Method, device and equipment for autonomous vehicle and computer readable storage medium

Abstract

According to the embodiment of the invention, a method, device and equipment for an autonomous vehicle and a computer readable storage medium are provided. The method includes, in response to detecting an anomaly associated with the autonomous vehicle, determining to enter a target mode of minimum risk operation (MRM) of a minimum risk condition (MRC). And obtaining strategy information corresponding to the target mode of the MRM, wherein the strategy information at least indicates the maximum influence degree allowed by the target mode on the traffic environment. And controlling the parking process of the autonomous vehicle based on the current traffic environment and the strategy information of the autonomous vehicle. Therefore, according to the embodiment of the invention, the influence degree of parking on traffic can be reduced, and meanwhile, it is ensured that the vehicle can quickly and safely enter the minimum risk condition MRC in the abnormal state.

Description

Technical Field

[0001] Example embodiments of the present disclosure relate generally to the field of computers, and more particularly to methods, apparatuses, devices, and computer-readable storage media for autonomous vehicles. Background Art

[0002] Autonomous driving is a technology that uses computers to replace human drivers or assist human drivers to perceive the vehicle's surroundings, plan the vehicle's movement trajectory, and control the vehicle to a designated destination.

[0003] During the driving process of the autonomous vehicle, some faults may occur. In this case, how to control the autonomous vehicle to stop safely is an important part of improving driving safety and reliability. Summary of the invention

[0004] In a first aspect of the present disclosure, a method for an autonomous vehicle is provided. The method includes: in response to detecting an abnormality associated with the autonomous vehicle, determining a target mode of a minimum risk maneuver (MRM) for entering a minimum risk condition (MRC). Obtaining strategy information corresponding to the target mode of the MRM, the strategy information at least indicating a maximum degree of impact on a traffic environment allowed by the target mode. Based on the current traffic environment of the autonomous vehicle and the strategy information, controlling a parking process of the autonomous vehicle.

[0005] In a second aspect of the present disclosure, a device for an autonomous vehicle is provided. The device includes: a target mode determination module, configured to determine a target mode of a minimum risk operation MRM for entering a minimum risk condition MRC in response to detecting an abnormality associated with the autonomous vehicle. A strategy information acquisition module, configured to acquire strategy information corresponding to the target mode of the MRM, the strategy information at least indicating the maximum degree of impact allowed by the target mode on the traffic environment. A parking control module, configured to control the parking process of the autonomous vehicle based on the current traffic environment of the autonomous vehicle and the strategy information.

[0006] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the device executes the method of the first aspect or the second aspect.

[0007] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect or the second aspect.

[0008] In a fifth aspect of the present disclosure, a computer program product is provided, which includes computer executable instructions, and when the computer executable instructions are executed by a processor, the method of the first aspect or the second aspect is implemented.

[0009] It should be understood that the contents described in the summary of the present invention are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0011] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0012] Figure 2 A flow chart showing a method for an autonomous vehicle according to some embodiments of the present disclosure is shown;

[0013] Figure 3 A schematic diagram showing a comparison of the characteristics of four MRM modes according to some embodiments of the present disclosure;

[0014] Figure 4 A schematic diagram showing a comparison of parking ranges of four MRM modes according to some embodiments of the present disclosure is shown;

[0015] Figure 5 A schematic diagram of a dedicated right-turn lane according to some embodiments of the present disclosure is shown;

[0016] Figure 6 A schematic structural block diagram showing an apparatus for an autonomous vehicle according to certain embodiments of the present disclosure; and

[0017] Figure 7 A block diagram of a device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0019] It should be noted that the titles of any sections / subsections provided herein are not restrictive. Various embodiments are described throughout this article, and any type of embodiment may be included under any section / subsection. In addition, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0020] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0021] The embodiments of the present disclosure may involve user data, data acquisition and / or use, etc. These aspects are subject to the corresponding laws, regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user knows and confirms. Accordingly, when implementing each embodiment of the present disclosure, the type, scope of use, usage scenario, etc. of the data or information that may be involved should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with the relevant laws and regulations. The specific notification and / or authorization method can vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this respect.

[0022] In this specification and the embodiments, if personal information processing is involved, it will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or it is necessary to perform a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0023] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. In this article, "model" may also be referred to as "machine learning model", "machine learning network" or "network", and these terms are used interchangeably in this article.

[0024] With the continuous development of autonomous driving technology, the safety of vehicles without human intervention has become a focus of attention. In particular, when an abnormality occurs in the vehicle (such as system failure of the vehicle computer, sensor failure or insufficient energy), it is crucial to quickly and effectively control the vehicle to enter a safe state. In some related technologies, the problem is usually solved through a simple emergency stop mechanism, but this may lead to hidden dangers such as traffic congestion and secondary accidents.

[0025] Embodiments of the present disclosure provide a method for an autonomous vehicle, which may include determining a target mode of a minimum risk maneuver (MRM) for entering a minimum risk condition (MRC) in response to detecting an anomaly associated with the autonomous vehicle. Obtaining strategy information corresponding to the target mode of the MRM, the strategy information at least indicating the maximum degree of impact on the traffic environment allowed by the target mode. Based on the current traffic environment of the autonomous vehicle and the strategy information, controlling a parking process of the autonomous vehicle.

[0026] The embodiments of the present disclosure can dynamically determine the target mode of the minimum risk operation MRM when the autonomous vehicle detects an abnormality, obtain the corresponding strategy information, and control the parking process in combination with the current traffic environment, thereby achieving the technical effect of differentiated processing according to the abnormality type and traffic conditions. This method effectively reduces the impact of parking on traffic, while ensuring that the vehicle can quickly and safely enter the minimum risk condition MRC under abnormal conditions, thereby improving the real-time and flexibility of the autonomous vehicle's abnormal handling.

[0027] Example Environment

[0028] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. An autonomous vehicle 101 may be included in the environment 100. In some embodiments, the autonomous vehicle 101 may be any type of vehicle that can carry people and / or objects and move through a power system such as an engine, including but not limited to a car, a truck, a bus, an electric car, a motorhome, etc. The autonomous vehicle 101 may be an autonomous driving vehicle (also referred to as an autonomous vehicle) that integrates functions such as environmental perception, planning and decision-making, and multi-level assisted driving.

[0029] like Figure 1 As shown, the electronic device 150 may be any device with computing capabilities, and the electronic device 150 may control the parking process of the autonomous vehicle.

[0030] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and does not imply any limitation on the scope of the present disclosure.

[0031] Controlling the parking process of an autonomous vehicle

[0032] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings. Figure 2 A flow chart of a method 200 for an autonomous vehicle is shown, according to some embodiments of the present disclosure.

[0033] like Figure 2 As shown, at block 201 , electronic device 150 determines a target mode of minimum risk operation MRM to enter a minimum risk condition MRC in response to detecting an anomaly associated with autonomous vehicle 101 .

[0034] Autonomous vehicle 101 may include a vehicle that can autonomously perceive the environment, plan a path, and perform driving operations through sensors, control systems, and algorithms without relying on manual driving. Autonomous vehicle 101 may trigger abnormalities due to various reasons during operation, such as hardware failure (such as sensor failure), software failure (such as algorithm error), and external environmental changes (such as extreme weather or road obstacles). These abnormalities may pose potential risks to the driving safety of the vehicle and the surrounding traffic environment.

[0035] Different types of anomalies have different degrees of impact on the vehicle's remaining driving ability. For example, some anomalies allow the vehicle to move slowly, while some severe anomalies may completely lose the ability to drive. To cope with these different scenarios, the autonomous vehicle needs to determine the appropriate minimum risk operation (MRM) target mode to enter the minimum risk condition (MRC). The MRM target mode can be divided into four modes according to the degree of impact on the traffic environment.

[0036] Figure 3 A schematic diagram of comparing characteristics 300 of four MRM modes according to some embodiments of the present disclosure is shown. As an example, the four modes may include: a first MRM mode to a fourth MRM mode. The four modes are introduced below respectively.

[0037] The first MRM mode indicates that the autonomous vehicle 101 should stop in the harbor area (ZONE_HARBOR) first, such as the service area of ​​a highway or a dedicated parking space in a city. The first MRM mode has the lowest degree of traffic congestion and is usually only applicable to situations where the vehicle has a high residual system capacity, such as a minor sensor failure or a minor algorithm abnormality, etc. The autonomous vehicle 101 can be parked for a long time in this mode for inspection or to resume normal operation. Due to the limited number and uneven distribution of harbor areas, this mode has high requirements on the path planning and navigation capabilities of the autonomous vehicle 101, and is the highest priority minimum risk operation mode.

[0038] The second MRM mode indicates pulling over, and the maximum impact level is the second level, which is higher than the first level. The second MRM mode instructs the autonomous vehicle 101 to pull over in the pullover area (ZONE_PULLRIGHT), such as the emergency lane or hard shoulder on the right side of the road. Compared with the first MRM mode, the second MRM mode has a slightly higher degree of traffic congestion, but it is still within an acceptable range. As an example, the second MRM mode can be applicable to autonomous vehicles 101 that have moderate abnormalities (such as decreased power system performance), but still have basic steering and movement capabilities. This mode has fewer restrictions on parking areas and a shorter parking time. The autonomous vehicle 101 needs to quickly enter the pullover area to reduce interference with traffic flow.

[0039] The third MRM mode indicates stopping in the current lane, and the maximum impact degree is the third degree, which is higher than the second degree. The third MRM mode instructs the autonomous vehicle 101 to slowly decelerate and stop in the current lane (ZONE_INLANE). As an example, the third MRM mode is applicable to situations where the autonomous vehicle 101 cannot turn but can still control deceleration, such as when the brake system fails and partially loses. Since the autonomous vehicle 101 is parked in the current lane, this mode has a greater impact on traffic congestion and only allows short-term parking to wait for further rescue or instructions. The third MRM mode has lower requirements on the system residual capacity of the autonomous vehicle 101, but requires real-time detection of the traffic environment to avoid secondary risks.

[0040] The fourth MRM mode indicates an emergency stop with a maximum impact level of the fourth level, which is higher than the third level. The fourth MRM mode instructs the autonomous vehicle 101 to stop immediately in any permitted zone (ZONE_URGENCY) with maximum braking capability. As an example, the fourth MRM mode is suitable for highly urgent abnormal situations, such as brake failure or complete loss of control of the vehicle. Since the goal of emergency stopping is to quickly eliminate potential risks, the degree of traffic obstruction is the highest and there are almost no restrictions on parking areas. In this mode, the autonomous vehicle 101 has the lowest requirement for the remaining capacity of the system and only needs to be able to trigger the brakes and stop moving. It is the lowest priority but highest safety measure.

[0041] Figure 4 A comparison diagram of parking ranges 400 of four MRM modes according to some embodiments of the present disclosure is shown. In combination with the above content, starting from the first parking area corresponding to the first MRM mode, the parking area range gradually expands (the fourth parking area range corresponding to the fourth MRM mode is relatively the largest), and the restrictions gradually decrease, reflecting different adaptations to the severity of abnormalities.

[0042] For the first MRM mode, the parking area can be represented as ZONE_HARBOR, and vehicles are only allowed to park in a specific harbor area or in a harbor area or a shoulder area that meets the following conditions: the area is between the road boundary line and the curb with a certain height (the vehicle cannot pass through), the shoulder width is wide enough to accommodate a vehicle body, and the area is not prohibited from parking (for example, there is no no parking sign).

[0043] For the second MRM mode, the parking area can be represented as ZONE_PULLRIGHT, and the range is expanded relative to ZONE_HARBOR, allowing the vehicle to park on the right in the emergency lane or diversion area. As an example, the area where parking is allowed may include the emergency lane on the right side of the road and the diversion area (such as the diversion area at the exit of a highway). ZONE_INLANE can define a no-parking area (such as a main lane). If the emergency lane is occupied, the electronic device 150 can temporarily select the secondary right lane as the parking target point.

[0044] For the third MRM mode, the parking area can be represented as ZONE_INLANE, and the parking range is further expanded to allow vehicles to slow down in the current lane. As an example, ZONE_INLANE can include any position in the current lane except the no-parking zone. The no-parking zone can include at least one of the following: the intersection, the yellow grid line area, the rightmost motor vehicle lane before the entrance and exit, the intersection and the 30-meter (adjustable value) range before and after the intersection, and the single right-turn lane and its 10-meter (adjustable value) range in and out.

[0045] For the fourth MRM mode, the parking area can be represented as ZONE_URGENCY, which has the widest range and almost no restrictions on the parking position. As an example, ZONE_URGENCY can include feasible areas including intersections, yellow grid line areas, main lanes, etc. In some emergency scenarios (such as collision detection), the parking process may require additional constraints, such as the deceleration must not exceed a certain value, but the parking position range is still not affected.

[0046] In block 202 , the electronic device 150 obtains policy information corresponding to a target mode of the MRM, where the policy information at least indicates a maximum degree of impact on the traffic environment allowed by the target mode.

[0047] The strategy information at least includes the maximum degree of impact on the traffic environment allowed by the target mode, that is, it clearly defines the interference tolerance of the autonomous vehicle to the surrounding traffic flow in this mode. The strategy information corresponding to different MRM target modes has different focuses. For example, corresponding to the first MRM mode, the strategy information may indicate that the autonomous vehicle 101 is only allowed to dock in the designated harbor area, and the maximum degree of impact is close to zero. Corresponding to the fourth MRM mode, the strategy information may allow the autonomous vehicle 101 to stop at the highest deceleration in any feasible area, and the maximum degree of impact is higher. By obtaining strategy information that matches the target mode, the system can formulate a safer and more efficient exception handling path for the autonomous vehicle while reducing the adverse impact on the traffic environment.

[0048] In block 203 , the electronic device 150 controls the parking process of the autonomous vehicle 101 based on the current traffic environment and strategy information of the autonomous vehicle 101 .

[0049] The electronic device 150 can control the parking process of the autonomous vehicle 101 based on the environmental perception data and the constraints of the target mode. The current traffic environment can include the type of lane where the autonomous vehicle 101 is located (such as a main lane, a dedicated lane, or an emergency lane), the flow and speed of surrounding vehicles, road signs (such as a no parking sign), and the availability of shoulders or side areas. In combination with the acquired strategy information (such as the constraints of the parking position, the tolerance for traffic impact, and the parking time limit), the electronic device 150 can dynamically adjust the parking path and the target position. As an example, for the first MRM mode, the electronic device 150 can preferentially search for the nearest harbor area to park. For the second MRM mode, the electronic device 150 can choose the right emergency lane or hard shoulder for parking. For the third MRM mode, the electronic device 150 can slow down in the current lane while minimizing the traffic impact. For the third MRM mode, the electronic device 150 will stop directly in any allowed area with the maximum deceleration in the shortest time. By combining the traffic environment and strategy information in real time, the autonomous vehicle 101 can ensure that it quickly enters the minimum risk condition MRC in abnormal situations while minimizing the interference with traffic flow. During the parking process, the electronic device 150 controls the autonomous vehicle 101 to turn on the corresponding turn signal. Except during the lane changing / parking process, the double flashers must be turned on at other times (including after parking).

[0050] Through the above process, the electronic device 150 can dynamically determine the target mode of the minimum risk operation MRM, obtain the strategy information corresponding to the target mode, and control the parking process in combination with the current traffic environment, thereby achieving flexibility and efficiency in handling abnormalities of autonomous vehicles. According to different abnormality types and the remaining driving capabilities of the vehicle, the appropriate MRM mode is selected, and the parking path can be dynamically optimized and the target position can be adjusted in real time in combination with the parking area, time limit and traffic impact constraints in the strategy information, so that the vehicle can quickly and safely enter the minimum risk condition MRC. This method effectively reduces the adverse effects on the traffic environment, and at the same time, through a hierarchical design, it meets the needs of multiple scenarios from minor abnormalities to emergency failures, significantly improving the safety and intelligence of autonomous vehicles.

[0051] In the previous example, the policy information indicates the maximum impact of the target mode on the traffic environment. In addition, the policy information may also indicate the maximum parking time of the autonomous vehicle 101. In this case, the electronic device 150 adjusts the target mode of the MRM in response to the autonomous vehicle not completing parking within the maximum parking time.

[0052] When the autonomous vehicle 101 fails to complete parking within the maximum parking time, the electronic device 150 can automatically adjust the MRM target mode according to the strategy information to ensure that the vehicle can enter the minimum risk condition (MRC) as soon as possible.

[0053] For example, when the autonomous vehicle 101 fails to complete parking after a specific mileage (e.g., tentatively set as 2 kilometers) or a specific time (e.g., tentatively set as 4 minutes) in the first MRM mode, the electronic device 150 will adjust the target mode to the second MRM mode, instructing the autonomous vehicle 101 to park in the pull-over area. For another example, if the autonomous vehicle 101 fails to complete parking within a specific time (e.g., tentatively set as 2 minutes) in the second MRM mode, a remote operation (RA) is triggered, and the remote control system determines whether it is necessary to continue trying the second MRM mode or adjust to the third or fourth MRM mode. If the autonomous vehicle 101 meets the adjustment conditions, it is instructed to enter a slow stop or emergency stop state in the current lane. In this process, while requesting a remote response or waiting for a decision, the autonomous vehicle 101 continues the parking operation of the current target mode. This mechanism provides a flexible adjustment strategy by dynamically adjusting the target mode, ensuring that the autonomous vehicle 101 can always complete parking in a safe and efficient manner under abnormal circumstances.

[0054] In some embodiments, the policy information may also indicate a system capability constraint corresponding to the target mode. In this case, the electronic device 150 adjusts the target mode of the MRM in response to detecting that the system capability of the autonomous vehicle 101 does not satisfy the system capability constraint.

[0055] The policy information may indicate the system capability constraints corresponding to the target mode, such as the minimum braking capability, steering capability, or positioning navigation accuracy required for the autonomous vehicle 101 to execute the current target mode. When the electronic device 150 detects that the actual system capability of the autonomous vehicle 101 is lower than the system capability constraint, the target mode of the current minimum risk operation (MRM) will be adjusted. For example, when the autonomous vehicle 101 is in the first MRM mode, but the system capability is not sufficient to accurately navigate to the harbor area, the electronic device 150 can dynamically downgrade the target mode to the second MRM mode, allowing the autonomous vehicle 101 to complete parking in the side area. Similarly, if the autonomous vehicle 101 cannot complete parking within a predetermined distance due to partial failure of the braking system in the second MRM mode, the target mode can be adjusted to the third or fourth MRM mode, so that the autonomous vehicle 101 can slow down or emergency stop in the current lane. Through this adjustment mechanism of system capability constraints, the electronic device 150 can adapt to changes in the hardware performance or sudden abnormalities of the autonomous vehicle 101, ensuring that the minimum risk condition (MRC) can still be safely entered when the autonomous vehicle 101 has limited capabilities.

[0056] In some embodiments, the electronic device 150 determines a parking position constraint corresponding to a target mode of the MRM based on the strategy information. The parking position constraint determines a target parking point, wherein the impact of parking at the target parking point on the current traffic environment is less than the maximum impact, and triggers the autonomous vehicle to park at the target parking point.

[0057] For the first MRM mode, the electronic device 150 controls the autonomous vehicle 101 to find a defined bay area for parking and shifts to P gear. The bay area usually has the least impact on the traffic environment, so the autonomous vehicle 101 needs to have a high navigation accuracy to accurately drive into the target parking spot. When the autonomous vehicle 101 completes parking in the bay area within a specific mileage (such as 2 kilometers) or duration (such as 4 minutes), and the body posture meets the parking conditions, it is considered to be parked successfully.

[0058] For the second MRM mode, the electronic device 150 controls the autonomous vehicle 101 to select the right hard shoulder or emergency lane for parking according to the parking position constraint, and puts the autonomous vehicle 101 in P gear. If the right lane is full and cannot be parked, the electronic device 150 will dynamically adjust the parking position, for example, selecting the secondary right lane as a temporary target point. If the right lane becomes available before the autonomous vehicle 101 stops, the electronic device 150 can update the parking position constraint in real time and control the autonomous vehicle 101 to park back in the right lane. When the center point of the vehicle is within the allowed parking position and the angle between the vehicle body and the lane line is less than a preset value (such as 30°), it is considered to be parked successfully.

[0059] For the third MRM mode, the electronic device 150 detects whether the vehicle can be parked in the current lane at a speed not exceeding a preset deceleration (eg, -3 m / s) based on the parking position constraint. 2 ) to complete parking within a specified distance (e.g., 25 meters). If it cannot be completed, the electronic device 150 plans to drive to the next parking area and complete parking within a preset distance after entering the area. If an unexpected environmental factor (e.g., a pedestrian suddenly appears) requires a greater deceleration (e.g., -6 m / s 2 ), the electronic device 150 will adjust the parking position constraints and complete parking in time. In order to handle extreme situations, for the third MRM mode, if the speed of the autonomous vehicle 101 does not drop to 0 within 20 seconds and is not taken over by the safety mode (Fallback), it will be recorded as a failure of the third MRM mode. In such a case, if the current area is not a prohibited parking area, the electronic device 150 will immediately trigger the fourth MRM mode and use a preset deceleration (such as -3m / s 2 ) decelerates to a parking state. If the current area is a no-parking area, the autonomous vehicle 101 must first leave the no-parking area and then trigger the fourth MRM mode to complete the parking operation. Direct adjustment to the fourth MRM mode is not allowed in the no-parking area. In addition, the electronic device 150 also limits the speed behavior of the autonomous vehicle 101 in the third MRM mode. For example, when the autonomous vehicle 101 decelerates to below a predetermined speed (e.g., 30 kph), it is not allowed to accelerate again to above the predetermined speed unless the third MRM mode is explicitly released. This mechanism ensures that in complex traffic scenarios, the third MRM mode can dynamically adapt to the current environment to achieve fast and safe parking operations.

[0060] When the third MRM mode is triggered during the lane change process, the current lane and the target lane have equal priority, and the electronic device 150 can control the autonomous vehicle 101 to select a more suitable lane to complete parking according to the actual road conditions. When the autonomous vehicle 101 stops steadily in the parking area and is in P gear, it is considered to be parked successfully.

[0061] For the fourth MRM mode, the electronic device 150 controls the autonomous vehicle 101 to park along the planned trajectory at the maximum allowable deceleration (such as the maximum braking capacity of the system) and put it in P gear. In specific scenarios (such as collision detection requires a lower deceleration response), the electronic device 150 can adjust the parking form, for example, parking within 10 meters but the deceleration must not exceed -6m / s2. If the fourth MRM mode is triggered when reversing, the electronic device 150 can apply deceleration in the reversing direction until the car stops. Whether moving forward or reversing, as long as the vehicle stops steadily and is in P gear, it is considered successful. For extreme scenario safety, if the autonomous vehicle 101 fails to complete parking within 10 seconds after triggering the fourth MRM mode and is always in the fourth MRM mode (not taken over by the safety mode (Fallback)), it is recorded as a failure. At this time, the electronic device 150 can immediately trigger the safety mode takeover, forcibly decelerate the autonomous vehicle 101 to a stationary state, and ensure safe entry into the minimum risk condition. The safety mode takeover may include directly triggering the emergency brake or adjusting the parking path to adapt to sudden environmental risks. This mechanism not only ensures the parking efficiency of the fourth MRM mode under normal circumstances, but also effectively responds to extreme scenarios, improving safety and robustness.

[0062] For the four MRM modes, the first MRM mode corresponds to a first maximum parking time, the second MRM mode corresponds to a second maximum parking time, the third MRM mode corresponds to a third maximum parking time, and the fourth MRM mode corresponds to a fourth maximum parking time. The first maximum parking time is greater than the second maximum parking time, the second maximum parking time is greater than the third maximum parking time, and the third maximum parking time is greater than the fourth maximum parking time.

[0063] The first MRM mode corresponds to the first maximum parking time, which is the longest, allowing the autonomous vehicle 101 to park for a long time in the ZONE_HARBOR area. Since the harbor area is usually designed as a dedicated parking place with minimal impact on the traffic environment, the parking time can be relatively loose, such as for vehicle troubleshooting or waiting for rescue. The setting of the first maximum parking time reflects the optimal balance between safety and traffic flow in this mode.

[0064] The second MRM mode corresponds to the second maximum parking time, which is relatively short and allows the vehicle to be parked for a medium time in ZONE_PULLRIGHT (such as an emergency lane or hard shoulder). Since pull-over parking may have a certain impact on traffic flow, it is necessary to impose moderate restrictions on parking time. For example, when rescue or remote control does not intervene in time, the parking time can be set to 4 minutes according to the actual test situation. Exceeding this time will trigger the target mode to be downgraded or adjusted.

[0065] The third MRM mode corresponds to the third maximum parking time, which is further shortened and is suitable for the scenario where the vehicle is parking slowly in the current lane. Since parking in the lane has a greater impact on traffic congestion, the parking time needs to be strictly limited. For example, it can be set to 2 minutes to ensure that the vehicle can complete the abnormal handling as soon as possible and reduce interference with subsequent vehicles.

[0066] The fourth MRM mode corresponds to the fourth maximum parking time, which is the shortest and is suitable for highly urgent abnormal situations. When the vehicle is parked in ZONE_URGENCY (such as any allowed area), the parking operation must be completed as soon as possible and enter the minimum risk condition (MRC). The parking time is limited to a very short period of time, such as within 10 seconds, to minimize the continuous impact on the traffic environment.

[0067] The autonomous vehicle 101 may be a private car or an operating vehicle. If it is an operating vehicle and the autonomous vehicle 101 is in the process of delivering the driver to the destination, the method further includes: in response to the target mode being the first MRM mode or the second MRM mode, determining whether the parking position corresponding to the target mode is far from the destination. In response to the parking position being far from the destination, the autonomous vehicle 101 is controlled to start the parking process corresponding to the target mode after completing the delivery process.

[0068] When the autonomous vehicle 101 is an operating vehicle and is in the process of delivering a passenger, the electronic device 150 determines whether the parking position is far from the order destination according to the parking position constraint corresponding to the target mode. If the parking position is far from the destination, the autonomous vehicle 101 should complete the delivery process first and start the parking operation corresponding to the target mode after the passenger gets off the vehicle.

[0069] For example, in the first MRM mode, the parking position in the harbor area may be located on the road section after the order end point. At this time, the autonomous vehicle 101 can continue to move forward to the order end point, and after the passenger gets off, re-plan the parking path according to the requirements of the first MRM mode and park in the harbor area. Similarly, in the second MRM mode, the parking position in the right lane may also be located after the order end point. At this time, the autonomous vehicle 101 will first complete the task of delivering the passenger, and then return to the area that meets the parking position constraints of the second MRM mode to complete the pull-over parking operation.

[0070] In addition, to avoid interference in the state timing of the sending process, the passenger getting off the bus does not count the parking timing of the first MRM mode or the second MRM mode. This processing method ensures that while meeting the needs of passengers, the electronic device 150 can perform subsequent operations according to the parking requirements of the target mode.

[0071] In some embodiments, the current traffic environment indicates whether the current lane of the autonomous vehicle is a dedicated driving lane, the dedicated driving lane including a dedicated right turn lane.

[0072] Figure 5 A schematic diagram of a right-turn lane 500 according to some embodiments of the present disclosure is shown. The current traffic environment may include identification information of a dedicated driving lane to indicate whether the lane currently in which the autonomous vehicle 101 is located belongs to a dedicated driving lane. Dedicated driving lanes generally include right-turn dedicated lanes, the rightmost motor vehicle lane before the entrance and exit, and other lane types with specific restrictions. When controlling the parking of the autonomous vehicle 101, the electronic device 150 needs to dynamically adjust the target parking position and path planning according to the special requirements of the dedicated driving lane. For a separate right-turn dedicated lane (with hard isolation areas on both sides of the lane) and its specified distance range 501 (e.g., 10 meters) of the entrance and exit, it is defined as a no-parking area of ​​ZONE_URGENCY because its design purpose is to ensure the smooth flow of right-turn traffic. If the autonomous vehicle triggers the MRM mode in this area, it should give priority to leaving the right-turn dedicated lane before selecting a suitable parking spot.

[0073] The rightmost motor vehicle lane in front of the main entrance and exit may cause great interference to the traffic flow entering and leaving, and is therefore usually regarded as a no-parking zone where parking is not allowed. When executing the MRM mode, the autonomous vehicle 101 should avoid this zone and preferentially choose a location farther from the entrance and exit to complete the parking operation.

[0074] By combining the restrictions of these dedicated driving lanes, the autonomous vehicle 101 can dynamically adjust the parking path to ensure that the parking behavior complies with the policy information constraints of the target mode while avoiding unnecessary interference with the current traffic environment.

[0075] In some embodiments, the parking process based on the target mode of minimum risk operation MRM and the requirements for parking area selection and traffic congestion are significantly different from those for passenger pick-up and drop-off parking. Passenger pick-up and drop-off parking is temporary parking, and the parking duration can usually be well estimated. The degree of traffic congestion is relatively light and controllable, so the range of parking location selection is relatively large, such as bus stations, entrance and exit areas, etc. can all be used as pick-up and drop-off points. The parking process based on the target mode of minimum risk operation MRM belongs to parking after the vehicle has an abnormality. Since it is difficult to predict whether the abnormality will be restored and when the rescue will arrive, in order to ensure safety as much as possible and reduce the degree of traffic congestion, the parking process based on the target mode of minimum risk operation MRM is more stringent in area selection. For example, the rightmost lane adjacent to the entrance and exit, bus stations and other areas are prohibited parking areas. This design ensures that while meeting the needs of operating vehicle pick-up and drop-off, it provides a safer and more standardized parking solution under abnormal circumstances through different adaptations to the two parking scenarios.

[0076] Example devices and equipment

[0077] Figure 61 shows a schematic structural block diagram of an apparatus 600 for an autonomous vehicle according to some embodiments of the present disclosure. The apparatus 600 may be implemented as or included in a remote device 120. Each module / component in the apparatus 600 may be implemented by hardware, software, firmware, or any combination thereof.

[0078] As shown in the figure, the device 600 includes a target mode determination module 601, which is configured to determine a target mode of a minimum risk operation MRM for entering a minimum risk condition MRC in response to detecting an abnormality associated with the autonomous vehicle. A strategy information acquisition module 602 is configured to acquire strategy information corresponding to the target mode of the MRM, and the strategy information at least indicates the maximum degree of impact allowed by the target mode on the traffic environment. A parking control module 603 is configured to control the parking process of the autonomous vehicle based on the current traffic environment of the autonomous vehicle and the strategy information.

[0079] In some embodiments, the strategy information further indicates a maximum parking time of the ego vehicle, and the apparatus 600 further includes a target mode adjustment module. The target mode adjustment module may be configured to adjust the target mode of the MRM in response to the ego vehicle failing to park within the maximum parking time.

[0080] In some embodiments, the policy information further indicates a system capability constraint corresponding to the target mode, and the target mode adjustment module may be configured to adjust the target mode of the MRM in response to detecting that the system capability of the autonomous vehicle does not satisfy the system capability constraint.

[0081] In some embodiments, the parking control module 603 may be specifically configured to: determine, based on the strategy information, a parking position constraint corresponding to the target mode of the MRM; determine a target parking point based on the parking position constraint, wherein the impact of parking at the target parking point on the current traffic environment is less than the maximum impact; and trigger the autonomous vehicle to park at the target parking point.

[0082] In some embodiments, the target mode determined by the target mode determination module 601 is determined from the following preset modes: a first MRM mode, indicating docking in the port area, with a maximum impact degree of a first degree; a second MRM mode, indicating docking by the side of the road, with a maximum impact degree of a second degree, which is higher than the first degree; a third MRM mode, indicating docking in the current lane, with a maximum impact degree of a third degree, which is higher than the second degree; a fourth MRM mode, indicating an emergency stop, with a maximum impact degree of a fourth degree, which is higher than the third degree.

[0083] In some embodiments, the first MRM mode corresponds to a first maximum parking time, the second MRM mode corresponds to a second maximum parking time, the third MRM mode corresponds to a third maximum parking time, the fourth MRM mode corresponds to a fourth maximum parking time, and the first maximum parking time is greater than the second maximum parking time, the second maximum parking time is greater than the third maximum parking time, and the third maximum parking time is greater than the fourth maximum parking time.

[0084] In some embodiments, when the autonomous vehicle is in the process of delivering the driver to the destination, the parking control module 603 may be further configured to: in response to the target mode being the first MRM mode or the second MRM mode, determine whether the parking position corresponding to the target mode is far from the destination. In response to the parking position being far from the destination, control the autonomous vehicle to start the parking process corresponding to the target mode after completing the delivery process.

[0085] In some embodiments, the current traffic environment indicates whether the current lane of the autonomous vehicle is a dedicated driving lane, the dedicated driving lane including a dedicated right turn lane.

[0086] Figure 7 A block diagram illustrating a computing device 700 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that Figure 7 The computing device 700 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 7 The computing device 700 shown may be used to implement Figure 1 remote device 120 or electronic device 150.

[0087] like Figure 7 As shown, computing device 700 is in the form of a general-purpose computing device. Components of computing device 700 may include, but are not limited to, one or more processors or processing units 710, memory 720, storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. Processing unit 710 may be an actual or virtual processor and is capable of performing various processes according to a program stored in memory 720. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capabilities of computing device 700.

[0088] The computing device 700 typically includes a plurality of computer storage media. Such media may be any accessible media accessible to the computing device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 720 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 730 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data (e.g., training data for training) and may be accessed within the computing device 700.

[0089] The computing device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 7 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 720 may include a computer program product 725 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0090] The communication unit 740 enables communication with other computing devices via a communication medium. Additionally, the functions of the components of the computing device 700 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Therefore, the computing device 700 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0091] Input device 750 may be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 760 may be one or more output devices, such as a display, speaker, printer, etc. Computing device 700 may also communicate with one or more external devices (not shown) through communication unit 740 as needed, such as storage devices, display devices, etc., communicate with one or more devices that allow a user to interact with computing device 700, or communicate with any device that allows computing device 700 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0092] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0093] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0094] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0095] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0096] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0097] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for an autonomous vehicle, comprising: In response to detecting an anomaly associated with the autonomous vehicle, determining a target mode of minimum risk maneuver (MRM) to enter a minimum risk condition (MRC); Acquire strategy information corresponding to the target mode of the MRM, the strategy information at least indicating the maximum degree of impact allowed by the target mode on the traffic environment; as well as Based on the current traffic environment of the autonomous vehicle and the strategy information, a parking process of the autonomous vehicle is controlled.

2. The method according to claim 1, wherein the strategy information further indicates a maximum parking time of the ego vehicle, the method further comprising: In response to the autonomous vehicle failing to complete parking within the maximum parking time, adjusting the target mode of the MRM.

3. The method according to claim 1, wherein the policy information further indicates a system capability constraint corresponding to the target mode, the method further comprising: In response to detecting that a system capability of the autonomous vehicle does not satisfy the system capability constraint, adjusting the target mode of the MRM.

4. The method of claim 1, wherein based on the current traffic environment of the autonomous vehicle and the strategy information, controlling the parking process of the autonomous vehicle comprises: determining, based on the strategy information, a parking position constraint corresponding to the target mode of the MRM; The parking position constraint determines a target parking point, wherein the degree of impact of parking at the target parking point on the current traffic environment is less than the maximum degree of impact; as well as The autonomous vehicle is triggered to park at the target parking point.

5. The method of claim 1, wherein the target mode is determined from the following preset modes: The first MRM mode indicates that the port is docked in the harbor area, and the maximum impact degree is the first degree; A second MRM mode indicates that the vehicle is parked at the side of the road, and the maximum impact level is a second level, and the second level is higher than the first level; A third MRM mode indicates stopping in the current lane, the maximum impact degree is a third degree, and the third degree is higher than the second degree; The fourth MRM mode indicates an emergency stop, the maximum impact level is a fourth level, and the fourth level is higher than the third level.

6. The method of claim 5, wherein the first MRM mode corresponds to a first maximum parking duration, the second MRM mode corresponds to a second maximum parking duration, the third MRM mode corresponds to a third maximum parking duration, the fourth MRM mode corresponds to a fourth maximum parking duration, and The first maximum parking time is greater than the second maximum parking time, the second maximum parking time is greater than the third maximum parking time, and the third maximum parking time is greater than the fourth maximum parking time.

7. The method according to claim 5, wherein the autonomous vehicle is in the process of delivering a vehicle to a destination, the method further comprising: In response to the target mode being the first MRM mode or the second MRM mode, determining whether a parking position corresponding to the target mode is farther than the destination; as well as In response to the parking position being farther than the destination, the autonomous vehicle is controlled to start a parking process corresponding to the target mode after completing the delivery process. 8 . The method of claim 1 , wherein the current traffic environment indicates whether a current lane of the autonomous vehicle is a dedicated driving lane, the dedicated driving lane comprising a right-turn dedicated lane.

9. An apparatus for an autonomous vehicle, comprising: a target mode determination module configured to determine a target mode of minimum risk maneuver MRM for entering a minimum risk condition MRC in response to detecting an anomaly associated with the autonomous vehicle; a strategy information acquisition module, configured to acquire strategy information corresponding to the target mode of the MRM, wherein the strategy information at least indicates a maximum degree of impact allowed by the target mode on the traffic environment; as well as The parking control module is configured to control a parking process of the autonomous vehicle based on a current traffic environment of the autonomous vehicle and the strategy information.

10. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 8 when executed by the at least one processing unit.

11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 8.

12. A computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 8.

Images