Automated driving risk processing method and apparatus, device, medium, product, and vehicle
By designing a dual-layer redundant architecture of HAD main control system and HAD auxiliary control system in L3 autonomous driving system, and utilizing the simplified redundancy design and safety verification of HAD auxiliary control system, the problem of safe vehicle transfer when HAD main control system fails is solved, achieving a balance between cost-effectiveness and safety.
Patent Information
- Application Number
- PCT/CN2026/095986
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-05-09
- Filing Date
- 2026-05-09
- Publication Date
- 2026-11-12
AI Technical Summary
In a Level 3 conditional automated driving system, how can the HAD auxiliary control system safely switch over and execute the minimum risk strategy when the HAD master control system fails, ensuring that the vehicle moves from a dangerous state to a low-risk state, meeting functional safety standards, while also taking into account cost and safety?
The design incorporates a dual-layer redundant architecture for the HAD main control system and the HAD auxiliary control system. The HAD main control system has a high functional safety level and can prevent the vehicle from changing lanes when switching to the HAD auxiliary control system. It also executes a minimum risk strategy within the user's reaction time, including generating virtual lane boundaries, dynamically setting steering wheel angle thresholds, and implementing an emergency obstacle avoidance mechanism to ensure vehicle safety.
In the event of a failure of the HAD main control system, the simplified redundancy design and safety verification of the HAD auxiliary control system enable safe vehicle transfer and a minimum risk strategy, reducing hardware costs and ensuring vehicle safety and reliability in emergency situations.
Smart Images

Figure CN2026095986_12112026_PF_FP_ABST
Abstract
Description
Autonomous driving risk management methods, devices, equipment, media, products and vehicles Cross-reference to related applications
[0001] This application claims priority to Chinese patent application No. 202510595177.9, filed on May 9, 2025, the entire contents of which are incorporated herein by reference. Technical Field
[0002] This application relates to, but is not limited to, the field of vehicle technology, and particularly to a risk management method, apparatus, electronic device, computer-readable storage medium, program product, and vehicle based on autonomous driving. Background Technology
[0003] In intelligent driving scenarios, the core objective of the Minimum Risk Maneuver (MRM) is to transfer the vehicle from a dangerous state to a low-risk state through controlled operations when the vehicle's autonomous driving system fails, thereby ensuring the safety of occupants and the road, and meeting the risk control requirements of functional safety standards such as ISO 26262. Meanwhile, for Level 3 conditional autonomous driving systems, how to rationally design a Highly Automated Driving (HAD) main control system and a HAD auxiliary control system to achieve the aforementioned minimum risk maneuver while maintaining safety and considering cost remains a difficult problem to solve in the industry. Summary of the Invention
[0004] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.
[0005] This application provides a risk management method, apparatus, electronic device, computer-readable storage medium, program product, and vehicle based on autonomous driving.
[0006] According to a first aspect of the embodiments of this application, a risk management method based on autonomous driving is provided, applied to a vehicle, wherein the vehicle is equipped with a High-Level Automated Driving (HAD) master control system and a HAD auxiliary control system configured to control the vehicle to perform autonomous driving, wherein the functional safety level of the HAD master control system is higher than that of the HAD auxiliary control system; the method includes: when it is determined that the current operating environment of the vehicle is in the design operating domain of a Level 3 conditional automated driving system, preventing the vehicle from changing lanes within the user reaction time after the current control system controlling the vehicle to perform autonomous driving is switched from the HAD master control system to the HAD auxiliary control system; if no user takeover instruction is received, and if the runtime of the HAD auxiliary control system is greater than the user reaction time, then executing a minimum risk strategy matched to the current operating environment.
[0007] According to a second aspect of the embodiments of this application, a risk handling device based on autonomous driving is provided, applied to a vehicle, wherein the vehicle is equipped with a High-Level Automated Driving (HAD) master control system and a HAD auxiliary control system configured to control the vehicle to perform autonomous driving, wherein the functional safety level of the HAD master control system is higher than that of the HAD auxiliary control system; the device includes: a vehicle lane change prevention unit, configured to prevent the vehicle from changing lanes within the user reaction time after the current control system controlling the vehicle to perform autonomous driving is switched from the HAD master control system to the HAD auxiliary control system when it is determined that the current operating environment of the vehicle is in the design operating domain of a Level 3 conditional automated driving system; and a minimum risk strategy execution unit, configured to execute a minimum risk strategy matched to the current operating environment if the runtime of the HAD auxiliary control system is greater than the user reaction time when no user takeover instruction is received.
[0008] According to a third aspect of the present application, an electronic device is provided, comprising: at least one processor; at least one memory configured to store processor-executable instructions, wherein the at least one memory and the at least one processor are communicatively connected to each other; wherein the at least one processor implements the risk management method based on autonomous driving as described in the first aspect by executing the executable instructions.
[0009] According to a fourth aspect of the embodiments of this application, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed by at least one processor, it implements the risk handling method based on autonomous driving described in the first aspect.
[0010] According to a fifth aspect of the embodiments of this application, a computer program product is provided, including a computer program / instructions that, when executed by at least one processor, implement the risk handling method based on autonomous driving described in the first aspect.
[0011] According to a sixth aspect of the embodiments of this application, a vehicle is provided, comprising: a risk handling device based on autonomous driving as described in the second aspect above; or an electronic device as described in the third aspect above; or a non-transitory computer-readable storage medium as described in the fourth aspect above; or a computer program product as described in the fifth aspect above; or, at least one processor and at least one memory communicatively connected to the at least one processor, wherein the at least one memory stores computer-executable instructions, and the at least one processor implements the risk handling method based on autonomous driving as described in the first aspect by executing the computer-executable instructions.
[0012] It should be understood that the above general description and the following detailed description are exemplary and illustrative only, and are not intended to limit this application. Other aspects will become clear after reading and understanding the accompanying drawings and detailed description. Attached Figure Description
[0013] To more clearly illustrate the technical solutions of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. The drawings described below are merely some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0014] Figure 1 is a schematic diagram of the architecture of a risk management system based on autonomous driving, as shown in an embodiment of this application.
[0015] Figure 2 is a flowchart illustrating a risk management method based on autonomous driving according to an embodiment of this application.
[0016] Figure 3 is a schematic diagram of an HAD master control system shown in an embodiment of this application.
[0017] Figures 4A and 4B are schematic diagrams of an HAD auxiliary control system shown in an embodiment of this application.
[0018] Figure 5 is a flowchart illustrating another risk management method based on autonomous driving, as shown in an embodiment of this application.
[0019] Figure 6 is a schematic diagram of the structure of an electronic device according to an embodiment of this application.
[0020] Figure 7 is a block diagram of a risk management device based on autonomous driving, as shown in an embodiment of this application. Detailed Implementation
[0021] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application.
[0022] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.
[0023] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."
[0024] The embodiments of the risk management method based on autonomous driving of this application will be described in detail below with reference to the accompanying drawings.
[0025] Figure 1 is a schematic diagram of the architecture of a risk management system based on autonomous driving, as shown in an embodiment of this application. As shown in Figure 1, the system may include a vehicle 10, a HAD main control system 11, and a HAD auxiliary control system 12.
[0026] Vehicle 10 refers to an intelligent vehicle integrating Level 3 conditional automated driving (HAD) functionality. The core architecture of this system includes a "full-scale HAD main control system and a general HAD auxiliary control system," specifically a dual-layer redundancy design of HAD main control system 11 and HAD auxiliary control system 12. During normal operation, the vehicle relies on HAD main control system 11 for full-scene perception and decision-making. HAD auxiliary control system 12, as a degraded redundancy module, only takes over basic control when HAD main control system 11 fails. Through a collaborative mechanism, it ensures that even if HAD main control system 11 fails (e.g., its function is disabled or blocked), it can still trigger a minimum-risk strategy based on the perception information of HAD main control system 11 or its own limited capabilities, ultimately achieving the goal of safe parking. HAD main control system 11 and HAD auxiliary control system 12 can establish a communication channel to exchange relevant data when switching the current control system. Vehicle 10 can be a gasoline vehicle, hybrid vehicle, electric vehicle, or other vehicles with different power types and autonomous driving capabilities; this application does not impose any limitations on this. In the embodiments of this application, L3 conditional automated driving means that under specific conditions (such as highways), the vehicle can complete all driving operations completely autonomously, and the driver can "take off their hands and eyes", but needs to be ready to take over at any time when the system issues a request.
[0027] As a "full-scale HAD master control system," the HAD master control system 11 still possesses comprehensive perception coverage capabilities when operating independently and can autonomously perform MRM tasks such as parallel parking. The individual system's functional safety level (Automotive Safety Integrity Level, ASIL) reaches ASIL B or higher. Under normal circumstances, the HAD master control system 11 is responsible for full vehicle control. Even if the HAD auxiliary control system 12 is suspended or fails, its built-in high redundancy design still ensures that the vehicle can complete the full functions required for autonomous driving scenarios, thus meeting high reliability requirements. However, this also necessitates higher hardware costs, such as the development of high-performance chips, multi-sensor configuration, and increased development and verification complexity.
[0028] Taking Figure 3 as an example, assuming that the vehicle in the figure is performing intelligent driving through the HAD main control system 11 in the L3 conditional automated driving system, the HAD main control system 11 can achieve 360-degree full-range perception coverage of the driving environment through sensors in all directions. By recognizing and analyzing targets in each direction, it can meet the driving needs of complex driving scenarios such as cities.
[0029] As a "general HAD auxiliary control system," the HAD auxiliary control system 12 has significantly weaker perception capabilities and computing power than the main control system. It cannot independently achieve full-range environmental perception at a high safety level (i.e., ASIL B and above). In other words, the functional safety level of the HAD main control system 11 in this application is higher than that of the aforementioned HAD auxiliary control system 12. The main function of the HAD auxiliary control system 12 is to take over vehicle control based on limited perception information, such as shared data of the HAD main control system 11 or information perceived by its own basic sensors, when the HAD main control system 11 fails. It also restricts the execution of lane changing and other operation permissions within the user's reaction time and triggers MRM based on its own perception results. Its design simplifies hardware redundancy and safety verification strength, and its cost is lower than that of the HAD main control system 11. However, it needs to cooperate with the HAD main control system 11 to enable the vehicle to meet the overall ASIL level requirements.
[0030] The following description, using Figures 4A and 4B, assumes that the vehicle in Figure 4A is performing intelligent driving through the HAD (Help-Assisted Driving) system 12 in a Level 3 Conditional Automated Driving (HAD) system. It utilizes a combination of sensors in five directions around the vehicle (e.g., front, left front, right front, left rear, and right rear), such as a 5R1V (5Radar + 1Vision, i.e., 5 radars + 1 camera) system, to achieve limited perception coverage. It independently meets the functional safety level ASIL B requirements only in each direction. Its core design lies in the redundant perception and independent control capabilities for critical directions (e.g., the vehicle's main direction of travel and adjacent lanes). For example, by cross-verifying the target position and motion state using multiple radars, it ensures that even if the main HAD system 11 fails, the HAD system 12 can still perform lane change and obstacle avoidance or emergency braking based on local high-confidence data. This is suitable for scenarios requiring consideration of multi-directional risks such as pedestrians crossing urban roads and blind spots at intersections. Of course, the HAD auxiliary control system 12 can be further simplified to the system architecture shown in the operating vehicle in Figure 4B. In this case, the HAD auxiliary control system 12 focuses on the sensor combination for the vehicle's core driving directions (e.g., front, left rear, and right rear). For example, a simplified sensor configuration of 3R1V (3Radar + 1Vision, i.e., 3 radars + 1 camera) can be used to achieve limited perception coverage, meeting ASIL B safety level only in special scenarios such as highways. Specifically, the forward radar and camera can be fused to perceive vehicles in the main lane and adjacent lanes, while the lateral radar monitors blind spots, ensuring redundant control capabilities for high-speed following, lane changing, and other operations. However, the perception range and direction of the HAD auxiliary control system 12 in Figure 4B are significantly limited, making it unable to cope with complex risks such as pedestrians suddenly crossing the road in urban conditions and multi-directional interactions on unstructured roads. Therefore, it is only suitable for use on closed roads such as highways, relying on the uniformity of road conditions and the low probability of pedestrians to avoid safety vulnerabilities caused by perception blind spots.
[0031] Those skilled in the art will understand that the solutions in this application are not applicable to L4 highly automated driving systems, which correspond to L3 conditional automated driving systems. This is because the latter is strictly limited to operating within a preset Operational Design Domain (ODD) and is required to achieve fully autonomous control within that domain, without human intervention. Its system redundancy design and functional safety level already cover the fault response capabilities for all anticipated scenarios. Therefore, even if the HAD master control system in an L4 highly automated driving system fails, the HAD auxiliary control system, with performance identical to the HAD master control system, can directly complete a safe stop without relying on driver intervention. Consequently, there are no user reaction time or related concepts and requirements such as MRM (Management Reaction Time).
[0032] Figure 2 is a flowchart illustrating an exemplary embodiment of the present application of a risk management method based on autonomous driving. The method is applied to a vehicle, which is equipped with a high-level autonomous driving (HAD) main control system and a HAD auxiliary control system for controlling the autonomous driving of the vehicle. The functional safety level of the HAD main control system is higher than that of the HAD auxiliary control system. Specifically, it may include the following steps 202 and 204.
[0033] In step 202, if it is determined that the current operating environment of the vehicle is within the design operating domain of the L3 conditional automated driving system, the vehicle is prevented from changing lanes within the user reaction time after the current control system controlling the vehicle's automated driving is switched from the HAD master control system to the HAD auxiliary control system.
[0034] The operation of the L3 conditional automated driving system of the above-mentioned vehicle is premised on the vehicle being within the corresponding design operating domain. When the L3 conditional automated driving system is running, the above-mentioned HAD main control system or the above-mentioned HAD auxiliary control system can be selected as the current control system for controlling the autonomous driving of the above-mentioned vehicle. In the case of switching the current control system from the above-mentioned HAD main control system to the above-mentioned HAD auxiliary control system, the timing starts after the switch. Within the preset user reaction time, such as 10 seconds, the above-mentioned HAD auxiliary control system can control and prevent the above-mentioned vehicle from changing lanes.
[0035] In this embodiment, the above-mentioned design operating domain may include at least one of the following constraints: 1. The vehicle operates in a low-risk urban area that meets the low-risk conditions. The low-risk conditions may include whether the city where the vehicle is located meets the characteristics of "low pedestrian interference". For example, the probability of pedestrian intrusion into the roundabout or intersection in the city is lower than a preset probability threshold. Of course, the probability of pedestrian intrusion into the intersection depends on the data measurement and summary of the corresponding city's operation demonstration area, that is, the corresponding city opens up the passable L3 level autonomous driving operation area according to the conditions; 2. The speed of the vehicle is lower than the safe speed threshold corresponding to the current road scenario type. The system mandates that vehicles travel at low speeds, not exceeding the maximum speed limit for the corresponding scenario, when merging at urban intersections or highways. This speed limit reduces the impact energy of sudden events such as pedestrians crossing or collisions between vehicles in adjacent lanes, while also allowing redundant time for the limited perception and decision-making of the HAD (Hyper-Assisted Driving) system, preventing accidents caused by response delays. Furthermore, the system requires that the key driving scenario locations in the vehicle's navigation map meet the first functional safety level. This necessitates that the vehicle operate on roads equipped with high-precision maps or perception fusion navigation, ensuring that the data integrity and reliability of key driving scenario location information, such as lane change points and intersection features, meet ASIL (Autonomous Safety Level). Level B, in which the collaboration between the map and real-time perception can compensate for the insufficient local perception capability of the HAD auxiliary control system and ensure the safety of path planning; 4. The traffic light detection capability of the above vehicles meets the second functional safety level, which requires the HAD auxiliary control system to achieve ASIL B in its ability to recognize traffic lights. For example, the traffic light timing sequence is pre-stored on the map and cross-validated with the real-time perception results of the vehicle. For example, the map indicates the remaining time of the green light, while the HAD auxiliary control system provides images captured by the camera to verify the actual light color. Ultimately, this ensures that the system can still reliably respond to traffic signals when the sensors are limited, and avoids running red lights.
[0036] Those skilled in the art will understand that, given the specific content of the above-mentioned design operating domain, the vehicle needs to satisfy each constraint condition to determine that its current operating environment is within the design operating domain of the L3 conditional autonomous driving system. For L3 operating scenarios, the above-mentioned cooperative constraint method can reduce the capacity burden of the auxiliary control system in complex environments and ensure safety boundaries.
[0037] Furthermore, the triggering conditions for switching the current control system from the HAD master control system to the HAD auxiliary control system can be determined by the actual situation of the HAD master control system, thereby ensuring the flexibility of the control system switching operation.
[0038] In one embodiment, if an abnormality is detected in the operating state of the aforementioned HAD main control system, the current control system for the vehicle's autonomous driving can be switched from the HAD main control system to the aforementioned HAD auxiliary control system. Specifically, the HAD main control system can confirm the fault type and scope of impact based on its self-test unit or independent safety monitor. If it is determined that the fault is an unrecoverable error such as hardware damage or a degradation of safety-critical functions caused by a perception coverage rate below a threshold, then the abnormality in the HAD main control system's operating state can be confirmed, and a switching request can be sent to the vehicle controller or the HAD auxiliary control system. Alternatively, the built-in diagnostic module of the vehicle controller or the HAD auxiliary control system can monitor the operational health of the main control system in real time. Once an abnormal signal is detected, the control system switching process is immediately triggered. During the switching process, the HAD main control system can freeze the current control commands and synchronize status information such as vehicle speed and heading angle to the HAD auxiliary control system. The HAD auxiliary control system then takes over the vehicle based on a pre-loaded degradation control algorithm and prevents the vehicle from changing lanes, thereby maintaining the vehicle's basic control capabilities and preventing the risk of loss of control.
[0039] In the aforementioned degraded control algorithm, the effect of preventing vehicles from changing lanes can be achieved through a combination of one or more strategies using various methods. For example: 1. Dynamically set the steering wheel angle limit threshold based on the current vehicle speed and lane curvature, that is, calculate the maximum allowable steering wheel angle threshold in real time based on the current vehicle speed and lane curvature. For example, on high-speed straight sections with low curvature, limit the rate of change of steering angle to prevent sudden lane changes; on curves with high curvature, appropriately relax the threshold to maintain trajectory tracking; 2. Determine the lateral acceleration safety threshold of the vehicle based on the current vehicle speed, that is, set the upper limit of lateral acceleration based on the vehicle speed. If the control command of the HAD auxiliary control system causes the actual acceleration to approach the threshold, intervention can be triggered, such as torque superposition of reverse torque or forced deceleration, to avoid the risk of sideslip caused by aggressive steering; 3. Generate a virtual lane boundary for the current lane so that the vehicle can perform a boundary correction operation when deviating from the current lane. This involves using limited perception data from the auxiliary control system, such as lane line image data identified by a monocular camera or high-precision map information, to generate a virtual boundary within the current lane of the vehicle, such as a line segment of ±0.5 meters from the lane centerline. The system then uses a preset model to predict and control the lateral deviation between the vehicle's heading and the boundary in real time. If the deviation exceeds the preset tolerance, the system activates the correction logic, automatically fine-tunes the steering wheel to bring the vehicle back to the center of the lane, and suppresses lane change requests initiated by the system.
[0040] Understandably, the core purpose of preventing vehicles from changing lanes is to balance path stability and flexibility under degraded control, avoid instability caused by aggressive operation of the HAD (Hyper-Assisted Driving) system, and ultimately ensure vehicle safety. However, for emergency targets such as obstacles, pedestrians, or out-of-control vehicles that suddenly appear on the driving path and require immediate avoidance, the solution in this application can specifically introduce an emergency obstacle avoidance mechanism. That is, after the HAD system takes over, it allows temporary lifting of lane change restrictions and execution of emergency lane change operations. Specifically, through the limited perception capabilities of the HAD system, such as forward-facing radar and cameras, or the effective data remaining in the HAD main control system, such as pre-fault fusion perception results, collision risk targets in the lane can be detected in real time. When a collision risk target meets the preset emergency obstacle avoidance conditions, it can be used as an emergency obstacle avoidance target, and the vehicle can be temporarily allowed to change lanes to avoid the emergency obstacle avoidance target. The aforementioned emergency obstacle avoidance conditions may include, but are not limited to: 1. The collision risk target is a dynamic obstacle such as a pedestrian or vehicle, or a static obstacle such as a falling rock, and the expected collision time with the vehicle is less than the minimum collision threshold; 2. It is determined by lateral radar or camera that there is sufficient space in the adjacent lane and no continuously approaching vehicles at high speed; 3. The lateral control capability of the HAD auxiliary control system has been verified to be usable, for example, the steering actuator corresponding to the HAD auxiliary control system is in normal condition and the lane line recognition confidence level meets the standard.
[0041] Once the emergency obstacle avoidance conditions are met, the HAD (Hazard Auxiliary Control) system can immediately activate the corresponding module, temporarily deactivate the lane change prevention strategy, and generate an emergency lane change trajectory. This endows the HAD system with the ability to avoid risks in critical scenarios, reducing preventable collisions. If the risk is eliminated after the lane change, the lane change prevention strategy can be reactivated until the user's reaction time expires or a subsequent MRM (Match Keeping Assist) is triggered. Of course, in special circumstances, if the emergency lane change fails, such as when a vehicle suddenly appears in an adjacent lane, the lane change can be immediately aborted, and a combination of emergency braking and lane keeping can be triggered to minimize collision energy and maintain the safety of the vehicle. In short, regardless of whether obstacle avoidance is successful or not, the HAD system can reset the user's reaction time after an emergency operation. If it fails to take over after the timeout, it will execute an MRM (Match Keeping Assist) that matches the current operating environment. In this embodiment, lane keeping refers to controlling the vehicle to remain within the current lane.
[0042] In step 204, if the runtime of the HAD auxiliary control system is longer than the user's response time in the absence of a user takeover instruction, then the minimum risk strategy matched to the current operating environment is executed.
[0043] If the driver does not take over the vehicle within the aforementioned user response time, and the HAD (Hybrid Assist Control) system continues to operate beyond that time, a MRM (Mechanical Management Response) adapted to the current environment is triggered. This step compensates for the gap between the functional safety level of the auxiliary control system and the main control system by dynamically matching the MRM to the constraints of the current operating environment, ensuring vehicle driving safety even if the redundant system has limited capabilities.
[0044] The triggering conditions and judgment logic of the aforementioned user takeover command can be further refined by introducing a multimodal takeover signal source and verification rules to improve the reliability and response efficiency of driver intervention and reduce the probability of false triggering or missed detection. Specifically, this is divided into a torque signal continuously exceeding a threshold detected by the vehicle's steering wheel torque sensor and an emergency takeover trigger signal received by the vehicle's onboard human-machine interface. For the former, assuming the torque value applied by the driver to the steering wheel continuously exceeds a preset torque threshold, such as ≥2 N·m, and the duration is greater than the de-jitter cycle, such as 0.5 seconds, then the HAD auxiliary control system can determine that the driver intends to take over actively. For the latter, assuming the driver generates a signal by combining physical buttons with anti-mistouch design, voice commands, or touch screen controls, then the HAD auxiliary control system can also determine that the driver intends to take over actively. In summary, the HAD auxiliary control system 12 can respond to the user takeover command, allowing the vehicle to change lanes. The driver can directly control the vehicle's direction through the steering wheel, while the system maintains longitudinal control until complete takeover. It is worth mentioning that all the above takeover commands can be verified through multiple levels of checks, such as signal source authentication and timing consistency analysis. Alternatively, if two signals are triggered simultaneously, the HAD auxiliary control system can prioritize the emergency takeover signal and force the system into manual driving mode.
[0045] Meanwhile, upon receiving the indicated user takeover command, the HAD auxiliary control system will transfer vehicle control to the user and simultaneously display the triggering reason for the current control system switch via the central control screen, voice broadcast, and other means, so that the driver can understand the current situation as soon as possible after taking over the vehicle and take appropriate action.
[0046] Regarding the aforementioned minimum risk strategy, as a fallback strategy for the HAD auxiliary control system in case the user fails to take over the vehicle within the user's response time, it can be combined with scenario adaptability. The following multi-level collaborative strategy is defined to ensure safe state transfer within the current operating environment and the capabilities of the HAD auxiliary control system.
[0047] 1. Based on the deceleration strategy, the vehicle decelerates until it comes to a stop within the current lane. The HAD (Hyper-Assisted Drive) system can use the longitudinal control module to reduce speed in stages, maintaining continuous deceleration. If the current lane is a high-speed overtaking lane or a no-stopping zone, it can prioritize gradually shifting to the right lane.
[0048] 2. Identify and locate emergency stopping lanes or compliant shoulder areas, and perform path replanning for parallel parking. Based on pre-stored shoulder information in high-precision maps or real-time vehicle perception data (such as camera recognition of shoulder markings or radar detection of obstacles), the system can filter out the nearest and most spacious parking area. Specifically, if a partial path has already been generated before the HAD main control system malfunctions, the HAD auxiliary control system can directly call upon and downgrade its execution, for example, by reducing the trajectory tracking accuracy requirement; otherwise, a simplified parallel parking path can be generated, and strategies such as lateral control bandwidth limiting can be used to ensure the smoothness of the parallel parking process. In this embodiment, lateral control bandwidth limiting refers to controlling the vehicle's steering rate and adjusting the vehicle's smoothness by constraining the vehicle's maximum steering angle and maximum steering angular rate.
[0049] 3. Exchange cooperative parking protocols with surrounding traffic participants. The parking protocol includes the vehicle's position, movement status, and expected parking trajectory. The HAD (Hyper-Drive Assist) system can broadcast cooperative parking requests via an onboard communication unit supporting technologies such as C-V2X (Cellular Vehicle-to-Everything), including the vehicle's position, speed, target parking coordinates, and countdown timer, requesting adjacent vehicles to yield or synchronously reduce speed. If a confirmation response is received from surrounding vehicles, the vehicle can execute the aforementioned trajectory; if no response is received within the time limit, the system can degrade to an independent, conservative strategy, such as the first lane-only parking strategy.
[0050] 4. Send alarm information to the preset rescue platform. The alarm information includes at least the vehicle's location, fault code, and environmental information. The HAD auxiliary control system can send alarms in standard formats such as SAE J2735 to the cloud-based rescue platform, which include fault codes, location data, environmental risk levels, and vehicle status. Furthermore, based on guidance instructions from the platform (e.g., guidance instructions include the nearest rescue vehicle, recommended waiting location, etc., and are updated to the vehicle's infotainment system via Over-The-Air (OTA) technology), the HAD auxiliary control system optimizes the MRM.
[0051] 5. Activate vehicle warning devices to alert surrounding vehicles. The HAD auxiliary control system can simultaneously activate hazard lights, emergency lights, and the rear LED warning screen, and additionally activate laser projection at night to maximize visibility and collision warning.
[0052] The above strategies can be dynamically selected based on the actual situation. That is, based on environmental data such as lane type and traffic density and the health status shown by the HAD auxiliary control system (such as the health status including remaining perception capability), the optimal MRM combination is selected through a decision tree model to obtain a comprehensive MRM strategy similar to priority lane-keeping + warning on urban roads and priority deceleration + cooperative protocol on highways.
[0053] The following describes the flow of another risk management method based on autonomous driving, with reference to Figure 5. This method includes the following steps 502 to 510.
[0054] Step 502 includes HAD master control system anomaly detection and degradation triggering.
[0055] In one embodiment, assuming a vehicle is traveling at 60 km / h on an urban expressway, the HAD main control system meets full ASIL B standards. However, due to overheating of the computing unit, a degradation is triggered, switching to the HAD auxiliary control system. The HAD auxiliary control system's sensor configuration is 5R1V, belonging to ASIL B limited sensing. Specifically, when the HAD main control system's built-in temperature sensor detects that the computing unit temperature exceeds the limit, for example, >95°C, its own safety monitor determines it as an ASIL B level fault and sends a degradation request to the vehicle controller. Simultaneously, the HAD main control system freezes the current "maintain current speed of 60 km / h" control command, synchronizes high-precision map data and lane keeping status to the HAD auxiliary control system, and activates the fault warning light. In this embodiment, the lane keeping status may include information such as the vehicle's current lane on the map, the vehicle's position in the current lane (e.g., in the middle of the lane or near the edge of the lane), the distance the vehicle can still travel in the current lane, and whether the vehicle needs to change lanes ahead. However, this embodiment is not limited to these.
[0056] In step 504, control of the vehicle is transferred to the HAD (Hyper-Assisted Driving) system and lane change restrictions are activated.
[0057] In one embodiment, the HAD (Hyper-Assisted Driving) system takes over the vehicle based on a 5R1V sensor configuration (e.g., front / left front / right front / left rear / right rear radar + forward-facing camera), initiates a 10-second countdown for user reaction time, dynamically sets a steering wheel angle threshold, and generates a virtual lane boundary ±0.4 meters from the center of the current lane to prohibit lane changing operations.
[0058] In step 506, the HAD auxiliary control system determines whether a user takeover command has been detected.
[0059] In one embodiment, the HAD (Help-Assisted Driving) system can set a torque threshold of 2 N·m. If a continuous input torque exceeding the threshold is detected, such as the driver turning the steering wheel for more than 0.5 seconds, it can be determined that a takeover intention (i.e., a user takeover command) has been detected, and then step 508 is executed. If the runtime of the HAD system exceeds the aforementioned user reaction time, then step 510 is executed.
[0060] In step 508, the automatic driving system switches to manual driving mode.
[0061] In one embodiment, if a user takeover command is received within 10 seconds, the HAD (Hyper-Assisted Driving) system can gradually release lateral control authority while maintaining longitudinal control until the driver takes full control. Simultaneously, the central control screen displays "Control transferred, cause of failure: main control system overheating," and a voice prompt reminds the driver to take full control.
[0062] In step 510, the HAD auxiliary control system triggers the MRM.
[0063] In one embodiment, if no user takeover command is received within 10 seconds, an MRM combination is selected based on the urban road scenario, for example, with a speed of -2m / s. 2 After slowing to 20 km / h and coming to a stop, the electronic parking brake is activated, hazard lights are turned on, and fault codes and location data are sent to the cloud, awaiting assistance. Finally, the auxiliary control system enters a low-power mode, maintaining only the communication module online, awaiting external commands.
[0064] Figure 6 is a schematic structural diagram of an electronic device according to an exemplary embodiment of this application. Referring to Figure 6, at the hardware level, the electronic device includes at least one processor 602, an internal bus 610, a network interface 604, a memory 606, and at least one non-volatile memory 608, and may also include other necessary hardware. At least one processor reads a corresponding computer program from at least one non-volatile memory into memory and then runs it, forming a risk code detection device at the logical level. Of course, besides software implementation, this application embodiment does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.
[0065] Figure 7 is a block diagram of a risk handling device based on autonomous driving according to an embodiment of this application. Referring to Figure 7, this device can be applied to the electronic device shown in Figure 6 to implement the technical solution according to the embodiment of this application. The device is applied to a vehicle, which is equipped with a High Level Automated Driving (HAD) master control system and a HAD auxiliary control system for controlling the vehicle's autonomous driving. The functional safety level of the HAD master control system is higher than that of the HAD auxiliary control system. The device includes a vehicle lane change prevention unit 702 and a minimum risk strategy execution unit 704.
[0066] The vehicle lane change prevention unit 702 is configured to prevent the vehicle from changing lanes within the user reaction time after the current control system controlling the vehicle's autonomous driving switches from the HAD master control system to the HAD auxiliary control system, when it is determined that the current operating environment of the vehicle is in the design operating domain of the L3 level conditional automated driving system.
[0067] The minimum risk strategy execution unit 704 is configured to execute the minimum risk strategy that matches the current operating environment if the runtime of the HAD auxiliary control system is longer than the user's response time when no user takeover instruction is received.
[0068] In some embodiments, the vehicle lane change prevention unit 702 is specifically configured to: when it is determined that the working state of the HAD main control system is abnormal, the current control system controlling the vehicle to perform autonomous driving is switched from the HAD main control system to the HAD auxiliary control system.
[0069] In some embodiments, the design operating domain includes any of the following constraints: the vehicle is driving in a low-risk urban area that meets the low-risk conditions; the vehicle's speed is lower than the safe speed threshold corresponding to the current road scenario type; the key driving scenario locations in the vehicle's navigation map meet the first functional safety level; and the vehicle's traffic light detection capability meets the second functional safety level.
[0070] In some embodiments, the vehicle lane change prevention unit 702 is specifically configured to: dynamically set a steering wheel angle limit threshold based on the current vehicle speed and lane curvature; and / or determine a lateral acceleration safety threshold for the vehicle based on the current vehicle speed; and / or generate a virtual lane boundary for the current lane so that the vehicle can perform a boundary correction operation when it deviates from the current lane.
[0071] In some embodiments, the device further includes a temporary lane-changing unit.
[0072] The temporary lane change unit is configured to temporarily allow a vehicle to change lanes to avoid an emergency obstacle if an emergency obstacle is detected in the vehicle's path when the vehicle is prevented from changing lanes.
[0073] In some embodiments, the user takeover command includes: a torque signal detected by the vehicle's steering wheel torque sensor that continuously exceeds a threshold; and / or an emergency takeover trigger signal received by the vehicle's in-vehicle human-machine interface device.
[0074] In some embodiments, the minimum risk strategy includes any of the following: decelerating to a stop within the current lane based on a deceleration strategy; identifying and locating an emergency stopping lane or compliant shoulder area, and performing route replanning to pull over; exchanging a cooperative parking protocol with nearby traffic participants, the parking protocol including the vehicle's location, motion status, and expected parking trajectory; sending an alarm message to a pre-set emergency response platform, the alarm message including the vehicle's location, fault code, and environmental information; and activating a vehicle warning device to alert nearby traffic participants.
[0075] In some embodiments, the device further includes a user takeover unit.
[0076] The user takeover unit is configured to transfer control of the vehicle to the user upon receiving a user takeover command, and to display to the user the triggering reason for the current control system switchover.
[0077] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.
[0078] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units or modules described as separate components may or may not be physically separate. The components shown as units or modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules or units can be selected to achieve the purpose of the solution in the embodiments of this application, depending on actual needs. Those skilled in the art can understand and implement this without creative effort.
[0079] Based on the same concept as the methods described above, this application also provides an electronic device, including: at least one processor; at least one memory for storing processor-executable instructions; wherein the at least one processor implements the method as described in any of the above embodiments by running the executable instructions.
[0080] Based on the same concept as the above methods, this application also provides a non-transitory computer-readable storage medium storing computer-executable instructions thereon, which, when executed by at least one processor, implement the method described in any of the above embodiments.
[0081] Based on the same concept as the methods described above, this application also provides a computer program product, including a computer program / instructions that, when executed by at least one processor, implement the methods described in any of the above embodiments.
[0082] The vehicle in this embodiment can be used to control the high-level autonomous driving HAD master control system and HAD auxiliary control system for vehicle autonomous driving. When it is determined that the current operating environment of the vehicle is in the design operating domain of the L3 conditional autonomous driving system, after the current control system controlling the vehicle's autonomous driving is switched from the HAD master control system to the HAD auxiliary control system, the vehicle can be prevented from changing lanes within the user reaction time after the switch. At the same time, if the vehicle does not receive a user takeover command within the user reaction time and the runtime of the HAD auxiliary control system is longer than the user reaction time, then the minimum risk strategy matched to the current operating environment can be executed. Because the functional safety level of the HAD master control system is higher than that of the HAD auxiliary control system, the HAD auxiliary control system can simplify redundant design and reduce costs compared to the HAD master control system. Simultaneously, when the vehicle's current control system switches to the HAD auxiliary control system, preventing the vehicle from changing lanes within the user's reaction time provides the user with sufficient preparation time to understand the situation and take over the vehicle. This also avoids the additional risks caused by the vehicle arbitrarily changing lanes based on the less safe HAD auxiliary control system after the user has reacted. Even if the user does not react in time, the vehicle can execute the minimum risk strategy matched to the current operating environment, thereby maximizing vehicle safety. In other words, this application embodiment establishes a comprehensive risk handling mechanism for the HAD master control system and HAD auxiliary control system under L3 conditional automated driving systems, thus balancing the advantages of low cost and high safety.
[0083] The embodiments of the subject matter and functional operation described in this application can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. The embodiments described in this application can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing device or for controlling the operation of a data processing device. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing device. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.
[0084] The processing and logic flow described in this application can be executed by one or more programmable computers that execute one or more computer programs, such that the one or more programmable computers perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by special-purpose logic circuitry (e.g., FPGA (Field-Programmable Gate Array) or ASIC (Application-Specific Integrated Circuit)), and the device can also be implemented as special-purpose logic circuitry.
[0085] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.
[0086] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.
[0087] While the embodiments of this application contain numerous specific implementation details, these should not be construed as limiting the scope of this application or the scope of the claims, but are primarily used to describe the features of specific embodiments. Certain features described in multiple embodiments of this application may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation of a sub-combination.
[0088] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
[0089] Therefore, specific embodiments of the subject matter have been described. Furthermore, the processes depicted in the figures are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.
[0090] The above description is merely an exemplary embodiment of this specification and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the scope of protection of this application.
Claims
1. A risk management method based on autonomous driving, applied to a vehicle, wherein the vehicle is equipped with a High-Level Automated Driving (HAD) master control system and a HAD auxiliary control system configured to control the vehicle to perform autonomous driving, wherein the functional safety level of the HAD master control system is higher than the functional safety level of the HAD auxiliary control system; the method includes: If the current operating environment of the vehicle is determined to be within the design operating domain of the L3 conditional automated driving system, the vehicle shall be prevented from changing lanes within the user reaction time after the current control system controlling the vehicle to perform automated driving is switched from the HAD master control system to the HAD auxiliary control system. If the runtime of the HAD auxiliary control system exceeds the user's response time in the absence of a user takeover instruction, the minimum risk strategy matching the current operating environment will be executed.
2. The method according to claim 1, wherein, The current control system controlling the vehicle to perform autonomous driving is switched from the HAD main control system to the HAD auxiliary control system, including: If it is determined that the working state of the HAD main control system is abnormal, the current control system controlling the vehicle to perform autonomous driving will be switched from the HAD main control system to the HAD auxiliary control system.
3. The method according to claim 1 or 2, wherein, The design runtime domain includes any of the following constraints: The vehicle was traveling in a low-risk urban area that met the low-risk criteria. The vehicle's speed is lower than the safe speed threshold corresponding to the current road scenario type; The key driving scenario locations in the vehicle's navigation map meet the first functional safety level; The vehicle's signal light detection capability meets the second functional safety level.
4. The method according to any one of claims 1 to 3, wherein, Preventing the vehicle from changing lanes includes: Dynamically set the steering wheel angle limit threshold based on the current vehicle speed and lane curvature; and / or, Determine the lateral acceleration safety threshold of the vehicle based on the current vehicle speed; and / or, A virtual lane boundary is generated for the current lane, so that the vehicle can perform a lane departure correction operation if it deviates from the current lane.
5. The method according to any one of claims 1 to 4, further comprising: If the vehicle is prevented from changing lanes, but an emergency obstacle avoidance target is determined to exist in the vehicle's travel path, the vehicle is temporarily permitted to change lanes to avoid the emergency obstacle avoidance target.
6. The method according to claim 5, further comprising: If the vehicle is temporarily allowed to change lanes and there is no emergency obstacle to avoid in the vehicle's path, the vehicle will be prevented from changing lanes again. If the vehicle is temporarily permitted to change lanes but the lane change fails, control the vehicle to brake urgently and maintain lane position.
7. The method according to any one of claims 1 to 6, wherein, The user takeover instructions include: The vehicle's steering wheel torque sensor detects a torque signal that continuously exceeds a threshold; and / or, The vehicle's onboard human-machine interface receives an emergency takeover trigger signal.
8. The method according to any one of claims 1 to 7, wherein, The minimum risk strategy includes any of the following: Based on the deceleration strategy, slow down until stop within the current lane; Identify and locate emergency stopping lanes or compliant shoulder areas, and perform route replanning to allow parking to be completed at the side of the road; Exchange collaborative parking protocols with surrounding traffic participants, the parking protocols including the vehicle's location, movement status and expected parking trajectory; Send alarm information to a preset rescue platform. The alarm information includes the vehicle's location, fault code, and environmental information. Activate the vehicle warning device to alert nearby road users.
9. The method according to any one of claims 1 to 8, further comprising: Upon receiving the user takeover instruction, control of the vehicle is transferred to the user, and the user is shown the reason for the current control system switchover.
10. A risk management device based on autonomous driving, applied to a vehicle, the vehicle being equipped with a High-Level Automated Driving (HAD) master control system and a HAD auxiliary control system configured to control the vehicle to perform autonomous driving, wherein the functional safety level of the HAD master control system is higher than the functional safety level of the HAD auxiliary control system; the device comprises: The vehicle lane change prevention unit is configured to prevent the vehicle from changing lanes within the user reaction time after the current control system controlling the vehicle to perform autonomous driving switches from the HAD master control system to the HAD auxiliary control system, when it is determined that the current operating environment of the vehicle is in the design operating domain of the L3 conditional automated driving system. The minimum risk strategy execution unit is configured to execute a minimum risk strategy that matches the current operating environment if the runtime of the HAD auxiliary control system exceeds the user's response time when no user takeover instruction is received.
11. An electronic device, comprising: At least one processor; At least one memory configured to store processor-executable instructions, wherein the at least one memory and the at least one processor are communicatively connected to each other; The at least one processor implements the risk management method based on autonomous driving as described in any one of claims 1 to 9 by running the executable instructions.
12. A non-transitory computer-readable storage medium, wherein, The non-transitory computer-readable storage medium stores a computer program, which, when executed by at least one processor, implements the risk management method based on autonomous driving as described in any one of claims 1 to 9.
13. A computer program product comprising a computer program that, when executed by at least one processor, implements the risk management method based on autonomous driving as described in any one of claims 1 to 9.
14. A vehicle comprising: The risk management device based on autonomous driving according to claim 10, or The electronic device according to claim 11, or The non-transitory computer-readable storage medium according to claim 12, or The computer program product according to claim 13, or At least one processor; and at least one memory communicatively connected to the at least one processor, the at least one memory storing computer-executable instructions, the at least one processor executing the computer-executable instructions to perform the risk management method based on autonomous driving as described in any one of claims 1 to 9.
