safety and provide redundant parking states, the sending unit may simultaneously send a request to both the electronic parking brake system (EPB) and the Parking Gear (P Gear) when the vehicle is blocked. Alternatively, in one embodiment, the sending unit may notify the driver's mobile phone or a remote server (e.g., a cloud server / system) of the vehicle being blocked.

[0046] Those skilled in the art will readily understand that the obstacle detection method for vehicles provided in one or more embodiments of the present invention can be implemented by a computer program. For example, when a computer storage medium (e.g., a USB flash drive) containing the computer program is connected to a computer, running the computer program will execute the obstacle detection method for vehicles according to one or more embodiments of the present invention.

[0047] Go to Figure 3 It illustrates a schematic diagram of a vehicle incorporating a parking assistance system or an automatic parking or automatic driving system, according to an embodiment of the present invention. Figure 3 In this designation, the parking assistance system (or automatic parking or automatic driving system) is designated as 310. This parking assistance system 310 interconnects with multiple types of sensors, including cameras 322, 324, 326, and 328 mounted around the vehicle body; ultrasonic sensors 331, 332, 333, and 334 mounted at the front of the vehicle; extended-range ultrasonic sensors 342 and 346 mounted on the left and right sides of the front of the vehicle; ultrasonic sensors 335, 336, 337, and 338 mounted at the rear of the vehicle; and extended-range ultrasonic sensors 344 and 348 mounted on the left and right sides of the rear of the vehicle. Based on data provided by these various types of sensors, the parking assistance system 310 can initially make a fuzzy judgment about the presence of a specific obstacle, and then further confirm whether the vehicle is blocked, i.e., whether the vehicle can drive directly through the obstacle, based on vehicle torque and / or wheel rebound count.

[0048] It should be noted that, Figure 3 This description illustrates only one embodiment of a vehicle incorporating a parking assistance system, automatic parking, or automatic driving system. Those skilled in the art, upon reading this specification, can modify the type and / or number of sensors as needed, and are not limited to this description. Figure 3 As shown.

[0049] In summary, the obstacle detection scheme for vehicles according to embodiments of the present invention can determine whether a vehicle is blocked based on the vehicle's torque and / or the number of wheel rebounds when a specific obstacle is detected. This scheme can further improve the accuracy of obstacle detection, and is particularly helpful in enhancing safety during automatic parking or autonomous driving processes.

[0050] Although the foregoing specification describes only some embodiments of the invention, those skilled in the art will understand that the invention can be implemented in many other forms without departing from its spirit and scope. Therefore, the examples and embodiments shown are to be considered illustrative rather than restrictive, and the invention may encompass various modifications and substitutions without departing from the spirit and scope of the invention as defined in the appended claims.

Claims

1. A roadblock detection method for a vehicle, characterized by, The method includes: The system receives sensor signals and detects the existence of a specific obstacle based on the sensor signals. The specific obstacle refers to an obstacle that the electronic control unit (ECU) or other control unit cannot determine whether the vehicle can drive through based on the sensor detection results. After the wheels contact the specific obstacle, it is determined whether the vehicle is blocked based on the vehicle's torque and / or the number of wheel rebounds. Specifically, the vehicle is blocked if the number of wheel rebounds after contacting the specific obstacle exceeds a preset threshold or if the vehicle's target torque is greater than a calibrated maximum torque. If the vehicle is blocked, a request is sent to the electronic parking brake system. The calibrated maximum torque is a maximum torque value calibrated based on the boundaries of autonomous driving or automatic parking, the maximum gradient, and the height of obstacles that can be traversed.

2. The method as described in claim 1, wherein, Receiving sensor signals and detecting the presence of a specific obstacle based on the sensor signals includes: The system receives signals from a camera / camera and determines that the obstacle belongs to the specific obstacle by detecting the boundary features of the obstacle based on the signals from the camera / camera.

3. The method of claim 1, further comprising: In the event that the vehicle is blocked, the vehicle's status is fed back to the driver and / or a remote server.

4. A road obstacle detection device for vehicles, characterized in that, The device includes: The detection unit is used to receive sensor signals and detect the existence of a specific obstacle based on the sensor signals. The specific obstacle refers to an obstacle that the electronic control unit (ECU) or other control unit cannot determine whether the vehicle can drive through based on the sensor detection results. A determining unit is configured to determine whether a vehicle is blocked based on the vehicle's torque and / or the number of wheel rebounds after the wheel contacts the specific obstacle, wherein the determining unit is configured to determine that the vehicle is blocked when the number of wheel rebounds after contacting the specific obstacle exceeds a preset threshold or when the vehicle's target torque is greater than a calibrated maximum torque; and The transmitting unit is configured to send a request to the electronic parking brake system when the vehicle is blocked. The calibrated maximum torque is a maximum torque value calibrated based on the boundaries of autonomous driving or automatic parking, the maximum gradient, and the height of obstacles that can be traversed.

5. The device as claimed in claim 4, wherein, The detection unit is configured to receive signals from a camera / camera and determine that the obstacle belongs to the specific obstacle based on the boundary features of the obstacle detected by the camera / camera signals.

6. The device as claimed in claim 4, wherein, The sending unit is also configured to feed back the status of the vehicle to the driver and / or a remote server.

7. A computer storage medium, characterized in that, The medium includes instructions that, when executed, perform the method as described in any one of claims 1 to 3.

8. A parking assistance system, the system comprising the device as claimed in any one of claims 4 to 6.

9. An automatic parking or automatic driving system, the system comprising the device as claimed in any one of claims 4 to 6.

10. A vehicle comprising the parking assistance system of claim 8 or the automatic parking or automatic driving system of claim 9.

Images