Node starting control method and device of automatic driving vehicle, electronic equipment and computer program product

Abstract

The invention discloses a node starting control method and device of an automatic driving vehicle, electronic equipment and a computer program product. The method comprises the steps that running state data and external environment data of the automatic driving vehicle are monitored; according to the operation state data and the external environment data, determining an abnormal scene where the automatic driving vehicle is located at present, and performing scene evaluation to obtain an abnormal scene evaluation result; determining a current driving strategy of the automatic driving vehicle according to the abnormal scene evaluation result; and determining a current node starting strategy according to the current driving strategy and the abnormal scene evaluation result, and controlling the node starting of the automatic driving vehicle according to the current node starting strategy. According to the method, the current abnormal scene of the vehicle can be accurately identified in real time and quantitative evaluation of the scene can be carried out, so that the driving strategy is dynamically adjusted, the optimal node starting strategy is determined, the adaptability and the response speed of the automatic driving vehicle in a complex and changeable environment are improved, and the safety and the stability of the system are enhanced.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a node startup control method, device, electronic equipment, and computer program product for an autonomous driving vehicle. Background Art

[0002] With the rapid development and widespread application of autonomous driving technology, autonomous vehicles are gradually becoming an important part of the future transportation system. However, autonomous vehicles face many technical challenges and safety risks in the complex and changing actual operating environment, which are directly related to the normal operation of the vehicle and the safety of life and property of passengers.

[0003] Sensors are the "eyes" and "ears" of the autonomous driving system, and their performance stability and reliability are crucial. However, in actual applications, sensors may fail or have limited performance due to various reasons, such as bad weather, equipment aging, or physical damage. At this time, if the autonomous driving system still uses a fixed node startup strategy, it may not be able to quickly and effectively switch to backup sensors or adjust the corresponding algorithms, resulting in a decrease in the system's perception ability, affecting the vehicle's driving safety and decision-making accuracy.

[0004] On the other hand, the autonomous driving system needs to process a large amount of environmental data and make real-time driving decisions based on this data. However, delays in data processing and decision-making, especially in emergency situations, may cause the system to fail to respond in a timely manner, thereby increasing the risk of traffic accidents. Fixed node startup strategies often make it difficult to dynamically adjust data processing capabilities and decision-making speeds according to real-time conditions to meet safety requirements in different scenarios.

[0005] In addition, with the continuous increase in the functions and complexity of autonomous driving systems, the problem of system overload has become increasingly prominent. In the case of limited system resources, overload may limit the functions of autonomous driving, or even cause system crashes, posing a serious threat to driving safety. The existing fixed node startup strategy lacks a flexible adjustment mechanism when facing system overload, making it difficult to ensure the stable operation of the system.

[0006] Network security is also one of the challenges that autonomous driving systems cannot ignore. As the degree of vehicle networking increases, autonomous driving systems face the risk of various attacks and unauthorized access from cyberspace. If the system lacks effective network security protection measures and flexible node startup strategies, once attacked, it may lead to serious consequences such as system paralysis and data leakage, posing a great threat to the safety of vehicles and passengers.

[0007] In summary, the existing autonomous driving systems have many deficiencies in node startup strategies, making it difficult to cope with the complex and changing actual operating environment and various potential technical challenges and safety risks. Therefore, it is of great practical significance and urgent need to develop a method that can intelligently adjust the node startup strategy according to the current scenario to ensure that the autonomous driving system maintains optimal performance and safety when facing different challenges. Summary of the invention

[0008] The embodiments of the present application provide a node startup control method, device, electronic device, and computer program product for an autonomous driving vehicle to achieve dynamic adjustment of node startup strategies under different abnormal scenarios, ensuring that the autonomous driving system can maintain optimal performance and safety in various scenarios.

[0009] The present application embodiment adopts the following technical solutions:

[0010] In a first aspect, an embodiment of the present application provides a node startup control method for an autonomous driving vehicle, wherein the node startup control method for an autonomous driving vehicle includes:

[0011] Monitor the operating status data and external environment data of the autonomous driving vehicle;

[0012] Determine the abnormal scene in which the autonomous driving vehicle is currently located according to the operating status data and the external environment data and perform scene evaluation to obtain an abnormal scene evaluation result;

[0013] Determining a current driving strategy of the autonomous driving vehicle according to the abnormal scenario evaluation result;

[0014] Determine the current node startup strategy of the autonomous driving vehicle according to the current driving strategy of the autonomous driving vehicle and the abnormal scenario evaluation result, and control the node startup of the autonomous driving vehicle according to the current node startup strategy.

[0015] Optionally, determining the abnormal scene in which the autonomous driving vehicle is currently located according to the operating status data and the external environment data and performing scene evaluation to obtain the abnormal scene evaluation result includes:

[0016] Performing scene recognition according to the operating status data and the external environment data to obtain an abnormal scene in which the autonomous driving vehicle is currently located;

[0017] A preset evaluation strategy is used to perform a scene evaluation on the abnormal scene in which the autonomous driving vehicle is currently located to obtain an abnormal scene evaluation result, wherein the abnormal scene evaluation result includes at least one of an impact evaluation result, a processing priority evaluation result, and a risk assessment result.

[0018] Optionally, determining a current driving strategy of the autonomous driving vehicle according to the abnormal scenario evaluation result includes:

[0019] Calculating a comprehensive abnormal scenario score according to the abnormal scenario assessment result, wherein the comprehensive abnormal scenario score is used to characterize the degree of influence of the abnormal scenario currently in which the autonomous driving vehicle is located on the autonomous driving function;

[0020] The current driving strategy of the autonomous driving vehicle is determined according to the comprehensive score of the abnormal scenario, and the current driving strategy is at least one type of a manual driving strategy, an assisted driving strategy or an autonomous driving strategy.

[0021] Optionally, determining a current node startup strategy of the autonomous driving vehicle according to the current driving strategy of the autonomous driving vehicle and the abnormal scenario evaluation result includes:

[0022] When the current driving strategy is a manual driving strategy, shut down the node associated with the automatic driving function;

[0023] When the current driving strategy is an assisted driving strategy or an autonomous driving strategy, the current node startup strategy of the autonomous driving vehicle is determined according to the type of abnormal scene in which the autonomous driving vehicle is currently located and the evaluation result of the abnormal scene.

[0024] Optionally, determining a current node startup strategy of the autonomous driving vehicle according to the type of abnormal scene in which the autonomous driving vehicle is currently located and the abnormal scene evaluation result includes:

[0025] In the case where the abnormal scenario currently in which the autonomous driving vehicle is located includes a sensor failure or a restricted scenario, determining, according to the abnormal scenario evaluation result, that the current node startup strategy includes at least one of starting a redundant sensor node and adjusting a sensor association algorithm;

[0026] In the case where the abnormal scenario currently in which the autonomous driving vehicle is located includes a data processing and / or decision delay scenario, determining the current node startup strategy according to the abnormal scenario evaluation result includes at least one of adjusting the order of data processing flow nodes and enabling a fast decision algorithm;

[0027] In a case where the abnormal scenario currently in which the autonomous driving vehicle is located includes a system overload scenario, determining, according to the current driving strategy and the abnormal scenario evaluation result, that the current node startup strategy includes at least one of allocating additional resources to critical nodes, suspending the operation of non-critical nodes, or reducing the resources of non-critical nodes;

[0028] In the case where the abnormal scenario currently in which the autonomous driving vehicle is located includes a scenario of network security problems, the current node startup strategy is determined according to the current driving strategy and the abnormal scenario evaluation result, including starting a network security protocol, isolating nodes affected by network security, and starting at least one of a security protection enhancement program.

[0029] Optionally, controlling the node startup of the autonomous driving vehicle according to the current node startup strategy includes:

[0030] Determine the nodes to be started in the autonomous driving vehicle according to the current node startup strategy and adjust the startup order of each node to be started in the autonomous driving vehicle;

[0031] Allocate corresponding resources to each node to be started according to the current node startup strategy;

[0032] Based on the adjusted startup sequence of each node to be started and the allocated resources, each node is started in sequence.

[0033] Optionally, controlling the node startup of the autonomous driving vehicle according to the current node startup strategy further includes:

[0034] Configuring each node to be started according to the current node startup strategy;

[0035] Based on the adjusted startup sequence, allocated resources, and configuration of each node to be started, each node to be started is started in sequence.

[0036] In a second aspect, an embodiment of the present application further provides a node startup control device for an autonomous driving vehicle, wherein the node startup control device for an autonomous driving vehicle comprises:

[0037] A monitoring unit, used to monitor the operating status data and external environment data of the autonomous driving vehicle;

[0038] An evaluation unit, configured to determine the abnormal scene in which the autonomous driving vehicle is currently located according to the operating state data and the external environment data and perform scene evaluation to obtain an abnormal scene evaluation result;

[0039] a determination unit, configured to determine a current driving strategy of the autonomous driving vehicle according to the abnormal scenario evaluation result;

[0040] A startup control unit is used to determine the current node startup strategy of the autonomous driving vehicle based on the current driving strategy of the autonomous driving vehicle and the abnormal scenario evaluation result, and control the node startup of the autonomous driving vehicle according to the current node startup strategy.

[0041] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0042] A processor; and a memory arranged to store computer executable instructions, which, when executed, cause the processor to execute any of the aforementioned node startup control methods for the autonomous driving vehicle.

[0043] In a fourth aspect, an embodiment of the present application further provides a computer program product, comprising a computer program or instructions, which, when executed by a processor, implements any of the aforementioned node startup control methods for the autonomous driving vehicle.

[0044] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the node startup control method of the autonomous driving vehicle in the embodiment of the present application first monitors the operating status data and external environment data of the autonomous driving vehicle; then determines the abnormal scene in which the autonomous driving vehicle is currently located according to the operating status data and the external environment data and performs scene evaluation to obtain the abnormal scene evaluation result; then determines the current driving strategy of the autonomous driving vehicle according to the abnormal scene evaluation result; finally determines the current node startup strategy of the autonomous driving vehicle according to the current driving strategy of the autonomous driving vehicle and the abnormal scene evaluation result, and controls the node startup control of the autonomous driving vehicle according to the current node startup strategy. The node startup control method of the autonomous driving vehicle in the embodiment of the present application can accurately identify the abnormal scene in which the autonomous driving vehicle is currently located and conduct a scientific and comprehensive scene evaluation by monitoring the operating status and external environment of the autonomous driving vehicle in real time. Based on the evaluation results, the autonomous driving strategy can be intelligently adjusted, and then the optimal node startup strategy can be determined to achieve refined and intelligent management of the nodes. This not only significantly improves the adaptability and response speed of the autonomous driving vehicle in complex and changeable environments, but also effectively enhances the safety and stability of the system. By flexibly adjusting the node startup strategy, it is ensured that the autonomous driving vehicle can maintain the best operating performance and passenger safety when facing various abnormal scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0046] Figure 1 A schematic diagram of a flow chart of a node startup control method for an autonomous driving vehicle in an embodiment of the present application;

[0047] Figure 2 This is a structural schematic diagram of a node startup control device for an autonomous driving vehicle in an embodiment of the present application;

[0048] Figure 3 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0050] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0051] The present application embodiment provides a node startup control method for an autonomous driving vehicle, such as Figure 1 As shown, a schematic flow chart of a node startup control method of an autonomous driving vehicle in an embodiment of the present application is provided, and the node startup control method of the autonomous driving vehicle at least includes the following steps S110 to S140:

[0052] Step S110, monitoring the operating status data and external environment data of the autonomous driving vehicle.

[0053] During the node startup control process of the autonomous driving vehicle in the embodiment of the present application, it is necessary to acquire and monitor the operating status data and external environment data of the autonomous driving vehicle in real time, which mainly includes continuous tracking and recording of the operating status of various systems and components within the autonomous driving vehicle.

[0054] Specifically, the operating status data covers multiple key aspects of the vehicle, including but not limited to: power system status: monitoring the operating status of power sources such as engines, motors, and batteries, including parameters such as power output, energy consumption, and temperature; braking system status: real-time detection of brake pad wear, brake fluid level, brake pressure, etc.; steering system status: monitoring steering angle, steering torque, steering motor status, etc.; sensor data: including surrounding environment information provided by radar, laser radar (LiDAR), cameras, ultrasonic sensors, etc.; vehicle control status: such as vehicle speed, acceleration, steering angle, gear, etc., reflecting the current motion state of the vehicle.

[0055] External environmental data mainly focuses on the real-time conditions of the vehicle's surroundings, including but not limited to: road information: identification of road types (such as highways, urban roads, rural roads), lane lines, traffic signs, traffic signals, etc.; traffic participant information: detection and identification of surrounding vehicles, pedestrians, bicycles and other dynamic obstacles, including their speed, direction, distance, etc.; weather and road conditions: monitoring current weather conditions (such as rain, snow, fog, light intensity, etc.) and road conditions (such as slippery, icy, potholes, etc.); obstacles and hazards: identification and warning of potential hazards such as road construction, accident scenes, and suddenly appearing objects to ensure that the vehicle can avoid them in time.

[0056] Of course, it should be noted that the specific dimensions of operating status data and external environment data to be monitored can be flexibly set by technicians in this field according to actual needs, and no specific limitation is made here.

[0057] Step S120, determining the abnormal scene in which the autonomous driving vehicle is currently located based on the operating status data and the external environment data and performing a scene evaluation to obtain an abnormal scene evaluation result.

[0058] Based on the real-time operating status data and external environment data obtained in the above steps, the abnormal scenario in which the autonomous driving vehicle is currently located is further analyzed and a scenario assessment is performed. This process aims to identify potential risks or challenges that the vehicle may currently face so that appropriate countermeasures can be taken in a timely manner.

[0059] Specifically, the acquired operating status data and external environment data can be preprocessed to remove noise, fill missing values, and convert them into a format that can be used for analysis. Then, key features are extracted from the preprocessed data, which can reflect the operating status of the vehicle and changes in the external environment. Features may include vehicle speed, acceleration, steering angle, distance to surrounding obstacles, weather conditions, etc. The extracted features are matched with a predefined abnormal scenario library. The abnormal scenario library may contain a variety of common dangerous situations, such as sensor failure, data processing and decision delays, system overload, network security, etc. By comparing the similarity between features, it can be determined whether the vehicle is currently in one or some abnormal scenarios.

[0060] Of course, in addition to the above matching method, deep learning can also be used to identify abnormal scenes. The abnormal scene recognition model can be trained in advance, and the operating status data and external environment data can be used as input data of the abnormal scene recognition model to output the current abnormal scene.

[0061] After determining that the vehicle is in one or more abnormal scenarios, a comprehensive and scientific assessment of the abnormal scenarios can be conducted to generate abnormal scenario assessment results, which may include, for example, an assessment of the scope of impact, an assessment of the degree of impact, and a risk assessment, etc., providing an important basis for subsequent adjustments to autonomous driving strategies and formulation of node startup strategies.

[0062] Step S130, determining the current driving strategy of the autonomous driving vehicle according to the abnormal scenario evaluation result.

[0063] Based on the above abnormal scenario evaluation results, the most appropriate driving strategy is dynamically selected to ensure the safe driving of the autonomous driving vehicle in abnormal scenarios. The driving strategies here can be divided into manual driving strategies, assisted driving strategies, autonomous driving strategies, etc. For example, if the autonomous driving function of the current autonomous driving vehicle is considered to have a serious fault according to the abnormal scenario evaluation results, which seriously affects the safe driving of the vehicle, you can choose to switch to the manual driving strategy to ensure safety. If the autonomous driving function has a minor fault or abnormality, you can choose an assisted driving strategy to ensure driving safety while reducing the burden on the driver. If there are only minor abnormalities at some non-critical nodes or the autonomous driving functions are normal, you can choose an autonomous driving strategy to achieve a more efficient and comfortable driving experience.

[0064] Of course, it should be noted that the above-mentioned division of driving strategies is only a rough division method. The specific driving strategies and the specific driving parameters under different strategies can be flexibly set by technical personnel in this field according to actual needs, and no specific limitation is made here.

[0065] Step S140, determining the current node startup strategy of the autonomous driving vehicle according to the current driving strategy of the autonomous driving vehicle and the abnormal scenario evaluation result, and controlling the node startup of the autonomous driving vehicle according to the current node startup strategy.

[0066] Different driving strategies have different requirements for vehicle operation, which will affect the startup and management of nodes in the autonomous driving system. The abnormal scenario assessment results reflect the safety, complexity and challenge level of the current driving environment to the autonomous driving system, and will also affect the vehicle's choice of node startup strategy. Therefore, the embodiment of the present application needs to dynamically determine the current node startup strategy of the autonomous driving vehicle in combination with the current driving strategy of the autonomous driving vehicle and the abnormal scenario assessment results. The node startup strategy specifically refers to deciding which nodes need to be started, which nodes can enter sleep, low power consumption state or shut down, as well as the startup order and priority of the nodes. According to the determined current node startup strategy, corresponding instructions can be sent to each node to control the startup, sleep, low power consumption state or shutdown of each node.

[0067] The node startup control method of the autonomous driving vehicle of the embodiment of the present application can accurately identify the abnormal scene in which the autonomous driving vehicle is currently located and conduct a scientific and comprehensive scene evaluation by monitoring the operating status and external environment of the autonomous driving vehicle in real time. Based on the evaluation results, the autonomous driving strategy can be intelligently adjusted to determine the optimal node startup strategy, thereby achieving refined and intelligent management of the nodes. This not only significantly improves the adaptability and response speed of the autonomous driving vehicle in a complex and changing environment, but also effectively enhances the safety and stability of the system. By flexibly adjusting the node startup strategy, it is ensured that the autonomous driving vehicle can maintain the best operating performance and passenger safety when facing various abnormal scenarios.

[0068] In some embodiments of the present application, determining the abnormal scene in which the autonomous driving vehicle is currently located based on the operating status data and the external environment data and performing a scene evaluation to obtain an abnormal scene evaluation result includes: performing scene recognition based on the operating status data and the external environment data to obtain the abnormal scene in which the autonomous driving vehicle is currently located; performing a scene evaluation on the abnormal scene in which the autonomous driving vehicle is currently located using a preset evaluation strategy to obtain an abnormal scene evaluation result, and the abnormal scene evaluation result includes at least one of an impact assessment result, a processing priority assessment result, and a risk assessment result.

[0069] As mentioned above, based on the real-time operating status data and external environment data, the abnormal scenario in which the autonomous driving vehicle is currently located can be identified by using abnormal scenario library matching or deep learning models, and then certain evaluation strategies can be adopted to evaluate these abnormal scenarios. The results of the abnormal scenario evaluation will serve as the basis for selecting the corresponding node startup strategy.

[0070] The preset evaluation strategy of the embodiment of the present application can be regarded as a process of quantitatively analyzing the identified abnormal scenarios, the purpose of which is to determine the specific degree of impact of these abnormal scenarios on the operation of the autonomous driving system. Specifically, it may include the following aspects:

[0071] 1) Impact analysis: Evaluate the specific impact of each abnormal scenario on the performance and safety of the autonomous driving system, such as sensor failure may lead to reduced perception capabilities, and data processing delays may affect the timeliness of decision-making;

[0072] 2) Priority sorting: Sort abnormal scenarios according to their impact and urgency, and determine the abnormal scenarios that need to be handled first;

[0073] 3) Risk assessment: Assess the risks that each abnormal scenario may bring. For example, system overload may limit the autonomous driving function and increase the risk of accidents.

[0074] In some embodiments of the present application, determining the current driving strategy of the autonomous driving vehicle based on the abnormal scenario evaluation results includes: calculating an abnormal scenario comprehensive score based on the abnormal scenario evaluation results, the abnormal scenario comprehensive score being used to characterize the degree of influence of the abnormal scenario in which the autonomous driving vehicle is currently located on the autonomous driving function; determining the current driving strategy of the autonomous driving vehicle based on the abnormal scenario comprehensive score, the current driving strategy being at least one type of manual driving strategy, assisted driving strategy or autonomous driving strategy.

[0075] In order to further quantify the impact of abnormal scenario assessment results on autonomous driving vehicles, the embodiment of the present application can design a quantitative comprehensive scoring system for abnormal scenario assessment results, and the scoring system can include multiple scoring dimensions, such as the impact scoring dimension of abnormal scenarios and the risk scoring dimension, etc. Each scoring dimension can be set with one or more specific scoring indicators, for example, the impact score may include the degree of reduction in vehicle speed, the degree of reduction in passenger comfort, etc., and the risk score may include the probability of an accident, the severity of a potential accident, etc.

[0076] In the above-mentioned scoring system, different scoring dimensions and indicators can be assigned different weights. The allocation of these weights can be set based on expert experience, historical data analysis or machine learning algorithms. The allocation of weights is intended to ensure that the scoring results can accurately reflect the actual extent of the impact of abnormal scenarios on autonomous driving functions.

[0077] Based on the abnormal scenario assessment results, the scores of each scoring dimension and indicator can be calculated, and then these scores are weighted and summed according to the weight distribution to obtain the comprehensive score of these abnormal scenarios. The lower the comprehensive score, the greater the impact of the abnormal scenario on the autonomous driving vehicle and the greater the potential risk.

[0078] For example, assuming that the comprehensive score of an autonomous driving vehicle under ideal conditions is 100 points, if it is identified that abnormal scenarios such as sensor failure and data processing delay exist, the evaluation results of abnormal scenarios such as sensor failure and data processing delay can be quantified and scored separately, and the final calculated comprehensive score is 85 points.

[0079] The embodiments of the present application may pre-set a series of scoring thresholds to distinguish abnormal scenarios of different severity, and compare the comprehensive scores of abnormal scenarios with preset scoring thresholds to determine the current driving strategy that the autonomous driving vehicle should adopt. For example, whether to adopt a manual driving strategy, an assisted driving strategy, or an autonomous driving strategy. When the score is very low, it means that the abnormal scenario has a great impact on the autonomous driving function, and the driver may be required to take over the control of the vehicle and perform manual driving. When the score is moderate, it can be switched to assisted driving mode to provide a certain degree of assistance to the driver, but the driver is still required to maintain monitoring and control of the vehicle. When the score is high, it means that the abnormal scenario has little impact on the autonomous driving function, and the autonomous driving mode can continue to be maintained, but the level or parameters of autonomous driving may be adjusted to adapt to the current environment.

[0080] The embodiment of the present application designs a reasonable scoring system and sets scoring thresholds to determine the current driving strategy to be adopted based on the comprehensive score of the abnormal scenario, thereby ensuring that the vehicle can make the most appropriate decision when facing different abnormal scenarios, thereby ensuring driving safety and passenger comfort experience.

[0081] In some embodiments of the present application, determining the current node startup strategy of the autonomous driving vehicle based on the current driving strategy of the autonomous driving vehicle and the abnormal scenario evaluation results includes: when the current driving strategy is a manual driving strategy, shutting down the nodes associated with the autonomous driving function; when the current driving strategy is an assisted driving strategy or an autonomous driving strategy, determining the current node startup strategy of the autonomous driving vehicle based on the type of abnormal scenario in which the autonomous driving vehicle is currently located and the abnormal scenario evaluation results.

[0082] If the current driving strategy is a manual driving strategy, it means that the driver needs to fully control the vehicle. In this case, for safety reasons, all nodes or main nodes and systems associated with the autonomous driving function can be turned off to avoid conflicts or interference between the autonomous driving system and the driver's operations and ensure driving safety.

[0083] If the current driving strategy is an assisted driving strategy or a fully autonomous driving strategy, it means that the vehicle is at least autonomously controlled to a certain extent. In this case, the specific node startup strategy can be further determined based on the type of abnormal scenario the autonomous driving vehicle is currently in and the abnormal scenario evaluation results, including deciding which nodes related to the autonomous driving function need to be started, which nodes need to remain closed or adjust their working mode to best respond to the current abnormal scenario.

[0084] In some embodiments of the present application, the determining of the current node startup strategy of the autonomous driving vehicle according to the type of abnormal scenario in which the autonomous driving vehicle is currently located and the abnormal scenario evaluation result includes: when the abnormal scenario in which the autonomous driving vehicle is currently located includes a sensor failure or limitation scenario, determining the current node startup strategy according to the abnormal scenario evaluation result includes starting a redundant sensor node and adjusting a sensor association algorithm; when the abnormal scenario in which the autonomous driving vehicle is currently located includes a data processing and / or decision delay scenario, determining the current node startup strategy according to the abnormal scenario evaluation result includes adjusting the order of data processing flow nodes and enabling a fast decision algorithm; when the abnormal scenario in which the autonomous driving vehicle is currently located includes a system overload scenario, determining the current node startup strategy according to the current driving strategy and the abnormal scenario evaluation result includes allocating additional resources to critical nodes, suspending the work of non-critical nodes, or reducing the resources of non-critical nodes; when the abnormal scenario in which the autonomous driving vehicle is currently located includes a network security problem scenario, determining the current node startup strategy according to the current driving strategy and the abnormal scenario evaluation result includes starting a network security protocol, isolating nodes affected by network security, and starting a security protection enhancement program.

[0085] When an autonomous vehicle encounters a sensor failure or certain restricted scenarios (such as a sensor being blocked, environmental factors causing sensor performance degradation, etc.), based on the evaluation results of the abnormal scenario, it can choose to start a redundant sensor node (i.e., backup sensor) to ensure data continuity and accuracy. At the same time, the algorithm associated with the sensor can also be adjusted to better adapt to the characteristics of the current sensor data and improve the accuracy and efficiency of data processing.

[0086] When an autonomous vehicle encounters a data processing and / or decision delay scenario, the data processing or decision delay may affect the real-time response capability of the autonomous vehicle. To deal with this situation, the order of the data processing process nodes can be adjusted to optimize the processing path and reduce unnecessary delays. In addition, fast decision algorithms can be enabled, which are usually more concise and efficient, and can make decisions in a shorter time, thereby shortening the overall response time.

[0087] When the autonomous driving system faces resource shortage or overload (such as insufficient system resources due to processing multiple complex tasks at the same time), it can adopt the strategy of allocating additional resources to key nodes (such as increasing computing resources, memory, etc.) according to the current driving strategy and the evaluation results of abnormal scenarios to ensure the normal operation of key functions. At the same time, in order to reduce the burden on the system, it can also suspend the work of non-critical nodes or reduce their resource usage to release more system resources for key tasks.

[0088] Network security issues are also one of the important challenges facing autonomous vehicles. When a network security issue is detected (such as malicious attacks, data leaks, etc.), a network security protocol can be initiated to block the attack or prevent further data leakage. At the same time, nodes affected by network security can be isolated to prevent the problem from spreading to the entire system. In addition, security protection can be strengthened, such as using encrypted communications and regular security scans, to further improve the system's security protection capabilities.

[0089] The above strategies demonstrate how autonomous vehicles can flexibly adjust their node startup strategies when faced with different types of abnormal scenarios to ensure the stability, safety, and efficiency of the system.

[0090] In some embodiments of the present application, controlling the node startup of the autonomous driving vehicle according to the current node startup strategy includes: determining the nodes to be started in the autonomous driving vehicle according to the current node startup strategy and adjusting the startup order of each node to be started in the autonomous driving vehicle; allocating corresponding resources to each node to be started according to the current node startup strategy; and starting each node in sequence based on the adjusted startup order of each node to be started and the allocated resources.

[0091] When controlling the node startup of the autonomous driving vehicle according to the current node startup strategy, it is possible to first determine which nodes (or functional modules) need to be started in the current situation according to the current node startup strategy that is preset or generated in real time, and furthermore, the startup sequence of these nodes to be started can be adjusted. The adjustment of the startup sequence can be based on a variety of factors, such as safety, efficiency, resource availability, etc. For example, in some cases, it may be necessary to start the sensor node first to obtain environmental data, and then start the decision and control node to react based on the data.

[0092] After determining the nodes to be started and their startup order, necessary resources can be allocated to these nodes according to the current node startup strategy. These resources may include computing resources (such as CPU time, memory), communication resources (such as network bandwidth), energy resources (such as battery power), etc. The allocation of resources is intended to ensure that each node can operate in an optimal manner while avoiding excessive resource consumption or resource conflicts.

[0093] After completing node selection and resource allocation, each node can be started in sequence according to the adjusted startup sequence. This process may involve steps such as node initialization, configuration parameter loading, and communication establishment with other nodes. By starting nodes in sequence, the autonomous driving vehicle can gradually build a complete functional system required for its operation, thereby achieving autonomous control of the vehicle.

[0094] In some embodiments of the present application, controlling the node startup of the autonomous driving vehicle according to the current node startup strategy also includes: configuring each node to be started according to the current node startup strategy; and starting each node to be started in sequence based on the adjusted startup order, allocated resources and configuration of each node to be started.

[0095] After determining the nodes to be started, each node can also be configured as necessary according to the current node startup strategy. Configuration can include setting the node's operating parameters (such as the sampling rate of the sensor, the parameters of the control algorithm, etc.), loading the necessary software components (such as the algorithm library, the driver, etc.), and establishing communication connections with other nodes (such as network configuration, message queues, etc.). The purpose of configuration is to ensure that each node can operate as expected after startup and can work with other nodes to achieve the overall functionality of the autonomous driving vehicle. After completing the configuration of the node, the control system will start each node to be started in turn according to the previously adjusted startup sequence and the allocated resources.

[0096] In some embodiments of the present application, the system status and performance may be continuously monitored during the operation of the node, and dynamically adjusted and optimized according to the actual situation, which may include:

[0097] 1) System status monitoring: Real-time monitoring of the system status, such as the operating status of nodes, resource usage, and system performance indicators.

[0098] 2) Performance monitoring: Monitor the performance of the system, such as decision accuracy, response time, and data processing speed.

[0099] 3) Anomaly detection: Detecting anomalies in the system, such as node failures or performance degradation.

[0100] 4) Dynamic adjustment: Dynamically adjust node configuration and resource allocation based on monitoring results to optimize system performance.

[0101] 5) Optimization strategy update: Update the optimization strategy based on long-term performance data to improve the adaptability and efficiency of the system.

[0102] The present application also provides a node startup control device 200 for an autonomous driving vehicle, such as Figure 2 As shown, a schematic diagram of the structure of a node startup control device of an autonomous driving vehicle in an embodiment of the present application is provided, wherein the node startup control device 200 of the autonomous driving vehicle includes: a monitoring unit 210, an evaluation unit 220, a determination unit 230 and a startup control unit 240, wherein:

[0103] A monitoring unit 210, used to monitor the operating status data and external environment data of the autonomous driving vehicle;

[0104] An evaluation unit 220, configured to determine the abnormal scene in which the autonomous driving vehicle is currently located according to the operating state data and the external environment data and perform scene evaluation to obtain an abnormal scene evaluation result;

[0105] A determination unit 230, configured to determine a current driving strategy of the autonomous driving vehicle according to the abnormal scene evaluation result;

[0106] The startup control unit 240 is used to determine the current node startup strategy of the autonomous driving vehicle based on the current driving strategy of the autonomous driving vehicle and the abnormal scenario evaluation result, and control the node startup of the autonomous driving vehicle according to the current node startup strategy.

[0107] In some embodiments of the present application, the evaluation unit 220 is specifically used to: perform scene recognition based on the operating status data and the external environment data to obtain an abnormal scene in which the autonomous driving vehicle is currently located; use a preset evaluation strategy to perform a scene evaluation on the abnormal scene in which the autonomous driving vehicle is currently located to obtain an abnormal scene evaluation result, and the abnormal scene evaluation result includes at least one of an impact assessment result, a processing priority assessment result, and a risk assessment result.

[0108] In some embodiments of the present application, the determination unit 230 is specifically used to: calculate a comprehensive score of the abnormal scenario based on the abnormal scenario evaluation result, wherein the high or low comprehensive score of the abnormal scenario is used to characterize the degree of influence of the abnormal scenario in which the autonomous driving vehicle is currently located on the autonomous driving function; determine the current driving strategy of the autonomous driving vehicle based on the comprehensive score of the abnormal scenario, wherein the current driving strategy is at least one type of manual driving strategy, assisted driving strategy or autonomous driving strategy.

[0109] In some embodiments of the present application, the determination unit 230 is specifically used to: when the current driving strategy is a manual driving strategy, shut down the nodes associated with the autonomous driving function; when the current driving strategy is an assisted driving strategy or an autonomous driving strategy, determine the current node startup strategy of the autonomous driving vehicle according to the type of abnormal scene in which the autonomous driving vehicle is currently located and the abnormal scene evaluation result.

[0110] In some embodiments of the present application, the determination unit 230 is specifically used to: when the abnormal scenario currently in which the autonomous driving vehicle is located includes a sensor failure or restriction scenario, determining the current node startup strategy based on the abnormal scenario evaluation result includes starting redundant sensor nodes and adjusting sensor association algorithms; when the abnormal scenario currently in which the autonomous driving vehicle is located includes data processing and / or decision delay scenarios, determining the current node startup strategy based on the abnormal scenario evaluation result includes adjusting the order of data processing flow nodes and enabling a fast decision algorithm; when the abnormal scenario currently in which the autonomous driving vehicle is located includes a system overload scenario, determining the current node startup strategy based on the current driving strategy and the abnormal scenario evaluation result includes allocating additional resources to critical nodes, suspending the work of non-critical nodes, or reducing the resources of non-critical nodes; when the abnormal scenario currently in which the autonomous driving vehicle is located includes a network security problem scenario, determining the current node startup strategy based on the current driving strategy and the abnormal scenario evaluation result includes starting a network security protocol, isolating nodes affected by network security, and starting a security protection enhancement program.

[0111] In some embodiments of the present application, the startup control unit 240 is specifically used to: determine the nodes to be started in the autonomous driving vehicle according to the current node startup strategy and adjust the startup order of each node to be started in the autonomous driving vehicle; allocate corresponding resources to each node to be started according to the current node startup strategy; and start each node in sequence based on the adjusted startup order and allocated resources of each node to be started.

[0112] In some embodiments of the present application, the startup control unit 240 is specifically used to: configure each node to be started according to the current node startup strategy; and start each node to be started in sequence based on the adjusted startup order, allocated resources and configuration of each node to be started.

[0113] It can be understood that the node startup control device of the above-mentioned autonomous driving vehicle can implement the various steps of the node startup control method of the autonomous driving vehicle provided in the aforementioned embodiments, and the relevant explanations about the node startup control method of the autonomous driving vehicle are all applicable to the node startup control device of the autonomous driving vehicle, which will not be repeated here.

[0114] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 3At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0115] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0116] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0117] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a node startup control device for the autonomous driving vehicle at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0118] Monitor the operating status data and external environment data of the autonomous driving vehicle;

[0119] Determine the abnormal scene in which the autonomous driving vehicle is currently located according to the operating status data and the external environment data and perform scene evaluation to obtain an abnormal scene evaluation result;

[0120] Determining a current driving strategy of the autonomous driving vehicle according to the abnormal scenario evaluation result;

[0121] Determine the current node startup strategy of the autonomous driving vehicle according to the current driving strategy of the autonomous driving vehicle and the abnormal scenario evaluation result, and control the node startup of the autonomous driving vehicle according to the current node startup strategy.

[0122] The above application Figure 1The method performed by the node startup control device of the autonomous driving vehicle disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in software form. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0123] The present application also provides a computer program product, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 1 The method executed by the node startup control device of the autonomous driving vehicle in the illustrated embodiment is specifically used to execute:

[0124] Monitor the operating status data and external environment data of the autonomous driving vehicle;

[0125] Determine the abnormal scene in which the autonomous driving vehicle is currently located according to the operating status data and the external environment data and perform scene evaluation to obtain an abnormal scene evaluation result;

[0126] Determining a current driving strategy of the autonomous driving vehicle according to the abnormal scenario evaluation result;

[0127] Determine the current node startup strategy of the autonomous driving vehicle according to the current driving strategy of the autonomous driving vehicle and the abnormal scenario evaluation result, and control the node startup of the autonomous driving vehicle according to the current node startup strategy.

[0128] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0129] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0130] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0132] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0133] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0134] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0135] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0136] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0137] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A node startup control method for an autonomous driving vehicle, wherein: The node startup control method of the autonomous driving vehicle includes: Monitor the operating status data and external environment data of the autonomous driving vehicle; Determine the abnormal scene in which the autonomous driving vehicle is currently located according to the operating status data and the external environment data and perform scene evaluation to obtain an abnormal scene evaluation result; Determining a current driving strategy of the autonomous driving vehicle according to the abnormal scenario evaluation result; Determine the current node startup strategy of the autonomous driving vehicle according to the current driving strategy of the autonomous driving vehicle and the abnormal scenario evaluation result, and control the node startup of the autonomous driving vehicle according to the current node startup strategy.

2. The node startup control method of the autonomous driving vehicle according to claim 1, wherein: Determining the abnormal scene currently in which the autonomous driving vehicle is located according to the operating status data and the external environment data and performing scene evaluation to obtain the abnormal scene evaluation result includes: Performing scene recognition according to the operating status data and the external environment data to obtain an abnormal scene in which the autonomous driving vehicle is currently located; A preset evaluation strategy is used to perform a scene evaluation on the abnormal scene in which the autonomous driving vehicle is currently located to obtain an abnormal scene evaluation result, wherein the abnormal scene evaluation result includes at least one of an impact evaluation result, a processing priority evaluation result, and a risk assessment result.

3. The node startup control method of the autonomous driving vehicle according to claim 2, wherein: Determining the current driving strategy of the autonomous driving vehicle according to the abnormal scene evaluation result includes: Calculating a comprehensive abnormal scenario score according to the abnormal scenario assessment result, wherein the comprehensive abnormal scenario score is used to characterize the degree of influence of the abnormal scenario currently in which the autonomous driving vehicle is located on the autonomous driving function; The current driving strategy of the autonomous driving vehicle is determined according to the comprehensive score of the abnormal scenario, and the current driving strategy is at least one type of a manual driving strategy, an assisted driving strategy or an autonomous driving strategy.

4. The node startup control method of the autonomous driving vehicle according to claim 1, wherein: The determining of the current node startup strategy of the autonomous driving vehicle according to the current driving strategy of the autonomous driving vehicle and the abnormal scenario evaluation result includes: When the current driving strategy is a manual driving strategy, shut down the node associated with the automatic driving function; When the current driving strategy is an assisted driving strategy or an autonomous driving strategy, the current node startup strategy of the autonomous driving vehicle is determined according to the type of abnormal scene in which the autonomous driving vehicle is currently located and the evaluation result of the abnormal scene.

5. The node startup control method of the autonomous driving vehicle according to claim 4, wherein: The determining of the current node startup strategy of the autonomous driving vehicle according to the type of abnormal scene in which the autonomous driving vehicle is currently located and the abnormal scene evaluation result includes: In the case where the abnormal scenario currently in which the autonomous driving vehicle is located includes a sensor failure or a restricted scenario, determining, according to the abnormal scenario evaluation result, that the current node startup strategy includes at least one of starting a redundant sensor node and adjusting a sensor association algorithm; In the case where the abnormal scenario currently in which the autonomous driving vehicle is located includes a data processing and / or decision delay scenario, determining the current node startup strategy according to the abnormal scenario evaluation result includes at least one of adjusting the order of data processing flow nodes and enabling a fast decision algorithm; In a case where the abnormal scenario currently in which the autonomous driving vehicle is located includes a system overload scenario, determining, according to the current driving strategy and the abnormal scenario evaluation result, that the current node startup strategy includes at least one of allocating additional resources to critical nodes, suspending the operation of non-critical nodes, or reducing the resources of non-critical nodes; In the case where the abnormal scenario currently in which the autonomous driving vehicle is located includes a scenario of network security problems, the current node startup strategy is determined according to the current driving strategy and the abnormal scenario evaluation result, including starting a network security protocol, isolating nodes affected by network security, and starting at least one of a security protection enhancement program.

6. The node startup control method of the autonomous driving vehicle according to claim 1, wherein: The controlling the node startup of the autonomous driving vehicle according to the current node startup strategy includes: Determine the nodes to be started in the autonomous driving vehicle according to the current node startup strategy and adjust the startup order of each node to be started in the autonomous driving vehicle; Allocate corresponding resources to each node to be started according to the current node startup strategy; Based on the adjusted startup sequence of each node to be started and the allocated resources, each node is started in sequence.

7. The node startup control method of the autonomous driving vehicle according to claim 6, wherein: The controlling the node startup of the autonomous driving vehicle according to the current node startup strategy further includes: Configuring each node to be started according to the current node startup strategy; Based on the adjusted startup sequence, allocated resources, and configuration of each node to be started, each node to be started is started in sequence.

8. A node startup control device for an autonomous driving vehicle, wherein: The node startup control device of the automatic driving vehicle includes: A monitoring unit, used to monitor the operating status data and external environment data of the autonomous driving vehicle; An evaluation unit, configured to determine the abnormal scene in which the autonomous driving vehicle is currently located according to the operating state data and the external environment data and perform scene evaluation to obtain an abnormal scene evaluation result; a determination unit, configured to determine a current driving strategy of the autonomous driving vehicle according to the abnormal scenario evaluation result; A startup control unit is used to determine the current node startup strategy of the autonomous driving vehicle based on the current driving strategy of the autonomous driving vehicle and the abnormal scenario evaluation result, and control the node startup of the autonomous driving vehicle according to the current node startup strategy.

9. An electronic device, comprising: processor; And a memory arranged to store computer executable instructions, which, when executed, cause the processor to execute the node startup control method for the autonomous driving vehicle of any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, which, when executed by a processor, implements the node startup control method of any one of claims 1 to 7 of the autonomous driving vehicle.

Images