Control methods, electronic devices, and readable storage media for autonomous vehicles

Abstract

This application provides a control method, electronic device, and readable storage medium for autonomous vehicles. The method includes: in response to detecting a moving target object in a potential blind spot based on first data from a first time node of a data acquisition module, acquiring second data from a second time node of the data acquisition module, wherein the potential blind spot is a region where the detection module is in an unstable detection state, the unstable detection state being that the time for which data satisfying preset conditions is not detected exceeds a preset threshold, and the second time node is the next time node after a first preset time interval from the first time node; and in response to the inability to detect the moving target object based on the second data, controlling the following vehicle to execute a preset safety strategy. This application solves the technical problem of high safety risks in sensor detection blind spots for autonomous vehicles in related technologies, achieving the technical effect of improving the safety of autonomous vehicles.

Description

Technical Field

[0001] This application relates to the field of autonomous driving, and in particular to control methods, electronic devices, and readable storage media for autonomous vehicles. Background Technology

[0002] Currently, autonomous vehicles (especially autonomous trucks) are able to perceive and identify surrounding traffic participants through onboard perception systems in actual road operations, thereby providing data support for autonomous driving decisions. However, there are still certain detection blind spots. Therefore, in extreme cases, small traffic participants may still enter the aforementioned detection blind spots.

[0003] Therefore, how to further reduce the traffic safety risks of autonomous vehicles in blind spots has become an urgent technical problem to be solved in this field. Summary of the Invention

[0004] The control method, electronic device, and readable storage medium for autonomous vehicles provided in this application are intended to solve one or more of the aforementioned technical problems.

[0005] In a first aspect, embodiments of this application provide a control method for an autonomous vehicle, applied to a following vehicle in platooning autonomous driving. The following vehicle is equipped with a perception system, which includes at least a data acquisition module and a detection module. The data acquisition module acquires surrounding environmental data of the following vehicle based on multiple sensors. The detection module is used to detect target objects in the surrounding environmental data. The control method includes: in response to detecting a moving target object in a potential blind spot based on first data at a first time node of the data acquisition module, acquiring second data at a second time node of the data acquisition module, wherein the potential blind spot is an area where the detection module is in an unstable detection state, the unstable detection state is that the time for which no data satisfying a preset condition is detected exceeds a preset threshold, and the second time node is the next time node after a first preset time interval from the first time node; in response to the inability to detect the moving target object based on the second data, controlling the following vehicle to execute a preset safety strategy.

[0006] Secondly, this application also provides a control method for an autonomous vehicle, applied to a lead vehicle in platooning autonomous driving. The control method includes: receiving operating status information sent by a following vehicle, wherein the operating status information includes at least the disappearance area of ​​the target moving object; and displaying the disappearance area on a human-machine interface (HMI) to abnormally resolve the following vehicle executing the safety strategy in the above control method.

[0007] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor, when executing the computer program, implements the method described in any of the above-mentioned embodiments.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method described in any of the above-mentioned embodiments.

[0009] Fifthly, embodiments of this application provide a computer program product, including computer instructions, which, when executed by a processor, implement the method described in any of the above-mentioned embodiments.

[0010] In this embodiment, in response to the detection of a moving target object in a potential blind spot based on the first data of the first time node of the acquisition module, the second data of the second time node of the acquisition module is acquired. The potential blind spot is an area where the detection module is in an unstable detection state, where the time during which no data meeting preset conditions is detected exceeds a preset threshold. The second time node is the next time node after a first preset time interval from the first time node. In response to the inability to detect the moving target object based on the second data, the following vehicle is controlled to execute a preset safety strategy. In other words, after pre-calibrating the potential blind spots of the autonomous vehicle, this embodiment controls the autonomous vehicle to execute a preset safety strategy (e.g., emergency braking) based on a judgment mechanism that detects a moving object entering and disappearing from the potential blind spot. This solves the technical problem of high safety risks in sensor detection blind spots for autonomous vehicles in related technologies, achieving the technical effect of improving the safety of autonomous vehicles.

[0011] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application, it can be implemented according to the contents of the specification. In order to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0012] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments according to this application and should not be construed as limiting the scope of this application.

[0013] Figure 1 This illustration shows an application scenario diagram of a control method for an autonomous vehicle provided in an embodiment of this application;

[0014] Figure 2A flowchart of a control method for an autonomous vehicle provided in an embodiment of this application is shown;

[0015] Figure 3 A schematic diagram of a potential blind zone calibration method provided in an embodiment of this application is shown;

[0016] Figure 4a A schematic diagram of another potential blind zone calibration method provided in an embodiment of this application is shown;

[0017] Figure 4b This illustration shows a schematic diagram of yet another potential blind zone calibration method provided in an embodiment of this application;

[0018] Figure 5 This paper shows a block diagram of a control device for an autonomous vehicle provided in an embodiment of this application;

[0019] Figure 6 A flowchart of another control method for an autonomous vehicle provided in an embodiment of this application is shown;

[0020] Figure 7 A flowchart of a control method for autonomous vehicle platooning provided in an embodiment of this application is shown;

[0021] Figure 8 A schematic diagram of a visual interface for a navigation vehicle provided in an embodiment of this application is shown;

[0022] Figure 9 This invention illustrates a block diagram of a control device for an autonomous vehicle provided in an embodiment of this application.

[0023] Figure 10 A block diagram of an electronic device used to implement embodiments of this application is shown. Detailed Implementation

[0024] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the concept or scope of this application. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0025] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and all of them fall within the protection scope of the embodiments of this application.

[0026] Although existing autonomous vehicles have optimized the type and layout of sensors to minimize blind spots, areas close to the vehicle body can still miss detections at the perception level due to increased sensor distortion and significant changes in viewing angle. Moreover, according to feedback from actual road tests in the industry, there are still instances of vehicles dragging bicycles, indicating that there is still considerable room for improvement in the processing capabilities of related technologies in identifying and handling objects in blind spots.

[0027] In view of the above problems, the technical solution of this application and how the technical solution of this application solves the aforementioned technical problems will be described in detail below with specific embodiments. The listed specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0028] The application scenario of the autonomous vehicle control method provided in this application embodiment can include multiple autonomous vehicles (e.g., logistics trucks) adopting a platooning mode (also known as a formation driving mode). In this platooning mode, each vehicle travels in a preset platoon order, maintaining a safe distance and continuously communicating to achieve collaborative control and information sharing. Regarding platoon configuration, the vehicle at the front is the lead vehicle, which typically features L2 assisted driving capabilities, allowing for human driver control and reducing driver workload through limited automated driving functions, including lane keeping assist, cruise assist, and emergency braking assist. In this application scenario, the lead vehicle driver is responsible for driving the vehicle and guiding the entire platoon forward, while also providing manual intervention capabilities in complex road environments or emergencies to ensure platoon safety and lead the platoon out of trouble in special situations. The other vehicles in the platoon besides the lead vehicle are follow vehicles, which typically feature L4 autonomous driving capabilities, enabling them to automatically perform following, path keeping, distance control, and obstacle avoidance operations based on communication information from the lead vehicle and the entire platoon without a driver. The following vehicles receive real-time operational status information, speed commands, route planning data, and emergency control commands from the lead vehicle via V2V (Vehicle-to-Vehicle) or V2X (Vehicle-to-Everything) links. Simultaneously, they feed back their own operational status, fault information, and environmental perception results to the lead vehicle, thereby optimizing the overall safety and efficiency of the convoy. In this convoy configuration, a fleet typically has only one driver residing in the lead vehicle, responsible for overall guidance and safety, while the remaining vehicles rely entirely on the autonomous driving system for control and operation. This configuration significantly reduces labor costs, improves long-distance transportation efficiency, and enables multi-vehicle collaborative operation while maintaining safety. For example, such as... Figure 1 The image shows the formation of autonomous vehicles.

[0029] In the aforementioned application scenarios, this application provides a control method for autonomous vehicles, applied to following vehicles in platooning autonomous driving. The perception system includes at least a data acquisition module and a detection module. The data acquisition module collects surrounding environmental data of the following vehicle based on multiple sensors, and the detection module detects target objects within the surrounding environmental data. Optionally, in this application embodiment, the multiple sensors can be arranged using a combination of similar sensor fields of view to ensure omnidirectional, blind-spot-free coverage of the vehicle's near and far ends. For example, a combination of multiple camera fields of view can achieve panoramic monitoring of the environment surrounding the vehicle, while a combination of multiple millimeter-wave radar fields of view can perform long-range detection of objects around the vehicle. Furthermore, the fields of view of different types of sensors overlap as much as possible to achieve redundancy and complementarity. This design ensures that even if one sensor malfunctions or its signal is blocked, other sensors can still provide sufficient environmental perception data, thereby improving the reliability and fault tolerance of the perception system and providing strong support for the safe operation of autonomous vehicles. For example, the overlapping fields of view of cameras and millimeter-wave radar can complement each other. Cameras provide high-resolution image information in clear weather, while millimeter-wave radar provides reliable object detection information in adverse weather conditions. The combination of the two allows vehicles to accurately perceive their surroundings in various environments. Meanwhile, the addition of lidar further enhances perception capabilities. Its high-precision 3D perception can accurately measure the distance and shape of objects, complementing the advantages of cameras and millimeter-wave radar. In complex road conditions and nighttime weather, lidar can effectively compensate for the shortcomings of other sensors, ensuring the vehicle's comprehensive perception of its surroundings and significantly improving the safety of autonomous vehicles.

[0030] like Figure 2 The diagram shown is a flowchart of a control method for an autonomous vehicle according to an embodiment of this application. The method may include:

[0031] Step S202: In response to the detection of a moving target object in a potential blind zone based on the first data of the first time node of the acquisition module, the second data of the second time node of the acquisition module is obtained. The potential blind zone is the area where the detection module is in an unstable detection state. The unstable detection state is that the time during which no data meeting the preset conditions is detected exceeds a preset threshold. The second time node is the next time node after a first preset time interval from the first time node.

[0032] It is understood that, in this embodiment of the application, the aforementioned potential blind zone is defined based on whether the detection module can reliably detect the target object as a boundary. For example, if no target object is detected within 5 seconds, or if the interval between any two detected frames exceeds 200ms, the target object is included in the potential blind zone.

[0033] Optionally, in this embodiment, the specific setting of the first preset time can be flexibly set according to parameters such as application scenario and security requirements, and is not specifically limited. For example, the first preset time can be determined by predicting the remaining time for a moving object to enter the edge of a potential blind zone using a target tracking algorithm.

[0034] In addition, it is understood that the aforementioned moving objects may be traffic participants and other moving entities that have speed or motion tendencies relative to the road within the vehicle operating environment, including but not limited to: motor vehicles, non-motor vehicles, pedestrians, and obstacles that may move with changes in the environment.

[0035] In step S204, in response to the inability to detect the target moving object based on the second data, the following vehicle is controlled to execute a preset safety policy.

[0036] In step S204 above, the inability to detect the target moving object based on the second data can be understood as: the target moving object cannot be detected in the fully stable detection area, and the target moving object cannot be detected in the potential blind zone.

[0037] Through the above steps S202~S204, in response to the detection of a target moving object in a potential blind spot based on the first data of the first time node of the acquisition module, the second data of the second time node of the acquisition module is acquired. The potential blind spot is the area where the detection module is in an unstable detection state, where the time during which no data meeting preset conditions is detected exceeds a preset threshold. The second time node is the next time node after a first preset time interval from the first time node. In response to the inability to detect the target moving object based on the second data, the following vehicle is controlled to execute a preset safety strategy. In other words, after pre-calibrating the potential blind spots of the autonomous vehicle, this embodiment controls the autonomous vehicle to execute a preset safety strategy (e.g., emergency braking) based on a judgment mechanism that determines whether a moving object enters the potential blind spot and then disappears. This solves the technical problem of high safety risks in sensor detection blind spots for autonomous vehicles in related technologies, achieving the technical effect of improving the safety of autonomous vehicles.

[0038] In one possible implementation, the method further includes determining a potential blind spot. For example, determining the potential blind spot may include: S11, determining the potential blind spot based on the detection state of the detection module during the peripheral movement of the test object within the autonomous vehicle.

[0039] It is understood that the aforementioned test objects include various types and sizes to simulate moving objects of different shapes, including but not limited to: large test objects, small test objects, tall test objects, and short test objects. By introducing test objects of different shapes and sizes during the testing process, the performance of the detection module in terms of detection range, target recognition, and adaptability can be verified. Furthermore, it is understood that the perimeter of the aforementioned autonomous vehicle typically includes the front, rear, and both sides of the vehicle.

[0040] Optionally, in this embodiment, the detection state includes, but is not limited to, stable detection and unstable detection. When the detection state is stable detection, the test object is controlled to perform a first movement operation; when the detection state is unstable detection, the test object is controlled to perform a second movement operation, wherein the second movement operation and the first movement operation are two operations with opposite paths. Figure 3 As shown, the dashed area represents a potential blind spot, and the blue circle can be interpreted as a moving object. The movement process of this moving object is as follows: Figure 3 As shown by the curve in the middle.

[0041] In this embodiment of the application, step S11 above, by combining the dynamic movement of the test object around the autonomous vehicle with the detection status determination of the detection module, can accurately define the range and boundary of the potential blind spot around the autonomous vehicle, further improving the safety and rationality of autonomous driving decisions.

[0042] Optionally, in this embodiment, S11 may include: S111, dividing the area around the autonomous vehicle within a preset range into different point sets according to a specified interval; S112, repeating the following steps until all points in the point set have been traversed: taking any point in the point set as the starting point, controlling the test object to move to the starting point, and determining the detection state of the detection module; if the detection state is stable detection, setting the first target point close to the autonomous vehicle as the starting point; if the detection state is unstable detection, setting the second target point far from the autonomous vehicle as the starting point; S113, connecting the points with unstable detection states to form an envelope to obtain the potential blind zone.

[0043] Understandably, in steps S111-S113 above, the autonomous vehicle can first be parked in an open area, and the calibration system can be activated. When the test subject (e.g., a pedestrian) can be detected stably, the calibration system will give a first prompt (e.g., a short horn blast); if it cannot be detected stably, it will give a second prompt (e.g., a long horn blast). Then, the area is divided into multiple points at certain intervals (e.g., 0.5-meter intervals). The test subject is positioned at one of these points. If the detection module can detect the subject stably, it outputs the first prompt. Then, the subject moves one space closer to the vehicle and remains stationary for a few seconds, waiting for feedback from the detection module. This process is repeated for each point. The detection module confirms the detection status of each point, connects the detected areas to form an envelope, and identifies potential blind spots. Figures 4a-4b As shown, where, Figure 4a The dots in the diagram represent points. Figure 4b The blue dots represent points that can be detected reliably, while the red dots represent points that cannot be detected reliably.

[0044] To prevent misjudgment, in this embodiment of the application, S21 is also proposed to expand the potential blind zone.

[0045] Optionally, in the embodiments of this application, the above-mentioned methods for expanding the potential blind zone include at least two methods: the first is a static expansion method, and the second is a dynamic expansion method, which can be understood as a dynamic adaptation and adjustment scheme for the potential blind zone based on real-time operating conditions. These will be explained in detail below.

[0046] Regarding the above-mentioned static expansion method, the embodiments of this application propose: S211, determining the boundary position of the potential blind zone; S212, expanding the boundary position by a preset distance along a preset expansion direction.

[0047] It is understood that the aforementioned preset distance is based on preset fixed thresholds / empirical parameters (such as basic blind spot distance thresholds corresponding to different vehicle speed ranges, and default blind spot expansion coefficients for different road types), setting the initial expansion range of the blind spot area once. This range does not change with real-time operating conditions when there are no dynamic triggering conditions. For example, the aforementioned preset distance can be 0.2m.

[0048] Regarding the above-mentioned dynamic expansion method, the embodiments of this application propose: S213, determining the blind spot expansion coefficient based on target information, wherein the target information includes at least one of the following real-time information of the autonomous vehicle: motion state information, environmental information, surrounding moving object state information, and the state of the detection module; S214, expanding the potential blind spot based on the blind spot expansion coefficient.

[0049] Understandably, during autonomous driving, at least one type of real-time data is collected, including the vehicle's motion status information, environmental information, status information of surrounding moving objects, and the status of the detection module. This real-time data is then quantified into a dynamic expansion coefficient using a preset algorithm. Based on this dynamic expansion coefficient, the size of the potential blind spot range is further adjusted.

[0050] Optionally, the algorithm for calculating the dynamic expansion coefficient may include risk weights corresponding to vehicle motion state information (such as vehicle speed, steering angle, acceleration, etc.), perception attenuation compensation weights corresponding to environmental information (such as visibility, road surface adhesion coefficient, light intensity, etc.), safety redundancy weights corresponding to surrounding moving object state information (such as surrounding target collision risk, road type risk level, static obstruction degree, etc.), and detection capability compensation weights corresponding to detection module state (such as uncertainty of data fusion results, etc.).

[0051] Expanding the potential blind spot through the above steps S211~S212 or S213~S214 can not only accurately identify the basic detection blind spot of autonomous vehicles under normal operating conditions, but also uncover hidden blind spots in special scenarios such as complex environments, sensor failures, and vehicle dynamic attitudes, making the blind spot judgment results more consistent with real autonomous driving scenarios and reducing the risk of collisions caused by missed blind spot detection.

[0052] Due to the randomness of the movement of a moving object, it may disappear from a potential blind spot and then reappear. To address this, this application embodiment further proposes: detecting the target moving object in response to third data collected by the sensing system at a third time node, wherein the third time node is the next time node after a second preset time interval from the second time node. The method further includes:

[0053] S31 controls the following vehicle to travel according to the platooning parameters.

[0054] It is understood that, in the embodiments of this application, the specific setting of the second preset time can be flexibly set according to parameters such as application scenarios and security requirements, and is not specifically limited. For example, it can be set to the same time as the collection cycle of the sensing system, or it can be set to multiple collection cycles.

[0055] By using the above step S31, it can be ensured that the platooning continues to operate without affecting the safe driving of the autonomous vehicles.

[0056] In one possible implementation, controlling the following vehicle to execute a preset safety policy may include: S41, controlling the following vehicle to perform a downgraded parking operation.

[0057] Understandably, the aforementioned downgraded parking operation controls the following vehicle to enter emergency stop mode and no longer includes the advanced capabilities of the individual vehicle.

[0058] Corresponding to the application scenarios and methods provided in the embodiments of this application, the embodiments of this application also provide a control device for an autonomous vehicle, applied to a following vehicle in platooning autonomous driving. The following vehicle is equipped with a perception system, which includes at least a data acquisition module and a detection module. The data acquisition module collects surrounding environmental data of the following vehicle based on multiple sensors, and the detection module is used to detect target objects in the surrounding environmental data. Figure 5 The diagram shown is a structural block diagram of a control device for an autonomous vehicle according to an embodiment of this application. The device may include:

[0059] The acquisition module 52 is used to acquire second data at a second time node of the acquisition module in response to the detection of a target moving object in a potential blind zone based on the first data of the first time node of the acquisition module. The potential blind zone is the area where the detection module is in an unstable detection state. The unstable detection state is when the time for which no data meeting the preset conditions is detected exceeds a preset threshold. The second time node is the next time node after a first preset time interval from the first time node.

[0060] The first control module 54 is used to control the following vehicle to execute a preset safety strategy in response to the inability to detect the target moving object based on the second data.

[0061] pass Figure 5 The device shown, in response to detecting a moving target object in a potential blind spot based on first data from a first time node of the acquisition module, acquires second data from a second time node of the acquisition module. The potential blind spot is an area where the detection module is in an unstable detection state, defined as a period exceeding a preset threshold during which no data meeting preset conditions is detected. The second time node is the next time node after a first preset time interval from the first time node. In response to the inability to detect the moving target object based on the second data, the device controls the following vehicle to execute a preset safety strategy. In other words, this embodiment, after pre-calibrating the potential blind spot of the autonomous vehicle, controls the autonomous vehicle to execute a preset safety strategy (e.g., emergency braking) based on a judgment mechanism that detects a moving object entering and disappearing from the potential blind spot. This solves the technical problem of high safety risks in sensor detection blind spots for autonomous vehicles in related technologies, achieving the technical effect of improving the safety of autonomous vehicles.

[0062] In one possible implementation, the above-described apparatus further includes a determining module for determining the potential blind spot, wherein the determining module includes a determining unit for determining the potential blind spot based on the detection state of the detection module during the peripheral movement of the test object in the autonomous vehicle.

[0063] The determining unit includes: a dividing subunit, used to divide the area around the autonomous vehicle within a preset range into different point sets according to a specified interval; a processing subunit, used to repeatedly execute the following steps until all points in the point sets have been traversed: taking any point in the point set as the starting point, controlling the test object to move to the starting point, and determining the detection state of the detection module; if the detection state is stably detectable, setting the first target point close to the autonomous vehicle as the starting point; if the detection state is not stably detectable, setting the second target point far from the autonomous vehicle as the starting point; and an obtaining subunit, used to connect the points with the detection state of not stably detectable to form an envelope, thereby obtaining the potential blind zone.

[0064] Optionally, the above-described apparatus may further include a processing module for expanding the potential area.

[0065] The aforementioned processing module is further configured to determine the boundary position of the potential blind spot; and expand the potential blind spot by a preset distance along a preset expansion direction outside the boundary position. Alternatively, the aforementioned processing module is further configured to determine a blind spot expansion coefficient based on target information, wherein the target information includes at least one of the following real-time information of the autonomous vehicle: motion state information, environmental information, surrounding moving object state information, and the state of the detection module; and expand the potential blind spot based on the blind spot expansion coefficient.

[0066] Optionally, in response to the detection of the target moving object based on third data at a third time node of the acquisition module, wherein the third time node is the next time node after a second preset time interval from the second time node, the device further includes: a second control module for controlling the following vehicle to drive according to platooning parameters.

[0067] The aforementioned first control module is also used to control the following vehicle to perform a downgraded parking operation.

[0068] The functions of each module in each device in the embodiments of this application can be found in the corresponding description in the above method, and they have corresponding beneficial effects, which will not be repeated here.

[0069] Corresponding to the application scenarios and methods provided in the embodiments of this application, the embodiments of this application also provide a control method for autonomous vehicles, applied to the lead vehicle in platooning autonomous driving. For example... Figure 6The diagram shown is a control flowchart of an autonomous vehicle according to an embodiment of this application, including:

[0070] S602, receive the running status information sent by the following vehicle, wherein the running status information includes at least the disappearance area of ​​the target moving object.

[0071] Understandably, the aforementioned disappearing area can be a directional division around the autonomous vehicle, such as the left side, right side, front, and rear areas. Alternatively, it could be a more precise spatial range, such as the left front corner, right front corner, or a specific angular interval behind the vehicle.

[0072] S604, the disappearing area is displayed on the human-machine interface (HMI) to abnormally resolve the following vehicle that is implementing the safety strategy in the above control method.

[0073] Through the above steps S602~S604, the driver of the navigation vehicle can intuitively know the abnormal area by displaying the disappearance area of ​​the human-machine interface (HMI), thereby improving the efficiency of abnormal resolution.

[0074] The aforementioned operating status information also includes image information collected by the perception system installed on the vehicle. Optionally, in this embodiment, the above-mentioned prompting of the disappeared area on the HMI may include: S51, highlighting the disappeared area based on the image information to obtain processed image information; S52, combining voice information to prompt the processed image information on the HMI.

[0075] It is understood that in the above steps S51~S52, the above image information can be a plan view of the autonomous vehicle, and then the disappearing area of ​​the left front corner or the right side is highlighted in the plan view of the autonomous vehicle, and a voice prompt is given.

[0076] The embodiments of this application will be illustrated below with specific examples.

[0077] Example 1

[0078] This example uses a pedestrian as the target moving object and proposes a closed-loop processing method within the following vehicle. The method includes: acquiring real-time operating data of the autonomous vehicle, expanding the potential blind spot, and controlling the following vehicle to downgrade and stop when a pedestrian enters the potential blind spot without being detected based on the pre-calibrated potential blind spot. If the pedestrian is detected again, the following vehicle returns to normal.

[0079] Simultaneously, based on the product form of the queue, there is a lead vehicle (front vehicle) assisting the following vehicle in completing the confirmation and recovery function. When a pedestrian enters the blind spot and is not detected, the area where the pedestrian disappeared and the image information are simultaneously transmitted to the lead vehicle. The driver of the lead vehicle renders and highlights the disappearance area, and provides a voice prompt. The driver, ensuring their own vehicle's safety, confirms whether it is safe within the blind spot of the following vehicle. For example, the driver pulls over and carefully checks. This example implements a safety strategy of slowing down after a pedestrian disappears from a potential blind spot and a collaborative mechanism between the front and rear vehicles to degrade the status quo. See details. Figure 7 Steps S701-708 in the process.

[0080] Example 2

[0081] Taking a truck with multiple sensors arranged as three fisheye cameras and two ordinary cameras, and a pedestrian as the target moving object, the three fisheye cameras cover the area near the front of the truck, while the two rear cameras supplement the field of view of the trailer. When a pedestrian enters a potential blind spot and is not detected, the area where the pedestrian disappears, along with the image information, is simultaneously transmitted to the truck ahead. The driver of the truck ahead renders the image, highlighting the camera corresponding to the disappearing area. Figure 8 The system uses a fisheye camera on the right side of the road. After ensuring the safety of their own vehicle, the driver pulls the car over to the side of the road and carefully checks whether it is safe in the potential blind spot of the vehicle behind. If the abnormality is resolved, the system will recover.

[0082] Corresponding to the application scenarios and methods provided in the embodiments of this application, the embodiments of this application also provide a control device for an autonomous vehicle, applied to a lead vehicle in platooning autonomous driving. For example... Figure 9 The diagram shown is a structural block diagram of a control device for an autonomous vehicle according to an embodiment of this application. The device may include:

[0083] The receiving module 92 is used to receive the running status information sent by the following vehicle, wherein the running status information includes at least the disappearance area of ​​the target moving object;

[0084] The prompt module 94 is used to prompt the disappearing area on the human-machine interface (HMI) to resolve the abnormality of the following vehicle executing the safety strategy in the above control method.

[0085] pass Figure 9 The device shown allows the driver of the navigation vehicle to intuitively identify the abnormal area in the area where the human-machine interface (HMI) prompts disappear, thus improving the efficiency of abnormal resolution.

[0086] Optionally, the above-mentioned operating status information also includes image information collected by the perception system installed on the following vehicle. The above-mentioned prompting module 94 is also used to highlight the disappearing area on the image information to obtain processed image information; combined with voice information, the processed image information is prompted on the HMI.

[0087] The functions of each module in each device in the embodiments of this application can be found in the corresponding description in the above method, and they have corresponding beneficial effects, which will not be repeated here.

[0088] Figure 10 This is a block diagram of an electronic device used to implement embodiments of this application. For example... Figure 10 As shown, the electronic device includes a memory 1001 and a processor 1002. The memory 1001 stores a computer program that can run on the processor 1002. When the processor 1002 executes the computer program, it implements the method described in the above embodiments. The number of memories 1001 and processors 1002 can be one or more.

[0089] The electronic device also includes:

[0090] Communication interface 1003 is used to communicate with external devices and perform data exchange and transmission.

[0091] If the memory 1001, processor 1002, and communication interface 1003 are implemented independently, they can be interconnected via a bus to communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0092] Optionally, in a specific implementation, if the memory 1001, processor 1002, and communication interface 1003 are integrated on a single chip, then the memory 1001, processor 1002, and communication interface 1003 can communicate with each other through an internal interface.

[0093] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method provided in this application.

[0094] This application also provides a chip including a processor for calling and executing instructions stored in a memory, causing a communication device with the chip installed to perform the method provided in this application.

[0095] This application also provides a chip, including: an input interface, an output interface, a processor, and a memory. The input interface, output interface, processor, and memory are connected through an internal connection path. The processor is used to execute code in the memory. When the code is executed, the processor is used to execute the method provided in the application embodiment.

[0096] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting Advanced Reduced Instruction Set Machines (ARM) architecture.

[0097] Further, optionally, the aforementioned memory may include read-only memory and random access memory. The memory may be volatile memory or non-volatile memory, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available. Examples include Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Sync Link DRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

[0098] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0099] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0100] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0101] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process. Furthermore, the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functionality involved.

[0102] The logic and / or steps described in the flowchart or otherwise herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0103] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. All or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware, the program being stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiments.

[0104] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. This storage medium can be a read-only memory, a disk, or an optical disk, etc.

[0105] The above description is merely an exemplary embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope described in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A control method for an autonomous vehicle, characterized in that, A following vehicle used in platooning autonomous driving, the following vehicle is equipped with a perception system, the perception system including at least a data acquisition module and a detection module. The data acquisition module collects surrounding environmental data of the following vehicle based on multiple sensors, and the detection module is used to detect target objects in the surrounding environmental data. The control method includes: In response to the detection of a target moving object in a potential blind zone based on the first data of the first time node of the acquisition module, the second data of the second time node of the acquisition module is acquired, wherein the potential blind zone is the area where the detection module is in an unstable detection state, the unstable detection state is that the time for which no data meeting the preset conditions is detected exceeds a preset threshold, and the second time node is the next time node after a first preset time interval from the first time node; In response to the inability to detect the target moving object based on the second data, the following vehicle is controlled to execute a preset safety strategy; The potential blind spot is determined based on the detection status of the detection module during the test object's movement around the autonomous vehicle. The method further includes: expanding the potential blind spot, wherein expanding the potential blind spot includes: determining a blind spot expansion coefficient based on target information, wherein the target information includes at least one of the following real-time information of the autonomous vehicle: motion state information, environmental information, surrounding moving object state information, and the state of the detection module; and expanding the potential blind spot based on the blind spot expansion coefficient.

2. The method according to claim 1, characterized in that, Based on the detection state of the detection module during the peripheral movement of the test object in the autonomous vehicle, the potential blind spot is determined, including: The area around the autonomous vehicle within a preset range is divided into different sets of points according to a specified interval; Repeat the following steps until all points in the point set have been traversed: Using any point in the point set as the starting point, control the test object to move to the starting point and determine the detection state of the detection module; if the detection state is that it can be stably detected, set the first target point close to the autonomous vehicle as the starting point; if the detection state is that it cannot be stably detected, set the second target point far away from the autonomous vehicle as the starting point. The potential blind zone is obtained by connecting the points that are unstable to be detected.

3. The method according to claim 1, characterized in that, The expansion of the potential blind spot also includes: Determine the boundary location of the potential blind zone; The distance is increased by a predetermined distance along a predetermined expansion direction outside the boundary position.

4. The method according to claim 1, characterized in that, In response to the detection of the target moving object based on third data at a third time node of the acquisition module, wherein the third time node is the next time node after a second preset time interval from the second time node, the method further includes: The following vehicles are controlled to travel according to the platooning parameters.

5. The method according to claim 1, characterized in that, Controlling the following vehicle to execute a preset safety strategy includes: Control the following vehicle to perform a downgraded parking operation.

6. A control method for an autonomous vehicle, characterized in that, The control method for a lead vehicle used in platooning autonomous driving includes: Receive running status information sent by the following vehicle, wherein the running status information includes at least the disappearance area of ​​the target moving object; The disappearing area is displayed on the human-machine interface (HMI) to abnormally remove the following vehicle from the safety policy implemented in any one of claims 1 to 5.

7. The method according to claim 6, characterized in that, The operating status information also includes the image information of the following vehicle, and the HMI prompting about the disappearing area includes: The vanished area is highlighted based on the image information to obtain the processed image information; The processed image information is displayed on the HMI in conjunction with the voice information.

8. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory, wherein the processor, when executing the computer program, implements the method of any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

10. A computer program product, characterized in that, Includes computer instructions, wherein when executed by a processor, the computer instructions implement the method described in any one of claims 1-7.

Images