509 results about "Driving risk" patented technology

The invention relates to the technical field of intelligent traffic, and discloses a road transportation key operating vehicle intelligent supervision system, which comprises a data acquisition and fusion module used for acquiring multi-source heterogeneous data of a vehicle terminal, an external environment and the like in real time and carrying out standardization processing; the cognitive digital twinning construction module is used for constructing a dynamic heterogeneous graph representation human-vehicle-road-environment system and outputting a cognitive state vector through a graph neural network; the risk prediction and evaluation module is used for predicting a risk evolution trend based on the state vector sequence and quantifying the uncertainty of prediction by using a Monte Carlo discarding method; and the self-adaptive intervention decision module is used for combining risk prediction and uncertainty, making a decision through a reinforcement learning model and executing an optimal active intervention instruction. By constructing cognitive digital twinning and introducing uncertainty quantification and closed-loop self-checking, prospective prediction and self-adaptive intervention of driving risks are realized, and the accuracy and robustness of supervision are improved.

The invention discloses a child electric motorcycle intelligent safety control system based on the Internet of Things, and relates to the technical field of electric motorcycle safety control. The problem of insufficient driving risk perception and control response of children is solved. The method comprises the following steps: firstly, fusing obstacle trajectory prediction, a road adhesion coefficient and an environment contour, constructing a dynamic risk vector field, and generating a collision probability and out-of-control coefficient fused risk assessment matrix; then, the matching degree of handle operation and vehicle body response is calculated through cross attention, and a third-level behavior label is output; according to the behavior level and the risk direction, anti-sideslip control or progressive power limitation is executed, and intervention characteristics are recorded; and finally, constructing a virtual training task by using parent operation data, extracting a personalized control threshold, dynamically optimizing system parameters, and realizing a child driving behavior-oriented closed-loop safety control system.

The present disclosure discloses an anthropomorphic lane-changing control method and system based on driving risk quantification, and a vehicle. The method includes: determining whether a main vehicle has a lane-changing intention based on motion statuses of the main vehicle and a front vehicle in a current lane; if there is a lane-changing intention, generating an anthropomorphic lane-changing trajectory that satisfies safety constraints and reachability constraints; based on a motion status of a traffic participant that causes a risk to the main vehicle, calculating an overall risk level and determining whether the anthropomorphic lane-changing trajectory satisfies risk constraints; and if the risk constraints are not satisfied, regenerating an anthropomorphic lane-changing trajectory; or if the risk constraints are satisfied, performing tracking control based on a preview-following theory. In the present disclosure, a lane-changing intention is described and identified based on actually measured data, to generate an anthropomorphic lane-changing trajectory.

The invention relates to an automatic driving risk quantification method based on a conflict risk field. Comprising the steps of 1, constructing a basic risk field; step 2, under a basic risk field framework, constructing a conflict risk field by taking an ADV as a center; step 3, regarding the conflict risk field as a repulsive force acting on the ADV, and using the repulsive force to quantify the dynamic influence of the environmental elements and various TP states on the driving safety of the ADV; the method comprises the following steps: firstly, constructing a basic risk field on the basis of traffic vehicle distribution and motion characteristics, further forming a vehicle forward, lateral, backward and traffic regulation constraint multi-dimensional conflict risk field on the basis, and converting an abstract traffic conflict relationship into a computable repulsive force model; dynamic quantitative characterization of driving risks in a state dimension, a space dimension and a time dimension is realized, and continuous optimization and evolution of an end-to-end automatic driving algorithm are supported by means of a repulsive force model constructed based on a conflict risk field.

The invention relates to the technical field of risk assessment, in particular to a safe driving assessment method and system based on Beidou navigation. The method comprises the following steps: acquiring corresponding real-time position, speed and driving track data in a vehicle driving process through a Beidou navigation module, and acquiring vehicle state data and environment sensing data to obtain a vehicle multi-dimensional driving state data set; performing vehicle space-time and driving operation feature analysis and driving road matching analysis on the vehicle multi-dimensional driving state data set to obtain vehicle driving road attribute matching data; and carrying out vehicle driving risk estimation and vehicle safety over-rate evaluation based on the vehicle driving road attribute matching data, carrying out safety comparison verification evaluation, generating vehicle personalized driving improvement suggestions, and pushing the vehicle personalized driving improvement suggestions to the vehicle-mounted terminal to execute corresponding vehicle safe driving behavior improvement operation. According to the invention, real-time monitoring, accurate evaluation and active safety intervention of vehicle driving behaviors can be realized.

The invention provides a driving behavior intelligent identification method and system based on video analysis, and the method comprises the steps: obtaining a driver face video stream and a road environment video stream collected by a vehicle-mounted camera, and reading the driving information recorded by a whole vehicle communication network; recognizing an eyelid closing state, a sight line direction and a head posture in the driver face video stream based on a posture recognition model, and performing fatigue distraction analysis to obtain driver state information; performing motion trail analysis on the road environment video stream and the driving information, and performing driving risk assessment in combination with the driver state information to obtain driving assessment information; and performing early warning construction according to the driving evaluation information, generating early warning prompt information, and synchronously writing the early warning prompt information, the driving evaluation information and the driver state information into a safety data protection memory. The fatigue and distraction states of the driver can be recognized more accurately, and the accuracy of state judgment is improved.

The invention discloses an intelligent intervention system and method based on multi-mode driving behavior analysis, and belongs to the field of intelligent traffic. The system comprises a multi-dimensional perception module, a behavior analysis engine, a risk assessment matrix and a self-adaptive intervention module. The multi-dimensional sensing module is integrated with a multi-source heterogeneous sensor and is used for acquiring physiological characteristics of a driver, driving operation data and environment information; the behavior analysis engine analyzes multi-modal data based on spatial-temporal feature fusion, and digs a driving behavior mode; the risk assessment matrix judges danger levels according to the multi-dimensional driving risk quantification result level by level; and the self-adaptive intervention module implements a grading progressive correction strategy. The system realizes active prevention and control of driving risks through cross-modal data association, behavior chain prediction and environment-behavior coupling analysis. The system solves the problems that a traditional system is single in sensing dimension, coarse in risk assessment, rigid in intervention strategy and the like, and effectively improves the driving safety.

The invention provides a driving risk early warning method based on long-term and short-term driving style features. The method comprises the following steps: constructing long-term and short-term driving feature vectors according to driving behavior data; based on the standardized long-term and short-term driving feature vectors, a clustering method is adopted to determine long-term style feature vectors and long-term and short-term driving risk score labels; constructing a multilayer driving risk assessment model considering long and short term driving styles, and performing fitting training on the assessment model based on the long and short term driving style sample set to obtain an optimal multilayer driving risk assessment model; determining a long-term driving style category according to a long-term driving feature vector collected in real time, inputting the long-term driving style category and a short-term driving feature vector collected in real time into an optimal multilayer driving risk assessment model, and outputting a moving average trend of a scoring time sequence and a fluctuation trend of a driving behavior in a time window according to a predicted driving risk score output in real time. And formulating a two-stage early warning strategy. According to the invention, highly personalized and adaptive risk early warning can be provided.

The invention discloses a vehicle driving right transfer method based on abnormal driving behaviors and electronic equipment, and the method comprises the steps: collecting driver state data, vehicle driving state data and road environment data, and carrying out the multi-source data fusion; abnormal driving behavior detection is performed according to the multi-source data, and the driving risk is evaluated; a rule engine decision-making model based on the situation is used for deciding countermeasures to be taken, and the countermeasures comprise early warning type actions, auxiliary control type actions, forced take-over type actions and mutual switching among the actions based on an advanced auxiliary driving system or an automatic driving system; after the vehicle is forced to take over and runs for n minutes, whether the current vehicle is suitable for the driver to take over or not is judged according to driver state data collected in real time and the current comprehensive driving risk score, and whether driving right transfer is conducted or not is determined according to the judgment result. The accuracy of abnormal driving behavior detection is improved, the vehicle driving right is intelligently transferred, and the driving safety is improved.

The invention relates to the technical field of intelligent traffic, in particular to an intelligent network connection vehicle driving risk assessment method and a visualization system based on multi-source data fusion. According to the method, multi-source data such as vehicle perception, communication and maps are fused, an artificial potential field theory is combined, a gravitational force risk potential field function, a repulsive force risk potential field function and a road boundary repulsive force potential field function are constructed respectively, and a unified total risk potential field TPF is formed by a gravitational force risk potential field, a repulsive force risk potential field and a road boundary repulsive force potential field; according to the method, the driving risk of the intelligent networked vehicle is obtained, risk grade division and real-time visual display are realized through clustering analysis, the accuracy and dynamic response capability of risk assessment are improved, the method is suitable for safety decision support of advanced driving assistance and automatic driving systems, real-time assessment of the driving risk can be realized more accurately and efficiently, and the risk assessment efficiency is improved. And the risk assessment precision and the dynamic response capability are improved.

The invention belongs to the technical field of traffic control systems, and particularly relates to an expressway interleaving area automatic driving vehicle driving risk assessment method, which comprises the steps of 1, obstacle space-time risk field modeling, 2, road boundary and road line risk field modeling, 3, expressway upper and lower ramp risk field modeling, 4, total risk field calculation, 5, expressway interleaving area automatic driving vehicle driving risk assessment, 6, expressway interleaving area automatic driving vehicle driving risk assessment, 7, expressway interleaving area automatic driving vehicle driving risk assessment and 7, expressway interleaving area automatic driving vehicle driving risk assessment. The method has the advantages that the physical quantity of the space-time distance is innovatively introduced, the dimension of a two-dimensional space risk field is raised to a three-dimensional time-space risk field, the real-world expressway vehicle track is extracted, and the real-world expressway vehicle track is extracted. And the influence of the prediction trajectory and the time effect on the risk is effectively quantified. A special geometric configuration field of the upper ramp and the lower ramp of the interlacing area is also constructed, and accurate limitation is applied to operation of a specific vehicle. And on the basis of a risk dynamic balance theory, YOLO and other machine vision technologies, model parameters are calibrated by using real aerial photography data.

The invention discloses a simulation method for urban flood emergency rescue path planning, and the method comprises the steps: carrying out the modeling of an urban road network based on an urban topographic map, rainfall data, existing water distribution and key position information; mIKE simulation software is used for establishing a hydrodynamic model to simulate the rainfall and flood spreading process of the city, and flood dynamic information, including the depth and flow velocity of the flood, at each position point in the flood disaster scene model is obtained; respectively constructing objective functions according to the shortest maximum time of arrival of the disaster relief point, the lowest driving risk of the rescue vehicle and the shortest total weighted rescue time; setting constraint conditions to ensure that all disaster relief points are covered, and preventing vehicles from being excessively distributed; based on the flood dynamic information, the objective function and the constraint condition, adopting an NSGA-II non-dominated sorting genetic algorithm to solve a Pareto solution set; and performing weighted analysis on a result in the Pareto solution set to obtain an optimal solution, and outputting an urban flood emergency rescue path plan.

An intelligent driving risk early-warning method and apparatus, an electronic device, and a storage medium. The intelligent driving risk early-warning method is applied to a first vehicle, and comprises the following steps: when it is determined that the first vehicle is in an intelligent driving state, acquiring vehicle traveling information (S10); when it is determined that the vehicle traveling information satisfies a preset potential risk condition, performing risk data detection (S20); and when risk evaluation is performed by means of a preset risk evaluation model on the basis of the risk data to determine that the first vehicle has an intelligent driving risk, outputting intelligent driving risk early-warning information (S30).

The invention relates to the field of automatic driving and traffic safety, in particular to a fine-grained multi-task driving risk prediction method fused with a trajectory prediction auxiliary task. Comprising the following steps: step 1, automatically labeling risk labels based on trajectory data; 2, designing a main task of the driving risk prediction model; 3, auxiliary task design of the driving risk prediction model; and 4, constructing and training a driving risk prediction model. An experiment result based on a disclosed NGSIM data set shows that the precision and robustness of a driving risk prediction model can be remarkably improved by introducing trajectory prediction as an auxiliary task.

The invention relates to an automatic driving safety behavior decision-making method with interactive risk consciousness, which belongs to the technical field of automatic driving behavior decision-making, and comprises the following steps: S1, extracting the state of a vehicle and driving environment information based on sensor data; s2, defining a state space and an action space of deep reinforcement learning; s3, adopting a D3QN reinforcement learning algorithm to construct a decision framework and integrating a self-attention mechanism to capture multi-vehicle interaction features; s4, establishing a driving risk potential field model considering multi-vehicle interaction according to the multi-vehicle interaction characteristics and the motion state and the relative position of the environment vehicle; s5, constructing a comprehensive reward function based on the driving risk potential field; s6, performing network training by adopting an experience playback mechanism; and S7, deploying a risk action correction module at the output end of the value network.

The invention relates to the technical field of driving, in particular to a driving risk interaction prompting method, intelligent equipment and a readable storage medium, and aims to solve the technical problem of how to ensure that a driver can timely, accurately and effectively receive a risk prompt of a driving risk scene. In order to achieve the purpose, a driving risk scene of the intelligent equipment is obtained based on environment perception information of the intelligent equipment; obtaining a visual focus prediction result of the driver based on the driver state of the driver of the intelligent equipment; obtaining a channel availability evaluation result of at least one prompt channel of the intelligent equipment based on the prompt channel state of the intelligent equipment; according to a visual focus prediction result and a channel availability evaluation result, risk prompting is performed on a driving risk scene, so that the situation that the risk prompting is ignored in an unconcerned area of a driver is effectively avoided, and the risk prompting can be adaptively, timely, effectively and accurately perceived and transmitted by the driver; therefore, the driving safety of the intelligent equipment is effectively improved.

The invention relates to the technical field of automatic driving risk analysis, in particular to a traffic risk analysis method and analysis device based on a graph neural network, and the method comprises the steps: sequentially carrying out the coding of a graph encoder and the coding of an attention mechanism based on the obtained historical track information of an intelligent agent and the lane line information of a map, and obtaining an attention mechanism; obtaining an attention mechanism coding result; decoding by using a cross attention mechanism based on an attention mechanism coding result; and performing prediction trajectory decoding by using a multi-layer perceptron based on a cross attention mechanism decoding result, performing decoding by using a deconvolution network based on a decoding result, calculating risk matrix loss by using a probability loss function, and performing model training and verification to obtain a risk analysis model based on a graph neural network so as to predict traffic risks. Therefore, the problems that the risk analysis depth of traffic participants is limited and future intentions and potential risks of the traffic participants are difficult to accurately describe by traffic risk analysis methods in related technologies are solved.

The invention discloses an auxiliary driving method. The method comprises the following steps: acquiring a driving strategy association factor; performing feature extraction on the driving strategy correlation factors to obtain driving strategy correlation features; dynamically distributing the weights of the plurality of driving strategy associated features; performing weighted fusion on the plurality of driving strategy associated features to obtain a driving strategy fusion feature; determining a risk level evaluation index based on the driving strategy fusion feature, and obtaining a risk evaluation result based on the risk level evaluation index and an index threshold; the index threshold value is generated based on the personalized data of the driver and the traffic environment data; and generating an auxiliary driving strategy according to a risk assessment result. According to the method, the multi-dimensional driver data is fused, the feature weight is dynamically distributed, and the risk assessment result is generated in combination with the personalized index threshold, so that the problem of misjudgment caused by single data dimension and fixed weight of a traditional system is solved, and the method has the advantages of improving the driving risk assessment accuracy, enhancing the system adaptability and improving the driving safety.

The invention discloses an auxiliary driving risk prediction method based on driver state monitoring and a related device, and relates to the technical field of auxiliary driving risk prediction. In the scheme of the invention, unsupervised clustering is carried out on historical driver physiological data and historical vehicle driving data by using a clustering algorithm; preliminarily dividing collision risk grades of automobile operation; constructing a training data set and a test data set according to a plurality of groups of historical driver physiological data, historical vehicle driving data and corresponding collision risk levels, and obtaining a trained collision risk prediction model; and finally, based on the actually measured vehicle driving data and the actually measured driver physiological data, risk prediction is carried out by using the collision risk prediction model so as to obtain an auxiliary driving risk prediction result. In addition, the auxiliary driving risk prediction result can also be used for updating division of collision risk levels in combination with actual conditions. The problem of insufficient prediction accuracy caused by the fact that a traditional risk prediction method is only based on vehicle operation data is solved, and the prediction accuracy of the driving risk is improved.

The invention discloses a vehicle driving risk prediction method and device in an off-road environment based on a large model, and relates to the technical field of off-road risk prediction, and the method comprises the steps: obtaining current vehicle state data and current environment perception data; determining a target multi-axis rollover risk index based on the current vehicle state data; determining a target lateral instability index based on the current vehicle state data and the current environment perception data; fusing the target multi-axis rollover risk index and the target lateral instability index to generate target risk level data; based on the current vehicle state data, the current environment perception data and the target risk level data, generating a target operation recommendation sequence through a large cross-country decision model; and outputting risk early warning information based on the target operation recommendation sequence.

The invention provides a road transport vehicle driving risk uncertainty prediction method and system, and belongs to the technical field of vehicle driving risk prediction technology, and the method comprises the steps: obtaining an alarm number space-time sequence, a traffic flow space-time sequence and a multi-graph static adjacency matrix of a current time step; and processing the obtained alarm number time-space sequence, the traffic flow time-space sequence and the multi-graph static adjacency matrix by using a pre-trained road transport vehicle driving risk uncertainty prediction model to obtain the road transport vehicle alarm number in the future time step. According to the invention, accurate short-time prediction of the driving risk of the road transport vehicle is realized, and powerful technical support is provided for improving the reliability and real-time performance of vehicle driving risk early warning.

The invention relates to the technical field of vehicles, in particular to a risk assessment method and device for a vehicle, the vehicle and a storage medium, and the method comprises the steps: obtaining biological data of a driver, state data of the current vehicle and environment data; inputting the biological data of the driver, the state data of the current vehicle and the environment data into a preset risk assessment model to obtain a comprehensive risk score; and determining a risk level of the current vehicle based on the comprehensive risk score and the duration to execute a response action according to the risk level. Therefore, the problems that the monitoring accuracy is reduced, the health data of the driver cannot be combined and emergency health events cannot be dealt with due to the fact that the risk assessment of the vehicle is easily influenced by external factors are solved, the driving risk can be comprehensively assessed in combination with the biological data of the driver, the vehicle state data and the environment data, and the risk assessment precision is improved.

The invention relates to the technical field of image or video recognition or understanding, and discloses a bus driver driving state evaluation method, which comprises the following steps: acquiring a face image, an electrocardiosignal and voice audio data of a bus driver, performing timestamp alignment and preprocessing, and constructing a multi-mode driving state data set; extracting multi-modal features of the collected data, and mapping the multi-modal features to a unified feature space; fusing multi-modal features through a cross-modal attention mechanism, dynamically adjusting attention weight based on an emotional change difficulty index, and extracting emotional change key features; and predicting a two-dimensional continuous emotion value of the driver by using the fusion features, calculating a long-time-sequence emotion driving risk score based on an emotion stimulation dynamic model, and performing evaluation and early warning of a driving state. The problems of single-mode analysis, lack of long-period early warning and driving state static recognition in the prior art are solved, and the purposes of accurate evaluation, high safety, multi-mode fusion and long-time-sequence prediction are achieved.

The embodiment of the invention relates to the technical field of driving safety management, and particularly discloses a driving safety management method and system based on driving track monitoring. According to the embodiment of the invention, the driving state data of the target engineering vehicle is directly or cooperatively collected; generating smooth trajectory data, and performing anomaly evaluation on the smooth trajectory data; an optimal driving path is planned, and dynamic driving guidance is carried out; performing dynamic risk analysis and early warning prompt on the target engineering vehicle; and constructing a driving risk portrait, and performing periodic assessment on a target driver of the target engineering vehicle. Trajectory cleaning and reconstruction can be carried out, smooth trajectory data can be generated, abnormity assessment can be carried out, dynamic risk analysis and early warning prompt can be carried out on a target engineering vehicle, a driving risk portrait can be constructed, periodic assessment can be carried out, personalized management of engineering transport vehicle driving safety can be realized, management precision can be improved, and the engineering transport vehicle driving safety management efficiency can be improved. And the driving data can be effectively utilized, and a basic support is provided for management decision guidance and strategy optimization.

The invention discloses a mountain area double-lane road driving dynamic risk assessment method based on an artificial potential field theory. The method comprises the following steps: S1, extracting trajectory data with potential conflicts in vehicle natural driving data; s2, constructing an obstacle risk field, and quantifying driving risks caused by dynamic and static obstacles on a road; s3, constructing a road line risk field, and quantifying potential risks caused by driving of the vehicle deviating from the center line; s4, constructing a road boundary risk field, and quantifying the risk generated when the vehicle approaches the road boundary; s5, integrating the risk field models of the three driving risk sources to construct a comprehensive driving risk field model; and S6, visualizing the driving risk of the specific target vehicle in the form of a risk map. According to the method, a mountain area double-lane road driving dynamic risk assessment model based on the artificial potential field theory is constructed, and the mountain area double-lane road driving dynamic risk is scientifically, reasonably and accurately described and discriminated from the angle of accident prevention.

The invention discloses a synergy control method for a confluence area based on Rainbow DQN and a driving risk field, relates to the technical field of traffic safety, and aims to solve the problems that the overall traffic quality of mixed traffic flow is reduced and the confluence risk is increased due to the fact that a control logic is not matched with a real-time risk in an existing signal control method for the confluence area of an expressway. According to the invention, by considering the CAV-containing mixed traffic flow of the main line of the confluence area, the main line traffic flow information and the ramp queuing information, the state space and the action space of the cooperative control agent are designed in a refined manner, and a reward function considering the traffic efficiency, the traffic safety and the cooperative interaction is provided; therefore, the main line speed limit value can be dynamically controlled, the ramp queuing vehicles are dynamically coordinated, the main line CAV vehicle driving track is induced, and the passing efficiency and the traffic safety are effectively improved. The overall traffic quality of the mixed traffic flow is ensured, and the confluence risk is reduced.

The invention discloses a driving risk assessment method based on a coupled vibration model, and the method comprises the steps: S1, obtaining a vehicle dynamic parameter and a geometric dimension parameter, and building a vehicle dynamic model based on the vehicle dynamic parameter and the geometric dimension parameter by employing finite element analysis software or directly calculating a dynamic differential equation set; s2, acquiring bridge vibration excitation, roughness excitation and crosswind excitation; s3, inputting the bridge vibration excitation, the roughness excitation and the crosswind excitation into the vehicle model for coupled vibration analysis, and obtaining vehicle vibration response data; and S4, based on the vehicle vibration response data, obtaining a driving safety index and a comfort index, and performing risk assessment according to preset threshold values of safety and comfort. According to the method, multi-dimensional factors such as the wind environment, the vehicle dynamic response, the bridge structure vibration characteristic and the driving comfort degree are considered, and a high-precision and high-reliability risk assessment basis can be provided for a bridge operation unit.

The invention relates to the technical field of automatic driving, in particular to an automatic driving risk scene generation method and system suitable for a strong interaction environment and a storage medium, and the method comprises the steps: firstly collecting the data of a real vehicle following or lane changing target scene, and then calculating the vehicle motion interaction feature F of the target scene; and a TimeGAN model is improved in combination with an attention mechanism to obtain an F-TimeGAN model, a target scene is input into the F-TimeGAN model for scene generation, and finally, a strong interaction risk scene is screened out from the generated scene for automatic driving test. The strong interaction risk scene data which is difficult to collect in reality can be efficiently generated based on the conventional target scene data, the interactivity and the risk of the generated scene are enhanced, the problem of rare key test scene data is effectively solved, and scene data support is provided for safety verification of automatic driving in a strong interaction environment.

The invention discloses a remote driving risk early warning method based on communication time delay perception, which comprises the following steps: firstly, collecting related data of a target communication link, carrying out preprocessing and feature extraction on the data, fitting a nonlinear relationship between time delay and multiple features based on an extreme gradient lifting XGboost algorithm, and predicting a change condition of the time delay in real time; constructing a communication risk evaluation model, and quantifying a communication risk value based on the time delay change condition; predicting a vehicle trajectory according to the vehicle dynamics model and the driver execution instruction sequence; calculating a lane departure risk and an obstacle collision risk based on the vehicle trajectory, the environmental risk value being the sum of the two; and comprehensively considering an environment risk value and a communication risk value, and judging whether to trigger an alarm according to a designed safety threshold. According to the method, an environment risk evaluation mode is redesigned on the basis of considering the communication time delay, and the environment risk and the communication risk are comprehensively incorporated into an early warning framework, so that better safety guarantee is provided for a remote driving system.

The invention belongs to the technical field of software engineering, particularly relates to an automatic driving system performance enhancement method based on an expert hybrid architecture, and aims to solve the core problems that an end-to-end automatic driving system is confronted with semantic fuzziness to cause unreliable decision, multi-task interference hinders optimization planning, too long reasoning delay increases driving risks and the like. According to the method, an ExpertAD framework is provided, task key features are amplified through a perception adapter (PA), and the relevance of scene context understanding is guaranteed; related driving tasks are dynamically activated through a sparse expert mixture (MoSE), and task interference is minimized; and in combination with a customized training loss function, collaborative optimization of planning effectiveness and reasoning efficiency is realized. Experiments show that compared with an existing method, the method has the advantages that the average collision rate is reduced by 20%, the reasoning delay is reduced by 25%, higher multi-skill planning capacity is achieved in rare scenes (such as accident handling and first-aid vehicle avoiding), and good generalization is achieved for unseen urban environments.