Methods, apparatus, devices, and computer storage media for autonomous vehicles

Abstract

This provides a method for improved autonomous vehicles. [Solution] Embodiments of the present disclosure provide a method, apparatus, device, and storage medium for an autonomous vehicle. The method includes: determining a target mode for a minimum risk operation MRM to enter a minimum risk condition MRC in response to the detection of an anomaly associated with the autonomous vehicle; obtaining policy information corresponding to the target mode of the MRM, the policy information indicating at least the maximum degree of impact on the traffic environment that the target mode allows; and controlling the parking process of the autonomous vehicle based on the current traffic environment and the policy information. Embodiments of the present disclosure can ensure that the vehicle enters a minimum risk condition MRC quickly and safely in an anomaly condition while reducing the degree of impact the parking has on traffic.

Description

Technical Field

[0001] Exemplary embodiments of the present disclosure generally relate to the field of computers, and particularly to methods, devices, equipment, and computer-readable storage media for autonomous vehicles.

Background Art

[0002] Autonomous driving is a technology that plans the movement trajectory of a vehicle by using a computer to sense the surrounding environment of the vehicle or assist a human driver instead of the human driver, and controls the vehicle to reach a specified destination.

[0003] Several failures may occur during the driving of an autonomous vehicle. In this case, how to control the safe parking of the autonomous vehicle is an important part of enhancing driving safety and reliability.

Summary of the Invention

[0004] According to a first aspect of the present disclosure, a method for an autonomous vehicle is provided. The method includes determining a target mode of a minimum risk operation (MRM) that enters a minimum risk condition (MRC) in response to detecting an abnormality associated with the autonomous vehicle; obtaining policy information corresponding to the target mode of the MRM, where the policy information at least indicates the maximum degree of influence on a traffic environment allowed by the target mode; and controlling a parking process of the autonomous vehicle based on the current traffic environment of the autonomous vehicle and the policy information.

[0005] A second aspect of this disclosure provides a device for an autonomous vehicle. The device comprises: a target mode determination module configured to determine a target mode for a minimum risk operation MRM that enters a minimum risk condition MRC in response to the detection of an anomaly associated with the autonomous vehicle; a policy information acquisition module configured to acquire policy information corresponding to the target mode of the MRM, the policy information being configured to indicate at least the maximum degree of impact on the traffic environment that the target mode is permitted to; and 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 policy information.

[0006] A third aspect of this disclosure provides an electronic device comprising at least one processing unit and at least one memory, the memory of which is coupled to at least one processing unit and stores instructions to be executed by at least one processing unit. When the instructions are executed by at least one processing unit, they cause the device to perform the method of the first or second aspect.

[0007] A fourth aspect of this disclosure provides a computer-readable storage medium, which stores a computer program, which is executed by a processor to implement the method of the first or second aspect.

[0008] According to a fifth aspect of this disclosure, a computer program product is provided. This computer program product includes computer executable instructions, which, when executed by a processor, implement the method of the first aspect of this disclosure.

[0009] It should be understood that the content described in this section is not intended to limit any or any significant features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will be readily apparent from the following description. [Brief explanation of the drawing]

[0010] The above and other features, advantages, and aspects of each embodiment of the present disclosure will become more apparent with reference to the drawings and the detailed description below. In the drawings, the same or similar reference numerals represent the same or similar elements. [Figure 1] A schematic diagram of an exemplary environment in which embodiments of this disclosure can be realized is shown. [Figure 2] A flowchart of a method for an autonomous vehicle according to some embodiments of this disclosure is shown. [Figure 3] A schematic diagram comparing the characteristics of four MRM modes according to several embodiments of this disclosure is shown. [Figure 4] A schematic diagram comparing the parking ranges of four MRM modes according to several embodiments of this disclosure is shown. [Figure 5] This is a schematic diagram of a right-turn-only lane according to some embodiments of the present disclosure. [Figure 6] This is a schematic block diagram of a device for an autonomous vehicle according to one embodiment of the present disclosure. [Figure 7] Block diagrams of devices according to multiple embodiments that can realize this disclosure are shown. [Modes for carrying out the invention]

[0011] Embodiments of this disclosure will be described in more detail below with reference to the drawings. While the drawings illustrate several embodiments of this disclosure, it should be understood that this disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Conversely, providing these embodiments should lead to a more detailed and complete understanding of this disclosure. It should be understood that the drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0012] The titles of any sections / subsections provided herein are not limiting. This specification provides a general overview of various embodiments, and any type of embodiment may be included in any section / subsection. Furthermore, any embodiment described in any section / subsection may be combined with any other embodiment described in the same section / subsection and / or a different section / subsection.

[0013] In the description of embodiments of this disclosure, “including” and similar terms should be understood as “including, but not limited to.” The term “based on” should be understood as “based at least in part.” The term “one embodiment” or “this embodiment” should be understood as “at least one embodiment.” The term “several embodiments” should be understood as “at least several embodiments.” Other explicit and implicit definitions may also be included below. Terms such as “first,” “second,” etc., may refer to different objects or the same object. Other explicit and implicit definitions may also be included below.

[0014] Embodiments of this disclosure may include user data, data acquisition and / or use, etc. All of these aspects are subject to applicable laws and regulations and related provisions. In embodiments of this disclosure, all data collection, acquisition, processing, modification, transfer, and use are carried out on the premise that the user is aware of and acknowledges them. Accordingly, when implementing each embodiment of this disclosure, it is necessary to notify the user of the type of data or information that may be relevant, the scope of use, and the usage scenarios in an appropriate manner in accordance with applicable laws and regulations, and to obtain the user's permission. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited to this.

[0015] Any solutions in this specification and its embodiments relating to the processing of personal information are based on a lawful foundation (e.g., obtaining the consent of the data subject and being necessary to perform a contract) and are processed only within the scope of the provisions or agreements. Users may refuse the processing of personal information other than that essential for basic functions, and this will not affect their use of those basic functions.

[0016] As used herein, the term “model” refers to a system that can learn the association between corresponding inputs and outputs from training data, thereby enabling it to produce a corresponding output for a given input after training is complete. Model generation can be based on machine learning techniques. Depth learning is a machine learning algorithm that uses multi-layer processing units to process inputs and provide corresponding outputs. In this specification, “model” may also be referred to as “machine learning model,” “machine learning network,” or “network,” as used interchangeably herein.

[0017] With the advancement of autonomous driving technology, safety in situations where there is no human intervention in the vehicle is becoming a key concern. In particular, in the event of a vehicle malfunction (e.g., system failure, sensor failure, or energy shortage), rapid and effective control to restore the vehicle to a safe state is crucial. Some related technologies typically address this problem with a simple emergency parking mechanism, but this can lead to hidden hazards such as traffic congestion and secondary accidents.

[0018] Embodiments of this disclosure propose a method for an autonomous vehicle that may include determining a target mode for a minimum risk operation (MRM) that enters a minimum risk condition (MRC) in response to the detection of an anomaly associated with the autonomous vehicle. Policy information corresponding to the MRM's target mode is obtained, which indicates at least the maximum degree of impact on the traffic environment that the target mode is permitted for. The parking process of the autonomous vehicle is controlled based on the current traffic environment of the autonomous vehicle and the policy information.

[0019] Embodiments of the present disclosure can achieve a technical effect of performing differentiated processing according to the type of abnormality and traffic situation by dynamically determining the target mode of the minimum risk maneuver (MRM) when an autonomous vehicle detects an abnormality, obtaining corresponding policy information, and combining it with the current traffic environment to control the parking process. This method effectively reduces the degree of impact of parking on traffic while ensuring that the vehicle quickly and safely enters the minimum risk condition (MRC) under abnormal conditions, enhancing the real-time performance and flexibility of the abnormal handling of autonomous vehicles.

[0020] Exemplary environment FIG. 1 shows a schematic diagram of an exemplary environment 100 in which embodiments of the present disclosure can be realized. The environment 100 can include an autonomous vehicle 101. In some embodiments, the autonomous vehicle 101 can 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 passenger cars, trucks, buses, electric vehicles, recreational vehicles, etc. The autonomous vehicle 101 can also be an autonomous driving vehicle (also referred to as an autonomous vehicle) that integrates functions such as environmental perception, planning, and multi-level assisted driving.

[0021] As shown in FIG. 1, the electronic device 150 can be a device having any computing power, and the electronic device 150 can control the parking process of the autonomous vehicle.

[0022] It should be understood that the structure and function of the environment 100 are described only for illustrative purposes and do not imply any limitation on the scope of the present disclosure.

[0023] Vehicle parking control process Hereinafter, some exemplary embodiments of the present disclosure will be described with reference to the drawings. FIG. 2 shows a flowchart of a method 200 for an autonomous vehicle according to some embodiments of the present disclosure.

[0024] As shown in Figure 2, in block 201, the electronic device 150, in response to detecting an anomaly associated with the autonomous vehicle 101, determines the target mode of the minimum risk operation MRM to enter the minimum risk condition MRC.

[0025] The autonomous vehicle 101 may include vehicles that can autonomously sense the environment, plan routes, and perform driving operations through sensors, control systems, and algorithms, without relying on human driving. The autonomous vehicle 101 may experience malfunctions during operation due to various causes, such as hardware failures (e.g., sensor failures), software failures (e.g., algorithm errors), and changes in the external environment (e.g., extreme weather or road obstructions), and these malfunctions may pose a potential risk to the vehicle's driving safety and the surrounding traffic environment.

[0026] Different types of anomalies affect the vehicle's remaining driving capacity to varying degrees. For example, some anomalies allow the vehicle to move slowly, while some serious anomalies may result in a complete loss of driving capacity. To address these different situations, autonomous vehicles need to determine an appropriate minimum risk operation (MRM) target mode to enter the minimum risk condition (MRC). The MRM target modes can be classified into four modes based on the degree of impact on the traffic environment.

[0027] Figure 3 shows a schematic comparison of the characteristics 300 of four MRM modes according to some embodiments of this disclosure. For example, the four modes may include the first to fourth MRM modes. The four modes are described below.

[0028] The first MRM mode indicates parking in a port area, with a maximum impact level of 1. The first MRM mode indicates that the autonomous vehicle 101 should preferentially park in a port area (ZONE_HARBOR), such as a highway service area or a designated parking space in an urban area. The first MRM mode is the least congested and is typically only applied when the vehicle has higher surplus system capabilities, such as in the case of a minor sensor failure or a minor algorithmic anomaly. In this mode, the autonomous vehicle 101 can stop for an extended period for inspection or to return to normal operation. Because the number of port areas is limited and their distribution is not uniform, this mode places a high demand on the autonomous vehicle 101's route planning and navigation capabilities and is the highest priority, minimum risk operation mode.

[0029] The second MRM mode indicates parking on the shoulder of the road, and the degree of maximum impact is a second degree, which is higher than the first degree. The second MRM mode indicates that the autonomous vehicle 101 parks in a shoulder area (ZONE_PULLRIGHT), such as an emergency lane or hard shoulder on the right side of the road. The second MRM mode has a slightly higher degree of traffic congestion than the first MRM mode, but it is within an acceptable range. As an example, the second MRM mode can be applied when the autonomous vehicle 101 experiences a moderate malfunction (e.g., a decrease in the performance of the power system) but still has basic steering and mobility capabilities. This mode has fewer restrictions on the parking area, a shorter parking time, and the autonomous vehicle 101 needs to enter the shoulder area quickly to reduce interference with the traffic flow.

[0030] The third MRM mode indicates parking within the current lane, and the maximum impact level is higher than the second level. The third MRM mode indicates that the autonomous vehicle 101 will slowly decelerate and park within the current lane (ZONE_INLANE). For example, the third MRM mode is applied when the autonomous vehicle 101 is unable to steer but can control deceleration, for example, when part of the brake system is lost due to a failure. Because the autonomous vehicle 101 is stopped within the current lane, this mode has a significant impact on traffic congestion and can only be stopped for a short time to await further assistance or command. This third MRM mode has a low demand on the autonomous vehicle 101's system surplus capacity, but it is necessary to detect the traffic environment in real time to avoid secondary risks.

[0031] The fourth MRM mode indicates emergency parking, and the degree of maximum impact is higher than the third degree. The fourth MRM mode indicates that the autonomous vehicle 101 will immediately park in any permissible area with maximum braking capacity (ZONE_URGENCY). For example, the fourth MRM mode is suitable for highly urgent abnormal scenarios such as brake failure or complete loss of control of the vehicle. The target of emergency parking is to quickly eliminate a potential risk, the degree of traffic congestion is highest, and there are few restrictions on the parking area. In this mode, the autonomous vehicle 101 has the lowest requirement for excess system capacity and can simply trigger the brakes to stop movement, making it the lowest priority but safest measure.

[0032] Figure 4 shows a schematic comparison of the parking area 400 for four MRM modes according to some embodiments of this disclosure. Combining the above, the parking area range gradually expands from the first parking area corresponding to the first MRM mode (the fourth parking area corresponding to the fourth MRM mode is relatively the largest), the restrictions gradually decrease, and different adaptations to the severity of the anomaly are embodied.

[0033] For the first MRM mode, the parking area can be expressed as ZONE_HARBOR, and only vehicles that meet specific conditions such as a harbor area, port area, or shoulder area are permitted to park. The shoulder area may include areas located between the road boundary line and the roadside with a certain height (where vehicles cannot pass), where the shoulder width is sufficient to accommodate the vehicle body, and which are not no-parking zones (e.g., without no-parking signs).

[0034] In the second MRM mode, the parking area can be represented as ZONE_PULLRIGHT, and its range is expanded beyond ZONE_HARBOR, allowing vehicles to park on the right side in emergency lanes or diversion zones. For example, the area where parking is permitted may include emergency lanes and diversion zones on the right side of the road (e.g., diversion zones at highway exits). ZONE_INLANE can define no-parking zones, such as main lanes. If the emergency lane is occupied, the electronic device 150 can temporarily select the secondary right lane as the parking target point.

[0035] In the third MRM mode, the parking area can be represented as ZONE_INLANE, further expanding the parking range and allowing the vehicle to come to a gentle stop within the current lane. For example, ZONE_INLANE can include any location within the current lane, excluding no-parking zones. No-parking zones can include at least one of the following: within an intersection, within the yellow grid line area, the rightmost lane before an entrance / exit, the intersection and the 30-meter (adjustable) area before and after the intersection, and the single-right-turn lane and the 10-meter (adjustable) area before and after it.

[0036] In the fourth MRM mode, the parking area can be represented as ZONE_URGENCY, which has the widest range and virtually no restrictions on the parking location. For example, ZONE_URGENCY can include intersections, yellow grid lines, and main lanes as drivable areas. In some emergency scenarios (e.g., collision detection), additional constraints may be required on the parking process; for example, deceleration must not exceed a certain value, but the range of the parking location remains unaffected.

[0037] In block 202, the electronic device 150 acquires policy information corresponding to the MRM's target mode, and the policy information indicates at least the maximum degree of impact on the traffic environment that the target mode allows.

[0038] The policy information includes at least clarifying the maximum degree of impact on the traffic environment that is permissible for the target mode, i.e., the degree to which the autonomous vehicle is tolerable of interfering with the surrounding traffic flow in this mode. Each policy information corresponding to a different MRM target mode has its own emphasis. For example, corresponding to the first MRM mode, the policy information may allow only the autonomous vehicle 101 to park in a designated port area, indicating that the maximum impact is close to zero. On the other hand, corresponding to the fourth MRM mode, the policy information may allow the autonomous vehicle 101 to park in any drivable area at maximum deceleration, indicating a relatively high maximum impact. By obtaining policy information that matches the target mode, the system can reduce adverse impacts on the traffic environment while formulating safer and more efficient anomaly handling routes for the autonomous vehicle.

[0039] In block 203, the electronic device 150 controls the parking process of the autonomous vehicle 101 based on the current traffic environment and policy information of the autonomous vehicle 101.

[0040] The electronic device 150 can control the parking process of the autonomous vehicle 101 based on environmental sensing data and target mode constraints. The current traffic environment may include the type of lane in which the autonomous vehicle 101 is located (e.g., main lane, dedicated lane, or emergency lane), the flow and speed of surrounding vehicles, road signs (e.g., no parking signs), and the availability of shoulder or roadside areas. Combined with acquired policy information (e.g., parking location constraints, tolerance for traffic impact, parking time limits), the electronic device 150 can dynamically adjust the parking route and target location. For example, in the first MRM mode, the electronic device 150 can prioritize searching for the nearest port area for parking. In the second MRM mode, the electronic device 150 can select to park in the right-hand emergency lane or hard shoulder. In the third MRM mode, the electronic device 150 can adjust to minimize traffic impact while coming to a gentle stop within the current lane. In the third MRM mode, the electronic device 150 can come to a direct stop in any acceptable area with maximum deceleration in the shortest possible time. By integrating traffic environment and policy information in real time, the autonomous vehicle 101 can minimize interference with traffic flow while ensuring it can quickly enter the minimum risk condition (MRC) in the event of an anomaly. While parked, the electronics 150 control the autonomous vehicle 101 to illuminate the corresponding turn signal, and at other times (including after parking), it should illuminate the double flash, except during lane change / parking processes.

[0041] Through the above process, the electronic device 150 dynamically determines the target mode for minimum-risk operation MRM, acquires policy information corresponding to the target mode, and controls the parking process in conjunction with the current traffic environment, thereby achieving flexibility and efficiency in handling anomalies in autonomous vehicles. Based on different anomaly types and the vehicle's surplus driving capacity, it selects an appropriate MRM mode, combines parking area, time limit, and traffic impact constraints in the policy information to dynamically optimize the parking route, adjust the target position in real time, and enable the vehicle to enter minimum-risk conditions MRC quickly and safely. This method effectively reduces adverse impacts on the traffic environment, meets the demands of multiple scenarios ranging from minor anomalies to emergency breakdowns through grade-specific design, and significantly improves the safety and intelligence of autonomous vehicles.

[0042] In the example above, policy information corresponding to the MRM's target mode is obtained, and the policy information indicates the maximum degree of impact on the traffic environment that the target mode allows. Alternatively, the policy information may also indicate the maximum parking time for the autonomous vehicle 101. In this case, the electronic device 150 adjusts the MRM's target mode in response to the fact that the autonomous vehicle has not been parked within the maximum parking time.

[0043] If the autonomous vehicle 101 fails to complete parking within the maximum parking time, the electronic device 150 automatically adjusts the MRM target mode based on policy information so that the vehicle can quickly enter the minimum risk (MRC) condition.

[0044] For example, if the autonomous vehicle 101 has not completed parking in the first MRM mode after passing a specific distance (e.g., a provisional 2 kilometers) or reaching a specific time (e.g., a provisional 4 minutes), the electronic equipment 150 adjusts the target mode to the second MRM mode so that the autonomous vehicle 101 parks in the shoulder area. Also, for example, if the autonomous vehicle 101 has not completed parking within a specific time (e.g., a provisional 2 minutes) in the second MRM mode, remote operation (RA) is triggered, and the remote control system determines whether it is necessary to continue the attempt in the second MRM mode or to adjust to the third or fourth MRM mode. Once the autonomous vehicle 101 meets the adjustment conditions, it indicates that it should enter a slow stop or emergency parking state within the current lane. During this process, the autonomous vehicle 101 continues the parking operation in the current target mode while requesting a remote response or waiting for a formulation. This mechanism provides a flexible adjustment policy by dynamically adjusting the target mode, ensuring that the autonomous vehicle 101 can always complete parking in a safe and efficient manner even in abnormal situations.

[0045] In some embodiments, the policy information may also indicate system capability constraints 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 meet the system capability constraints.

[0046] Policy information can indicate 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 perform the current target mode. When the electronics 150 detects that the actual system capability of the autonomous vehicle 101 is lower than the system capability constraints, the target mode for the current least risk operation (MRM) is adjusted. For example, if the autonomous vehicle 101 is in the first MRM mode but does not have sufficient system capability to navigate accurately to the port area, the electronics 150 can dynamically lower the target mode to the second MRM mode so that the autonomous vehicle 101 can complete parking within the shoulder distance area. Similarly, if the autonomous vehicle 101 is in the second MRM mode and part of the braking system fails, preventing it from completing parking within a predetermined distance, the target mode can be adjusted to the third MRM mode, the fourth MRM mode, and so on, so that the autonomous vehicle 101 can come to a gentle or emergency stop within the current lane. This system capability constraint adjustment mechanism allows the electronic equipment 150 to adapt to changes in the hardware performance of the autonomous vehicle 101 and sudden anomalies, ensuring that the autonomous vehicle 101 can safely enter the least risk condition (MRC) even when its capabilities are limited.

[0047] In some embodiments, the electronic device 150 determines a parking position constraint corresponding to the MRM's target mode based on policy information. The parking position constraint determines a target parking point such that the impact on the current traffic environment caused by parking at the target parking point is less than the maximum impact. The device then triggers the autonomous vehicle to park in the target parking area.

[0048] In the first MRM mode, the electronic device 150 controls the autonomous vehicle 101 to search for a port area that matches the definition, park, and engage the P range. Since port areas typically have the least impact on the traffic environment, the autonomous vehicle 101 needs to have high navigation accuracy to enter the target parking point precisely. Parking is considered successful if the autonomous vehicle 101 completes parking in the port area within a specific distance (e.g., 2 kilometers) or time (e.g., 4 minutes) and the vehicle's attitude matches the parking conditions.

[0049] In the second MRM mode, the electronic device 150 controls the autonomous vehicle 101 to select the right-hand hard shoulder or emergency lane according to the parking position constraints and park, then engage the P range. If the right-hand lane is full due to temporary parking and parking is not possible, the electronic device 150 dynamically adjusts the parking position, such as by selecting the secondary right-hand lane as a temporary target point. If the autonomous vehicle 101 is not firmly stopped, the right-hand lane becomes available, and the electronic device 150 can update the parking position constraints in real time and control the autonomous vehicle 101 to return to the right-hand lane. Parking is considered successful if the center point of the vehicle is within the acceptable parking position and the angle between the vehicle body and the lane line is less than a preset value (e.g., 30°).

[0050] For the third MRM mode, the electronic device 150 sets a preset deceleration (e.g., -3 m / s) within the current lane based on parking position constraints. 2 The system determines whether parking can be completed within a specified distance (e.g., 25 meters) without exceeding a certain limit. If it cannot be completed, the electronic device 150 plans to drive towards the next available parking area and completes parking within a preset distance after entering that area. If a sudden environmental factor (e.g., a pedestrian suddenly appearing) results in a greater deceleration (e.g., -6 m / s 2If necessary, the electronic device 150 adjusts the parking position constraints and completes parking in a timely manner. To handle extreme situations, for the third MRM mode, if the autonomous vehicle 101 does not reduce its speed to 0 within 20 seconds and does not switch to safety mode (Fallback), it is recorded as a failure of the third MRM mode. In such cases, if the current area is a no-parking zone, the electronic device 150 immediately triggers the fourth MRM mode and the preset deceleration (-3m / s 2 The vehicle slows down to a parking state. If the current area is a no-parking zone, the autonomous vehicle 101 must prioritize leaving the no-parking zone before triggering the fourth MRM mode to complete the parking operation. Direct adjustment to the fourth MRM mode is not permitted within a no-parking zone. Furthermore, the electronic equipment 150 restricts the speed behavior of the autonomous vehicle 101 in the third MRM mode unless the third MRM mode is explicitly deactivated. For example, if the autonomous vehicle 101 slows down to a predetermined speed (e.g., 30 kph) or below, it is not permitted to accelerate again to a speed above that predetermined speed. This mechanism ensures that the third MRM mode dynamically adapts to the current environment in complex traffic scenarios, enabling quick and safe parking operations.

[0051] When the third MRM mode is triggered during a lane change, the current lane and the target lane have equal priority, and the electronic device 150 controls the autonomous vehicle 101 to select the more appropriate lane according to the actual road conditions to complete the parking. Parking is considered successful when the autonomous vehicle 101 comes to a complete stop within the parking area and the P range is engaged.

[0052] For the fourth MRM mode, the electronics 150 controls the autonomous vehicle 101 to park along the planned trajectory with maximum allowable deceleration (e.g., the system's maximum braking capability) and engage the P range. In certain scenarios (e.g., collision detection requires a low deceleration response), the electronics 150 parks within, for example, 10 meters, but with a deceleration of -6 m / s. 2The parking configuration can be adjusted, such as not exceeding a certain limit. When the 4th MRM mode is triggered during back-off, the electronic device 150 can apply deceleration until the vehicle is parked in the back-off direction. Whether moving forward or backward, success is considered achieved simply by bringing the vehicle to a firm stop and engaging the P range. For safety in extreme scenarios, if the autonomous vehicle 101 fails to complete parking within 10 seconds of triggering the 4th MRM mode, and remains in the 4th MRM mode (not transitioning to safety mode (Fallback)), it is recorded as a failure. In this case, the electronic device 150 can immediately trigger the transition to safety mode, forcing the autonomous vehicle 101 to slow down to a stationary state and ensure safe entry into minimum risk conditions. The transition to safety mode may include directly triggering emergency braking or adjusting the parking path to adapt to sudden environmental risks. This mechanism not only ensures the parking efficiency of the 4th MRM model under normal circumstances but also effectively addresses extreme scenarios, improving safety and robustness.

[0053] Regarding the four MRM modes, the first MRM mode corresponds to the first maximum parking time, the second MRM mode corresponds to the second maximum parking time, the third MRM mode corresponds to the third maximum parking time, and the fourth MRM mode corresponds to the fourth maximum parking time. The first maximum parking time is longer than the second maximum parking time, the second maximum parking time is longer than the third maximum parking time, and the third maximum parking time is longer than the fourth maximum parking time.

[0054] The first MRM mode corresponds to the first maximum parking time, which is the longest, allowing the autonomous vehicle 101 to park for an extended period within the ZONE_HARBOR area. The port area is typically designed as a dedicated parking area and has minimal impact on the traffic environment, allowing for mitigated parking times for purposes such as vehicle breakdown investigation or waiting for assistance. The setting of the first maximum parking time reflects the optimal balance between safety and traffic flow in this mode.

[0055] The second MRM mode corresponds to the second maximum parking time, which is relatively short and allows the vehicle to park for an equal amount of time within a ZONE_PULLRIGHT (e.g., emergency lane or hard shoulder). Since shoulder parking can have a certain impact on traffic volume, parking time needs to be moderately limited. For example, if rescue or remote control does not intervene in a timely manner, the parking time can be set to 4 minutes depending on the actual test situation, and exceeding this time can trigger a downgrade or adjustment of the target mode.

[0056] The third MRM mode corresponds to the third maximum parking time, which is further shortened and suitable for scenarios where the vehicle is slowly parking in its current lane. Since parking within a lane has a significant impact on traffic congestion, it is necessary to strictly limit the parking time. For example, it can be set to 2 minutes, ensuring that the vehicle completes the emergency procedure as quickly as possible and reducing interference with following vehicles.

[0057] The 4th MRM mode corresponds to the 4th maximum parking time, which is the shortest possible time and applies to highly urgent abnormal situations. When a vehicle is parked within a ZONE_URGENCY (such as any permitted area), the parking operation must be completed as quickly as possible to enter the Minimum Risk Condition (MRC). The parking time is limited to a very short period, for example, within 10 seconds, to minimize the continuous impact on the traffic environment.

[0058] The autonomous vehicle 101 may be a private car or a service vehicle. If it is a service vehicle, the autonomous vehicle 101 is the passenger transport process to the destination, and the method further includes determining whether the parking location corresponding to the target mode is farther than the destination, in response to whether the target mode is a first MRM mode or a second MRM mode. In response to the parking location being farther than the destination, the autonomous vehicle 101 is controlled to start the parking process corresponding to the target mode after completing the passenger transport process.

[0059] If the autonomous vehicle 101 is an operational vehicle and is in the passenger transport process, the electronic device 150 determines whether the parking location is farther than the order endpoint based on the parking location constraints corresponding to the target mode. If the parking location is farther than the destination, the autonomous vehicle 101 should prioritize completing the passenger transport process and then begin the parking operation corresponding to the target mode after the passengers have disembarked.

[0060] For example, in the first MRM mode, the parking location in the port area may be located on a section of road after the order endpoint. In this case, the autonomous vehicle 101 can continue moving forward to the order endpoint, and after the passengers have disembarked, replan the parking route according to the requirements of the first MRM mode and park in the port area. Similarly, in the second MRM mode, the parking location in the right lane may also be after the order endpoint. In this case, the autonomous vehicle 101 will prioritize completing the passenger arrival task and return to an area that meets the parking location constraints of the second MRM mode to complete the roadside parking operation.

[0061] Furthermore, to avoid interference during the status measurement of the passenger drop-off process, the passenger drop-off process is not recorded during parking measurement in the first MRM mode or the second MRM mode. This processing method ensures that passenger requests are met while simultaneously allowing the electronic device 150 to perform subsequent operations in response to parking requests in the target mode.

[0062] In some embodiments, the current traffic environment indicates whether the autonomous vehicle's current lane is a dedicated lane, and a dedicated lane includes a right-turn-only lane.

[0063] Figure 5 is a schematic diagram of a right-turn-only lane 500 according to some embodiments of the present disclosure. The current traffic environment may include dedicated lane identification information to indicate whether the lane in which the autonomous vehicle 101 is currently located belongs to a dedicated lane. Dedicated lanes typically include right-turn-only lanes, the rightmost vehicle lane before an entrance / exit, and other lane types with specific restrictions. When controlling the parking of the autonomous vehicle 101, the electronic equipment 150 needs to dynamically adjust the target parking position and route plan in accordance with the special requirements of the dedicated lane. A single right-turn-only lane (with hard isolation zones on both sides of the lane) and the designated distance range 501 (e.g., 10 meters) of its entrance / exit are defined as a no-parking zone in ZONE_URGENCY, as they are designed to ensure the smooth flow of right-turn traffic. If the autonomous vehicle triggers MRM mode in this zone, it should preferentially leave the right-turn-only lane before selecting an appropriate parking point.

[0064] The rightmost lane, located in front of the main entrance / exit, is generally considered a no-parking zone because it can significantly interfere with the flow of traffic entering and exiting the vehicle. When autonomous vehicle 101 is performing MRM mode, it should avoid this zone and prioritize selecting a location further away from the entrance / exit to complete the parking maneuver.

[0065] By combining these regulated conditions for dedicated driving lanes, the autonomous vehicle 101 can dynamically adjust its parking route to ensure that the parking action conforms to the policy information constraints of the target mode, while avoiding unnecessary interference with the current traffic environment.

[0066] In some embodiments, the target mode parking process based on minimum-risk operation MRM differs significantly from the parking requirements for passengers being picked up or dropped off in terms of parking area selection and the degree of traffic congestion. Parking for passengers being picked up or dropped off falls under temporary parking, where parking time can usually be estimated relatively well, and the degree of traffic congestion is relatively light and controllable. Therefore, the range of parking location selection is wide, and areas such as bus stops and entrance / exit areas can all be used as passenger pick-up / drop-off points. On the other hand, the target mode parking process based on minimum-risk operation MRM falls under parking after a vehicle malfunction. Since information such as whether the malfunction has been resolved or when assistance will arrive is unpredictable, the target mode parking process based on minimum-risk operation MRM is more strict in area selection to ensure safety as much as possible and reduce traffic congestion. For example, areas such as the rightmost lane adjacent to entrances / exits and bus stops are no-parking zones. This design, through different adaptations of two types of parking scenarios, ensures that the pick-up / drop-off needs of operating vehicles are met while simultaneously providing a safer and more standardized parking solution in the event of an emergency.

[0067] Exemplary devices and equipment Figure 6 is a schematic block diagram of a device 600 for an autonomous vehicle according to one embodiment of the present disclosure. The device 600 may be implemented in or included in the remote device 120. Each module / component within the device 600 may be implemented in hardware, software, firmware, or any combination thereof.

[0068] As shown in the figure, the device 600 includes a target mode determination module 601 configured to determine the target mode of a minimum risk operation MRM that enters the minimum risk condition MRC in response to the detection of an anomaly associated with the autonomous vehicle. A policy information acquisition module 602 acquires policy information corresponding to the target mode of the MRM, and the policy information is configured to indicate at least the maximum degree of impact on the traffic environment that the target mode is permitted to. A parking control module 603 is configured to control the parking process of the autonomous vehicle based on the current traffic environment and policy information of the autonomous vehicle.

[0069] In some embodiments, the policy information also indicates the maximum parking time for the autonomous vehicle, and the device 600 also includes a target mode adjustment module. The target mode adjustment module adjusts the target mode of the MRM in response to the fact that parking of the autonomous vehicle is not completed within the maximum parking time.

[0070] In some embodiments, the policy information also indicates system capability constraints corresponding to the target mode, and the target mode adjustment module is configured to adjust the MRM's target mode in response to detecting that the autonomous vehicle's system capability does not meet the system capability constraints.

[0071] In some embodiments, the parking control module 603 can be configured to specifically determine parking position constraints corresponding to the target mode of the MRM based on strategic information. The parking position constraints determine a target parking point such that the impact on the current traffic environment by parking at the target parking point is less than the maximum impact. The autonomous vehicle is then triggered to park in the target parking area.

[0072] In some embodiments, the target mode determined by the target mode determination module 601 is selected from preset modes: a first MRM mode indicating parking in the port area with a maximum impact level of first degree; a second MRM mode indicating parking on the shoulder of the road with a maximum impact level of second degree, which is higher than the first degree; a third MRM mode indicating parking within the current lane with a maximum impact level of third degree, which is higher than the second degree; and a fourth MRM mode indicating emergency parking with a maximum impact level of fourth degree, which is higher than the third degree.

[0073] In some embodiments, the first MRM mode corresponds to the first maximum parking time, the second MRM mode corresponds to the second maximum parking time, the third MRM mode corresponds to the third maximum parking time, and the fourth MRM mode corresponds to the fourth maximum parking time, with the first maximum parking time being longer than the second maximum parking time, the second maximum parking time being longer than the third maximum parking time, and the third maximum parking time being longer than the fourth maximum parking time.

[0074] In some embodiments, the autonomous vehicle is a passenger transport process to a destination, and the parking control module 603 is further configured to determine whether the parking location corresponding to the target mode is farther than the destination, in response to the target mode being a first MRM mode or a second MRM mode. In response to the parking location being farther than the destination, the autonomous vehicle is controlled to start the parking process corresponding to the target mode after completing the passenger transport process.

[0075] In some embodiments, the current traffic environment indicates whether the autonomous vehicle's current lane is a dedicated lane, and a dedicated lane includes a right-turn-only lane.

[0076] Figure 7 shows a block diagram of a computing device 700 in which one or more embodiments of the present disclosure are implemented. It should be understood that the computing device 700 shown in Figure 7 is merely illustrative and should not constitute any limitation on the functionality and scope of the embodiments described herein. The computing device 700 shown in Figure 7 can implement the remote device 120 or electronic device 150 of Figure 1.

[0077] As shown in Figure 7, the computing device 700 is in the form of a general-purpose computing device. The components of the 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. The processing unit 710 may be an actual or virtual processor and can perform various processes according to a program stored in memory 720. In a multiprocessor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the computing device 700.

[0078] The computing device 700 typically includes multiple computer storage media. Such media may be any available media accessible to the computing device 700, and include, but are not limited to, volatile media, non-volatile media, removable media, and non-removable media. Memory 720 is volatile memory (e.g., registers, caches, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electro-erasable programmable read-only memory (EEPROM), flash memory, or any combination thereof). Storage media 730 may be removable media and non-removable media, and may include machine-readable media such as flash drives, disks, or any other media, which can be used to store information and / or data (e.g., training data for training) and can be accessed within the computing device 700.

[0079] The computing device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Not shown in Figure 7, disk drives for reading from or writing to removable, non-volatile disks (e.g., “floppy disks”) may be provided. In these cases, each driver may be connected to a bus (not shown) by one or more data media interfaces. Memory 720 may include a computer program product 725 having one or more program modules, these program modules being arranged to perform various methods or operations of various embodiments of the present disclosure.

[0080] The communication unit 740 enables communication with other computing devices via a communication medium. Furthermore, the functions of the components of the computing device 700 can be realized by a single computing cluster or multiple computer devices, and these computer devices can communicate via communication connections. Therefore, the computing device 700 can operate in a network environment using logical connections with one or more other servers, network personal computers (PCs), or other network nodes.

[0081] The input device 750 may be one or more input devices such as a mouse, keyboard, or trackball. The output device 760 may be one or more output devices such as a display, speaker, or printer. The computing device 700 may also communicate with one or more external devices (not shown) such as a storage device or display device via the communication unit 740 as needed, communicate with one or more devices that allow the user to interact with the computing device 700, or communicate with any device (e.g., a network card or modem) that allows the computing device 700 to communicate with one or more other computing devices. Such communication may be performed via an input / output (I / O) interface (not shown).

[0082] According to exemplary embodiments of the present disclosure, a computer-readable storage medium is provided which stores computer-executable instructions that are executed by a processor to accomplish the above-described method. According to exemplary embodiments of the present disclosure, a computer program product is further provided which is tangibly stored on a non-transient computer-readable medium and includes computer-executable instructions that are executed by a processor to accomplish the above-described method.

[0083] Here, various aspects of this disclosure will be described with reference to flowcharts and / or block diagrams of the methods, apparatus, devices, and computer program products realized by this disclosure. It should be understood that each block in the flowcharts and / or block diagrams, and each combination of blocks in the flowcharts and / or block diagrams, can be realized by computer-readable program instructions.

[0084] These computer-readable program instructions can be provided to the processing units of a general-purpose computer, a dedicated computer, or other programmable data processing device, and so a machine can be manufactured that generates a device that implements the functions / operations defined in one or more blocks of a flowchart and / or block diagram when these instructions are executed by the processing units of a computer or other programmable data processing device. These computer-readable program instructions may be stored in a computer-readable storage medium, and these instructions cause a computer, a programmable data processing device, and / or other device to operate in a particular way, and so a computer-readable medium storing the instructions includes a product containing instructions that implement various modes of the functions / operations defined in one or more blocks of a flowchart and / or block diagram.

[0085] Computer-readable program instructions can be loaded into a computer, other programmable data processing device, or other device, which can then execute a series of operational steps to generate a computer-implemented process. Thus, instructions executed on a computer, other programmable data processing device, or other device can implement functions / operations defined in one or more blocks of a flowchart and / or block diagram.

[0086] The flowcharts and block diagrams in the drawings illustrate the implementable architectures, functions, and operations of several implemented systems, methods, and computer program products relating to this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of an instruction containing one or more executable instructions for implementing a given logical function. The functions shown in a block may occur in an order different from the order shown in the drawing, or they may be implemented as a switch. For example, two consecutive blocks may actually be executed essentially in parallel, or they may be executed in reverse order depending on the functions they relate to. Note also that each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, may be implemented in a dedicated hardware-based system that performs a given function or operation, or in a combination of dedicated hardware and computer instructions.

[0087] While various implementations of this disclosure have been described above, these descriptions are illustrative, incomplete, and not limited to the various implementations disclosed. Many modifications and changes will be apparent to those skilled in the art without departing from the scope and spirit of the implementations described. The choice of terms used herein is intended to best describe the principle, practical use, or improvements in the technology in the market of each implementation, or to enable those skilled in the art to understand each embodiment disclosed herein.

Claims

1. In response to detecting an anomaly associated with an autonomous vehicle, the system determines the target mode of the least risk operation (MRM) to enter the least risk condition (MRC), and The policy information corresponding to the target mode of the MRM is obtained, and the policy information indicates at least the maximum degree of impact on the traffic environment that the target mode allows. This includes controlling the parking process of the autonomous vehicle based on the current traffic environment of the autonomous vehicle and the policy information, Methods for autonomous vehicles.

2. The policy information further indicates the maximum parking time for the autonomous vehicle, and the method is The further includes adjusting the target mode of the MRM in response to the fact that parking of the autonomous vehicle is not completed within the maximum parking time, The method according to claim 1.

3. The policy information further indicates the system capability constraints corresponding to the target mode, and the method is The further includes adjusting the target mode of the MRM in response to detecting that the system capabilities of the autonomous vehicle do not satisfy the system capability constraints. The method according to claim 1.

4. Controlling the parking process of the autonomous vehicle based on the current traffic environment and policy information of the autonomous vehicle is: Based on the aforementioned policy information, the parking position constraints corresponding to the target mode of the MRM are determined, The aforementioned parking location constraint involves determining a target parking point, wherein the degree of impact on the current traffic environment caused by parking at the target parking point is less than the maximum impact. The autonomous vehicle includes triggering the vehicle to park at the target parking point, The method according to claim 1.

5. The aforementioned target mode is, This indicates parking in the port area, and the first MRM mode is such that the maximum impact level is the first level, The second MRM mode indicates parking on the shoulder of the road, and the degree of maximum impact is a second degree which is higher than the first degree, The third MRM mode indicates parking within the current lane, and the degree of maximum impact is higher than the second degree, A preset mode is determined from the following: a fourth MRM mode, which indicates emergency parking and has a fourth degree of maximum impact that is higher than the third degree; The method according to claim 1.

6. The first MRM mode corresponds to the first maximum parking time, the second MRM mode corresponds to the second maximum parking time, the third MRM mode corresponds to the third maximum parking time, and the fourth MRM mode corresponds to the fourth maximum parking time. The first maximum parking time is longer than the second maximum parking time, the second maximum parking time is longer than the third maximum parking time, and the third maximum parking time is longer than the fourth maximum parking time. The method according to claim 5.

7. The autonomous vehicle is in the process of transporting passengers to their destination, and the method is: In response to the target mode being the first MRM mode or the second MRM mode, it is determined whether the parking position corresponding to the target mode is farther from the destination. The further includes controlling the autonomous vehicle to initiate a parking process corresponding to the target mode after completing the passenger transport process, in response to the parking location being further away from the destination, The method according to claim 5.

8. The current traffic environment indicates whether the autonomous vehicle's current lane is a dedicated lane, and the dedicated lane includes a right-turn-only lane. The method according to claim 1.

9. A target mode determination module configured to determine a target mode for a minimum risk operation (MRM) that enters a minimum risk condition (MRC) in response to the detection of an anomaly associated with an autonomous vehicle, A policy information acquisition module acquires policy information corresponding to the target mode of the MRM, and the policy information is configured to at least indicate the maximum degree of impact on the traffic environment that the target mode allows, 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 policy information, comprising: A device for autonomous vehicles.

10. At least one processing unit, An electronic device comprising at least one memory coupled to the at least one processing unit, wherein, when the instruction is executed by the at least one processing unit, the electronic device causes the electronic device to perform the method according to any one of claims 1 to 8. electronic equipment.

11. When executed on a processor, a computer program that implements the method described in any one of claims 1 to 8 is stored. Computer-readable storage medium.

12. When executed by a processor, the computer executable instruction includes a method according to any one of claims 1 to 8, Computer program products.

Images