1034 results about "Smart vehicle" patented technology

The invention belongs to the technical field of traffic optimization, and particularly relates to a traffic optimization method based on a three-layer Stackelberg game, and the method comprises the steps: obtaining mixed traffic data; according to the mixed traffic data, constructing a three-layer Stackelberg game model; an equilibrium solution of the three-layer game model is solved through a deep reinforcement learning algorithm, an SAC algorithm is introduced into an upper layer to generate a global constraint strategy, and a DDPG algorithm is adopted in a lower layer to optimize cooperative driving and safe obstacle avoidance driving behaviors of the intelligent vehicle; according to the global constraint strategy and the intelligent vehicle driving behavior optimization result, the traffic efficiency, safety and energy consumption and carbon emission indexes of the mixed traffic flow are optimized, the traffic state is continuously updated through behavior feedback data of a middle layer and a lower layer, and strategy optimization is carried out in combination with SAC and DDPG models. Therefore, the problems of insufficient dynamic adaptability, low efficiency of main body interaction processing, limitation of a game model and the like in the prior art are solved.

The invention relates to the field of logistics vehicle management, in particular to a centralized management method and system for intelligent vehicles. The invention discloses a centralized management system for smart vehicles. The centralized management system comprises a task receiving module, a portrait construction module, a vehicle screening module, a sign-in verification module and a queue management module. According to the method, the vehicle multi-dimensional portrait model is constructed, and the transportation cost, the transportation efficiency and the like are subjected to multi-dimensional matching calculation based on the multi-objective optimization algorithm, so that intelligent vehicle dispatching decision-making from experience driving to data driving is realized; according to the method, the historical operation data, the real-time state and the driver behavior characteristics of the vehicle are comprehensively considered, a global optimal vehicle dispatching scheme can be output, the vehicle dispatching accuracy and the resource utilization efficiency are remarkably improved, and the limitation that a traditional method only depends on a single factor for dispatching is overcome.

The invention discloses an intelligent vehicle cluster safe formation control method based on an observer, an intelligent vehicle cluster comprises a leader vehicle and follower vehicles, and a third-order longitudinal dynamics mathematical model is constructed for each follower vehicle and each leader vehicle. A sampling-based distributed observer is constructed based on a communication relationship among vehicles and a third-order longitudinal dynamics mathematical model, and an extended state observer is constructed based on state information of a follower vehicle and introduction of unmodeled disturbance; an intelligent vehicle cluster safe formation control strategy is constructed based on a distributed observer and an extended state observer, and a DoS attack model is constructed. According to the technical scheme, precise estimation of the state information of the leader vehicle by the follower vehicles and real-time precise estimation of each state component and unmodeled disturbance of each follower vehicle are achieved, it is guaranteed that each vehicle in the vehicle formation runs at a safe interval and at a constant vehicle speed, and the robustness of a vehicle system in a complex environment is improved.

The invention belongs to the field of intelligent vehicle-mounted technology, and particularly relates to a multifunctional vehicle-mounted sensing detection system based on multi-source information fusion, which comprises multi-source information acquisition, high-precision space-time synchronization and heterogeneous data preprocessing. A heterogeneous sensing system with feature level deep fusion, vehicle state dynamic performance evaluation and adaptive decision and risk evaluation capabilities is constructed, and a driving decision is dynamically adjusted through fusion perception and vehicle performance. The vehicle state and dynamic performance evaluation module is constructed by deeply integrating vehicle internal state data acquired by a vehicle-mounted diagnosis system into a perception fusion and decision planning process, and the core contradiction of disjunction of a perception result and a vehicle dynamic performance strategy is effectively solved. The system can evaluate key performance parameters such as power, braking, steering and the like of the vehicle and potential faults of the key performance parameters in real time, and the driving strategy and the safety margin are dynamically adjusted in the self-adaptive decision and risk evaluation module according to the actual physical limitation of the vehicle.

The invention relates to the technical field of intelligent early warning, in particular to an intelligent vehicle-mounted blind area early warning device based on multi-modal sensor fusion, which comprises a sensing array module, a driver sensing module, an environment recognition module, an early warning decision module and a linkage execution module, the sensing array module is used for being connected with a vehicle-mounted system to obtain vehicle-mounted data related to a driver and a driving environment. The driver sensing module is used for analyzing driving habit information of the driver according to the vehicle-mounted data. The environment identification module is used for analyzing environment identification information of the vehicle according to the vehicle-mounted data. The early warning decision module is used for generating a grading threshold value of blind area early warning monitoring according to the driving habit information and the environment identification information; a personalized early warning and monitoring model is established by using a deep learning algorithm, and dynamic risk levels of a driver in a driving process are divided. According to the method, the personalized driving habit model is generated through deep learning, invalid interference is reduced, and the blind area early warning efficiency is improved.

The invention provides a warning method and system of an intelligent tripod warning lamp, and relates to the technical field of intelligent vehicle-mounted technologies. When a vehicle is in danger, vehicle state information is collected to automatically generate a warning trigger instruction, and a rear target projection point is determined based on a road type and a vehicle position; projection parameters are calculated in combination with vehicle postures, a vehicle-mounted projection light source is driven to generate a triangular warning graph on the ground at the target distance, meanwhile, light beam output is adjusted in a self-adaptive mode according to environment illumination and visibility, and it is guaranteed that the graph is clear and visible and conforms to human eye safety; the projection position and parameters are dynamically updated to maintain stable warning during the duration of the dangerous state, and the system is automatically closed and reset when the danger is relieved or manual termination is performed, so that the risk of manual arrangement is avoided, and long-distance stable warning is realized.

The invention relates to an intelligent vehicle taillight system, a control method thereof and a vehicle, the intelligent vehicle taillight system comprises a data acquisition module used for acquiring vehicle dynamic operation parameters and external environment information, the vehicle dynamic operation parameters comprise at least one of brake pedal stroke, steering angle, vehicle speed and automatic driving state data, and the external environment information is used for acquiring the external environment information; the external environment information comprises at least one of a rear vehicle distance and a pedestrian position; the intelligent control module is connected with the data acquisition module and is used for generating current working condition information of the vehicle based on the vehicle dynamic operation parameters and the external environment information; and the tail lamp is connected with the intelligent control module and performs corresponding display and projection operation according to the current working condition information. According to the invention, the driving safety can be improved.

The invention discloses an auxiliary driving method and device and intelligent driving equipment, and the method comprises the steps: obtaining weather information which indicates the weather type and / or road surface type of the current environment of the intelligent driving equipment; wherein the first weather type comprises one or more of a weather type for limiting visibility of a driver, a weather type for limiting sensing capability of a sensing system, or a weather type for increasing a braking distance of the intelligent driving equipment, and the first road surface type comprises a road surface type for increasing the braking distance of the intelligent driving equipment; according to the first environment information, a prompt device of the intelligent driving equipment is controlled to prompt a driving suggestion, and the driving suggestion comprises a driving strategy corresponding to the first environment information. The method can be applied to vehicles such as intelligent vehicles and new energy vehicles, and when severe weather influencing driving safety is detected, the vehicle user can be prompted about related information in time, so that the influence of the severe weather on driving is reduced.

The invention discloses a multi-parameter self-adaptive optimization intelligent vehicle trajectory tracking control method in the technical field of intelligent vehicle control. The method comprises the following steps: estimating a vehicle motion state in real time according to a three-degree-of-freedom dynamic model and a sensor measurement value by adopting a self-adaptive extended Kalman filtering algorithm; based on the estimated vehicle motion state, designing and implementing a model prediction controller to perform trajectory tracking; calculating to obtain an optimal control increment sequence in a future control time domain; taking a first element of the optimal control increment sequence as an actual control instruction increment at the current moment to act on a vehicle actuator, and entering a next control period, so as to adaptively balance closed-loop trajectory tracking control of tracking precision and driving stability; according to the method, adaptive state estimation and fuzzy dynamic predictive control are fused, deep coupling of high-precision perception and intelligent decision making is achieved, and the trajectory tracking precision, the driving stability and the system robustness are remarkably improved under the complex working condition.

The invention discloses an intelligent vehicle safety decision-making method considering a conflict spatio-temporal evolution law, and the method comprises the steps: enabling an intelligent vehicle to obtain vehicle trajectory data from a cloud platform, building risk multi-scale characteristic indexes based on the vehicle trajectory data, and enabling the indexes to comprise a vehicle-to-longitudinal and transverse conflict index, a vehicle group order conflict index, and a vehicle cluster interaction conflict index, respectively measuring the vehicle microscopic risk, the vehicle group mesoscopic risk and the traffic flow macroscopic risk; constructing a directed association rule reflecting a different-scale risk conflict directed chain relationship; and constructing a linear CRF risk prediction model, fusing current microscopic, mesoscopic and macroscopic risk states and directed association rules among the states, predicting a microscopic risk state at a future moment, and triggering a corresponding early warning mechanism according to a prediction result to realize driving safety decision.

A self-triggering unmanned vehicle distributed formation control method based on a double-triggering mechanism belongs to the field of unmanned vehicle distributed cooperative formation control, and comprises the following steps: S1, constructing a multi-agent consistency cooperative control framework; s2, constructing an intelligent vehicle cooperative control system driven by a dynamic situation field; s3, carrying out communication topology modeling between the vehicles; s4, a self-triggering mechanism is introduced, and correct triggering of communication is ensured by designing a double-triggering threshold function; s5, establishing a prediction model of the vehicle formation; and S6, the distributed model prediction controller controls accurate implementation of a formation transformation strategy. According to the invention, through combination of a self-triggering mechanism and distributed model prediction control, the control efficiency and precision of the unmanned vehicle formation are significantly improved; compared with the traditional method, the communication frequency is reduced, and the communication burden is reduced by 5%; when the vehicle runs on a curve, the vehicle track error is reduced and is 4% more accurate than that of a traditional method.

The invention relates to the technical field of intelligent vehicle remote driving safety monitoring, in particular to a cloud cabin safety officer fatigue identification early warning method and system under a multi-vehicle supervision scene, and the method comprises the steps: constructing a differentiated sub-model system under different person-to-vehicle ratio scenes through an LSTM model-attention mechanism; generating a personalized fatigue identification sub-model adapted to a fatigue rule in each person-to-vehicle ratio scene; performing fatigue feature extraction on the corresponding multi-modal data by each personalized fatigue identification sub-model, and outputting a sub-fatigue identification result; fusing the parameter information of each personalized fatigue identification sub-model through multi-task federal learning, and generating a global fatigue identification model; and integrating the fatigue characteristics and the sub-fatigue identification results of the individual fatigue identification sub-models through a global fatigue identification model to obtain a comprehensive fatigue identification result. According to the invention, the accuracy and robustness of fatigue identification can be improved, and the risk of remote driving supervision failure caused by fatigue is reduced.

A high-order driving auxiliary lane changing trajectory planning method for an intelligent vehicle comprises the steps that laser radar and camera data are obtained, and feature vectors of obstacles are extracted after the data are processed by an ISP at the front end of a chip of the intelligent vehicle; constructing a spatio-temporal joint attention network model, inputting the feature vector of the obstacle into the spatio-temporal joint attention network model, calculating an interaction weight between the vehicle and the obstacle through a self-attention mechanism, and synchronously outputting predicted trajectory distribution of the obstacle and a candidate planning trajectory cluster of the vehicle; introducing a dynamic game in the game theory, and constructing a comprehensive cost function in combination with the interaction weight to obtain a screened track; and taking the screened trajectory as an initial value, inputting the initial value into a rear-end quadratic programming optimizer on the premise of meeting vehicle dynamics constraints, carrying out numerical optimization solution, searching an optimal programming sequence, and finally finishing lane changing trajectory planning. According to the invention, the interactive perception capability and riding comfort of the intelligent vehicle in a complex traffic scene can be improved.

The invention relates to a park intelligent vehicle scheduling method and system, and the method comprises the steps: receiving vehicle reservation information, generating a vehicle parking space and elevator preliminary distribution scheme based on the reservation information and a current resource occupation state, carrying out the adjustment and optimization of the preliminary distribution scheme of a plurality of vehicles at a preset scheduling moment, and obtaining an updated distribution scheme, and when the vehicle arrives at the park, the distribution result of the vehicle is corrected based on the updated distribution scheme and the real-time resource occupation state. The system comprises a scheduling server, a plurality of data acquisition terminals which are respectively arranged at the entrance of a park, parking spaces, elevators and parking spaces, and a communication module which is connected with the scheduling server and the data acquisition terminals. By implementing the scheme, the preliminary allocation scheme is calculated in combination with the reservation information and the current resource occupation state, the multi-vehicle allocation scheme is adjusted at the preset scheduling moment, and the final allocation scheme is generated based on the real-time state when the vehicles arrive, so that the capability of coping with arrival time fluctuation and temporary operation change is improved.

The invention discloses a double-level decision-making method of an urban expressway autonomous lane changing system, which comprises an upper-level decision-making method and a lower-level decision-making method, the upper-level decision-making method is used for calculating lane passing efficiency, and the lower-level decision-making method is used for analyzing lane changing safety. According to the method, a closed-loop behavior decision-making system of lane keeping-lane changing preparation-lane changing execution is constructed, the driving behavior of the intelligent vehicle can be described more accurately, and a clearer framework is provided for subsequent decision-making control. According to the method, the lane passing efficiency driving strategy is adopted for the autonomous lane changing intention, quantification and modeling are carried out by referring to the psychological mechanism that a human driver generates the lane changing intention when encountering a low-speed front vehicle, the decision logic under the actual driving situation is better met, and the intelligent vehicle lane changing decision is more reasonable and humanized. The invention provides a depreciation function calculation method, the influence of the traffic condition on the vehicle driving efficiency can be meticulously measured from the lane level, and a more scientific and more targeted basis is provided for intelligent vehicle lane changing decision making.

A method and apparatus for planning a vehicle driving path, and an intelligent vehicle and a storage medium, which relate to the field of autonomous driving. The method comprises operations such as acquiring a first pre-planned path, generating a first path on the basis of the first pre-planned path and the turning capability of a vehicle, and controlling the vehicle to travel along the first path, wherein the first pre-planned path is a pre-planned path between a road entrance and a road exit in a target intersection, the first path is a travelling path between the road entrance and the road exit, the first path comprises at least two arc-shaped road sections, and the distance between the road entrance and the road exit is less than twice the turning radius of the vehicle. Therefore, a vehicle can complete a one-time U-turn operation along a first path, thereby achieving the effect of improving the capability of autonomous driving in terms of U-turn scenarios at intersections.

The invention relates to the technical field of intelligent vehicle keys, in particular to an intelligent vehicle key-oriented remote unlocking system and a secure communication method thereof, and the system comprises an intelligent terminal module, a vehicle control module, a cloud server module, a security authentication module, an encryption communication module and a state feedback module; a real-time state feedback mechanism allows a user to know the state of the vehicle door lock at any time, once an abnormal condition occurs, an alarm mechanism is triggered immediately, the user is notified through multiple channels, and it is ensured that the user can take actions rapidly to protect property safety of the user.

The invention discloses a multi-modal terrain recognition method and system for an electric all-terrain vehicle, and relates to the technical field of intelligent vehicle sensing recognition, and the method comprises the steps: collecting a visual image, a laser radar point cloud and IMU dynamic data of a vehicle, and forming a time sequence multi-modal data set; performing feature extraction and time sequence modeling through a neural network model based on the time sequence multi-modal data set, and outputting a current terrain label and future terrain change trend information; according to the current terrain label and future terrain change trend information, preliminarily evaluating the terrain risk through a multi-index weighted scoring method and XGBoost; based on the preliminary terrain risk result and the tire state parameters, a final terrain risk value is obtained through a conflict detection mechanism by adopting a belief propagation and label reconstruction mode; according to the method, feature extraction and time sequence modeling are carried out on the time sequence multi-modal data through the neural network, accurate terrain tag identification and future change trend prediction are realized, and the accuracy and timeliness of identification are improved.

The invention relates to the technical field of intelligent vehicles, in particular to an intelligent vehicle automatic driving formation obstacle avoidance control method and device, and the method comprises the steps: constructing an intelligent vehicle formation controller according to the destination data and obstacle data of a target intelligent vehicle formation, so as to control the target intelligent vehicle formation to move towards the destination; establishing an intelligent vehicle formation space-time transformation strategy based on the queue expansion coefficient according to the queue expansion coefficient of the target intelligent vehicle formation and the driving safety boundary; performing dynamic optimization on the intelligent vehicle formation controller by adopting a Levy flight random search logic based on a cuckoo algorithm to obtain an optimized intelligent vehicle formation controller; and controlling the target intelligent vehicle formation to avoid obstacles by using the optimized intelligent vehicle formation controller and the intelligent vehicle formation space-time transformation strategy based on the queue expansion coefficient. Therefore, the problems that when intelligent vehicle formation obstacle avoidance is carried out through a traditional artificial potential field method, local minimum value and obstacle avoidance track jittering are likely to happen, and complex dynamic environments cannot be rapidly adapted are solved.

The invention discloses a portable fatigue driving monitoring and early warning system, and relates to the technical field of fatigue early warning. Comprising an acquisition module, a control module, a reminding module and a power module. The input end of the control module is connected with the output end of the acquisition module, and the output end is connected with the reminding module. Fatigue state judgment and intervention are carried out by collecting and analyzing the forehead lobe single-channel electroencephalogram signals of the user on the basis of integrated independent equipment, the process does not need to depend on intelligent terminal equipment such as an intelligent vehicle, an intelligent mobile phone or a cloud server, and power consumption and system complexity are reduced. The invention provides a set of non-electroencephalogram signal component identification and elimination method based on independent component energy spectrum, spectrum entropy and correlation analysis, interference of artifacts such as eye movement and myoelectricity is effectively inhibited, and the accuracy and reliability of fatigue monitoring of portable equipment are improved.

The invention discloses an intelligent vehicle elastic planning and control method based on large language model guidance under network attack, and belongs to the field of vehicle information safety and control, and the method specifically comprises the steps: firstly, building an intelligent vehicle auxiliary decision making and control system, and installing the system on a to-be-detected vehicle; the automatic driving decision-making unit generates an expected driving intention of the current to-be-detected period; the path planning unit generates a corresponding reference trajectory sequence. A vehicle reachable set estimator calculates a maximum allowable motion reachable range. The scene text editor completes scene description of the driving environment in combination with the perception information and converts the scene description into a structured text; the large language model performs comprehensive judgment on an expected driving intention and a planned reference trajectory sequence based on a maximum allowable motion reachable range and structured text description, and gives a final auxiliary decision variable. And based on the reachable set estimation value, constructing a vehicle motion controller based on data driving, and obtaining a control instruction to complete execution. According to the invention, the adaptability and robustness of the real vehicle operation environment are improved.

The invention discloses an in-vehicle intelligent mosquito repelling method, and relates to the technical field of intelligent vehicle environment control, and the method comprises the steps: synchronously collecting in-vehicle multi-modal data through a sensor, and carrying out the preprocessing of the in-vehicle multi-modal data, and obtaining the preprocessed in-vehicle multi-modal data; a chemical mosquito repelling mode or a physical mosquito repelling mode is selected based on the preprocessed multi-mode data, and in-vehicle mosquito repelling control is carried out; the mosquito density at the air outlet of the air conditioner is calculated, and if the mosquito density in the unit volume exceeds the preset density, an ultraviolet LED lamp is turned on for catalytic decomposition of dimethyl phthalate residues in the air; according to the method, historical driving data of a user is obtained through a vehicle-mounted T-BOX, an LSTM neural network is adopted for mosquito occurrence probability prediction, a pre-mosquito-repelling request is pushed to a user mobile terminal according to a prediction result, and in-vehicle intelligent mosquito repelling based on multi-modal sensing is completed. Efficient, safe and low-pollution mosquito repelling measures are achieved, response can be conducted quickly, and the health and comfort of passengers are guaranteed.

An intelligent chassis drift collision avoidance control method and system and an electronic and electrical architecture. The method comprises: performing quantitative analysis on collision avoidance requirement information by means of an obstacle envelope method so as to obtain obstacle envelope data; calculating a normal operation infeasible state domain of the obstacle envelope data on the basis of a vehicle dynamics model; performing safety analysis on the basis of the normal operation infeasible state domain, so as to determine, on the basis of a safety analysis result, whether to start an extreme collision avoidance operation; and if it is determined that the extreme collision avoidance operation is started, performing autonomous decision-making control of a vehicle on the basis of extreme dynamics control input data generated by a chassis domain control platform, so as to achieve drift collision avoidance. The method can give full play to the collision avoidance potential of vehicles, and improve the emergency response capability and backup level of intelligent vehicles.

The invention relates to the technical field of intelligent traffic and auxiliary travel, and discloses a multi-modal space-time fusion intelligent vehicle danger pre-judgment method and system, and the method comprises the steps: obtaining multi-modal sensing data around an intelligent vehicle, constructing a deep learning-based danger pre-judgment model which comprises a space-time fusion module and a risk evolution module; the space-time fusion module carries out space-time alignment and fusion on multi-modal sensing data to obtain unified space-time voxel features, and the space-time alignment and fusion processing process is focused on a high-uncertainty region through the risk attention gating module. The risk evolution module identifies objects around the intelligent vehicle according to the space-time voxel features, and predicts the motion trails and potential collision risks of the objects; and performing real-time danger judgment on the intelligent vehicle by using the world model distillation danger pre-judgment model and the post-distillation danger pre-judgment model. According to the invention, various sensing data can be effectively fused to carry out danger judgment in the vehicle driving process, and the judgment accuracy is improved.

Presented are intelligent vehicle systems for provisioning backup power to buildings during power outages, methods for making / using such systems, and vehicles equipped with such systems. A method of operating a vehicle includes a resident or remote vehicle controller detecting a charging port of the vehicle coupling to a charging plug of an electric vehicle supply equipment (EVSE). Responsive to the charging plug coupling to the charging port, the vehicle controller detects a power outage of a main power supply to the EVSE. Upon detecting the power outage, the controller responsively commands a vehicle battery assembly to discharge an auxiliary power feed to the EVSE. After discharging the auxiliary power feed to the EVSE, the controller determines if the vehicle is communicating with the EVSE; if so, the vehicle controller responsively commands the vehicle battery assembly to discharge a backup power feed, greater than the auxiliary power feed, to the EVSE.

The invention relates to the technical field of path navigation, in particular to an intelligent vehicle path planning navigation system fused with Beidou positioning, which comprises an information initial path module, a road condition information module, a risk assessment module, a local environment module, a path optimization module and a path determination module, and is characterized in that the initial position of a vehicle is determined, and an initial navigation path is constructed; generalized environment event information covering a front area in the initial navigation path is received, and dynamic road condition information is obtained; calculating an overlap ratio between a geographical influence range in the generalized environment event information and a spatial-temporal trajectory in the initial navigation path, and when the overlap ratio exceeds a threshold value of the dynamic road condition information, obtaining a specific risk assessment result; analyzing the whole-body real-time condition of the vehicle to determine local environment data; performing path re-planning decision on the initial navigation path to obtain an optimized navigation path; inputting the optimized navigation path to a terminal of the vehicle; according to the invention, the accuracy of intelligent vehicle path planning navigation fused with Beidou positioning can be improved.

A utility vehicle including a housing configured for storing goods therein during transport. A handlebar extends into a chassis sleeve defined by a chassis. The handlebar is slidably moveable forward and backward within the chassis sleeve. A sensor includes a flexible member having a first end mounted to the chassis sleeve and a second end mounted to the handlebar. The sensor is configured to sense a magnitude and a direction of a force exerted on the handlebar by an operator. A control module is in communication with the sensor and a motor. The control module is configured to control motor speed and motor direction of the motor based on the magnitude and the direction of the force exerted on the handlebar by the operator as sensed by the sensor.

The invention relates to the field of intelligent vehicles, and discloses a vehicle-mounted intelligent oxygen supply system and method, a vehicle and a storage medium. The system comprises a signal acquisition module used for acquiring an original respiration signal of a user; the AI processing module is used for preprocessing the original breathing signal to obtain a preprocessed breathing signal, extracting breathing characteristics of the user from the preprocessed breathing signal, learning the breathing characteristics of the user by utilizing a preset machine learning model, predicting a breathing mode of the user and generating a corresponding control signal; and the oxygen supply execution module is used for adjusting oxygen output parameters according to the control signal and outputting corresponding oxygen flow according to the oxygen output parameters. Through cooperation of all the modules, the technical effects that the oxygen utilization rate is greatly increased, the use comfort is remarkably improved, and breathing health is monitored in real time are achieved.

Systems and methods for implementing smart in-vehicle conferencing with user tracking and speaker prioritization. A controller system of a vehicle may determine, based at least in part on one or more cameras, a plurality of candidate best image sources, determine, from the plurality of candidate best image sources, a best image source for a speaker in the vehicle, determine, based at least in part on the best image source, a video feed, determine, based at least in part on one or more microphones, a plurality of candidate best audio sources, determine, from the plurality of candidate best audio sources, a best audio source for the speaker, determine, based at least in part on the best audio source, an audio feed, and provide, to a conference call line, the video feed and the audio feed.

The invention discloses a real-time cooperative task scheduling method and device for a vehicle-mounted operating system, and belongs to the field of intelligent vehicle-mounted systems and edge computing. The method comprises the following steps: collecting vehicle tracks and terminal and server state data in a vehicle-edge-cloud cooperative system in real time; using a PatchTST model to predict the future position of the vehicle based on the historical trajectory; constructing a collaborative scheduling model taking the vehicle and the edge server as intelligent agents; based on local observation, the vehicle agent generates an unloading decision, and the edge server agent generates a task migration decision; a multi-agent near-end strategy optimization algorithm for partial reward decoupling is adopted, and a strategy is optimized under a centralized training and distributed execution framework; task unloading, migration and dynamic result return are executed according to the decision; and calculating rewards based on the task completion condition and the system state, and continuously updating model parameters. According to the method, the task completion rate of vehicle-mounted task scheduling in a dynamic complex environment is effectively improved, and the average time delay is reduced.