1722 results about "Smart vehicle" patented technology

The invention discloses a vehicle multi-modal trajectory prediction method based on an improved attention network, and belongs to the technical field of intelligent vehicle trajectory prediction, and the method comprises the steps: collecting historical trajectory data of a target vehicle and surrounding vehicles as an input sequence; secondly, constructing a vehicle multi-modal trajectory prediction model which comprises a motion feature extraction module, a space-time interaction module, a space-time fusion module and a trajectory output module; the motion feature extraction module uses a multi-scale convolution attention network and a gating circulation unit for processing, the space-time interaction module uses a dynamic graph attention network for extracting vehicle interaction information, and the space-time fusion module splices and fuses target vehicle motion features and space-time interaction features to obtain space-time fusion features; the track output module inputs the fusion features into a gating circulation unit, decodes the fusion features and then inputs the fusion features into a mixed density network, and multi-mode output of vehicle tracks is achieved; and finally, a proper loss function is selected for training, so that the prediction precision and the convergence speed of the model are improved.

The invention discloses an intelligent vehicle extreme test scene generation method based on deep learning. The method comprises the following steps: building a hybrid generative adversarial network scene; collecting and preprocessing data; performing dynamic confrontation training; according to the extreme test simulation, an intelligent vehicle extreme test scene generation system based on deep learning comprises a hybrid generative adversarial network model, a data input module, a preprocessing module, an edge cloud module and an interaction module. A double-channel confrontation mechanism enables the risk controllability of a generated scene to be high, and dynamic confrontation training is carried out; a real multi-source data set is enhanced and labeled, the integrity of point cloud data is high through a point cloud missing region feature completion algorithm, and dynamic risk entry is effectively simulated by introducing a social force model into dynamic obstacle modeling; the multi-modal risk assessment network improves the assessment accuracy.

The invention discloses a control strategy model construction method based on big data, and relates to the technical field of intelligent control, a traffic situation deduction and emergency strategy generation module uses a multi-agent traffic simulation technology, simulates a traffic situation in combination with real-time traffic data, evaluates risks and early warns potential crisis by integrating multiple factors, and provides a control strategy model for the traffic situation deduction and emergency strategy generation module. And after an early warning is received, an emergency strategy is generated by using an intelligent algorithm, the strategy is evaluated and optimized by using virtual rehearsal, a result is fed back to a management department, and a synergistic effect with other modules is achieved. Traditional traffic detection equipment data is integrated with multi-source heterogeneous data such as mobile phone signaling, shared bicycle and online hailed bicycle GPS, intelligent vehicle-mounted equipment and public traffic operation, more comprehensive and accurate information such as traffic flow, flow direction, travel behavior track and the like is provided, and rich and accurate basis is provided for traffic management decisions.

The invention relates to the technical field of intelligent vehicle control, in particular to a loader vehicle control method and system, computer equipment and a storage medium. The method comprises the following steps: collecting multi-modal data of the loader, wherein the multi-modal data comprises working environment data, dynamic load state data and vehicle attitude data of the loader; constructing a three-dimensional operation scene digital twinborn model based on the multi-modal data, and predicting vehicle stability influence data of the influence of the load change on the vehicle stability based on the dynamic load state data; based on the digital twinborn model of the three-dimensional operation scene and the vehicle stability influence data, a dynamic control strategy is generated by utilizing a reinforcement learning algorithm, and cooperative actions of steering, lifting and walking mechanisms are synchronously optimized; according to operation environment data and a dynamic control strategy, hydraulic system pressure and motor torque distribution are adjusted in a self-adaptive mode, and operation efficiency and safety are ensured.

The invention provides a scene adaptive projection vehicle lamp system based on deep reinforcement learning and a control method, and relates to the technical field of intelligent vehicle lamps and automatic driving perception systems. Comprising a multi-modal sensing module, a feature fusion module, a strategy generation module and an execution module. The multi-mode sensing module is used for collecting environment state data and performing primary processing to form an environment data information flow; the feature fusion module is used for generating a unified environment feature vector for the environment data information flow; the strategy generation module is used for receiving the environment feature vector and generating a vehicle lamp adjustment strategy through multi-layer neural network calculation; evaluating a result obtained by executing the vehicle lamp adjustment strategy based on the vehicle lamp, and optimizing strategy parameters of the strategy network based on a PPO algorithm; the execution module is used for controlling the vehicle lamp according to the vehicle lamp adjustment strategy output by the strategy network. The intelligent level of the vehicle lamp is remarkably improved, and the system is widely applied to night driving assistance, urban interaction prompt and low-visibility driving scenes.

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 discloses an intelligent vehicle-mounted application adjusting method and system based on a driving scene, and relates to the field of vehicle-mounted application, and the method comprises the steps: obtaining current real-time driving data, current external environment information and current position information, and matching a user behavior mode of a current vehicle in a preset behavior mode database according to the current real-time driving data, identifying a driving scene of a current vehicle according to the current external environment information and the current position information, and predicting an information type and a presentation mode required by a current driver according to the user behavior mode and the driving scene, and determining an information presentation mode and information presentation time in a preset application database according to the information type and the presentation mode, and presenting all the vehicle-mounted applications according to the information presentation mode and the information presentation time, and by implementing the method, the driving experience of a driver can be improved in a complex driving scene.

The invention relates to a vehicle queue cooperative control method fusing deep reinforcement learning communication time delay compensation, and belongs to the technical field of intelligent vehicle control. For the problems of control error accumulation and queue instability caused by communication time delay in the vehicle-road cloud cooperative system, a solution integrating deep reinforcement learning prediction and preset performance control is provided. According to the technical scheme, the method comprises the following steps: constructing a vehicle state prediction model based on a DDPG algorithm, and generating a time delay compensation amount in real time; establishing a vehicle dynamics model containing communication time delay, and designing a sliding mode controller based on a barrier function; and dynamically adjusting the control constraint in combination with an adaptive error boundary mechanism. According to the method, through closed-loop fusion of prediction compensation and dynamic constraint, under the scene of burst communication delay (100-400 ms), the queue spacing error is reduced by 62%, the speed tracking error is still kept to be smaller than 0.3 m / s, and the queue stability and the anti-jamming capability are remarkably improved.

The invention relates to the technical field of electric vehicle control, in particular to an AI-based electric vehicle intelligent starting and acceleration control method and system. The method comprises the following steps: acquiring a driving log of a vehicle owner, performing intelligent vehicle optimization after starting, and constructing an intelligent starting mode selection strategy; physiological state data of a driver are obtained, state change evolution analysis is carried out, and a personalized driving portrait is constructed; holographic state sensing and vehicle virtual simulation are carried out, and a vehicle synchronous digital simulation model is constructed; radar feedback sensing information and a real-time monitoring image in front of a vehicle are collected, traffic situation prediction and vehicle scene prediction and perception are carried out, and a vehicle scene prediction and perception model is constructed. According to the method, the driving starting mode of the vehicle is intelligently selected, vehicle owner requirements and environment available power constraints are matched, and vehicle acceleration efficiency maximization and safety optimization are achieved.

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 relates to a combinable modular automobile emergency power supply, and relates to the technical field of new energy automobiles and intelligent vehicle-mounted power supplies, and the combinable modular automobile emergency power supply comprises a standardized power supply module, a modular connection mechanism and an intelligent management system. Each group of standardized power supply module is an independent unit, is internally provided with a lithium ion battery, is uniform in size and is provided with a standard interface, two sides of the standard interface are provided with magnetic attraction type contacts, one side of each magnetic attraction type contact is provided with a buckle type physical lock catch, a main control chip is integrated, and the electric quantity, temperature and output state of the module are monitored in real time; output voltage and dynamic load balance are dynamically adjusted, so that the standardized power supply modules can be combined into a power supply pack, multiple protection mechanisms are provided, output is dynamically adjusted through a PID algorithm, safety is ensured in combination with a triple protection mechanism, and high-temperature stable operation is achieved in cooperation with a temperature control fan; and reliable connection is ensured through double verification of the magnetic contacts and the Hall sensors.

The invention relates to the field of artificial intelligence, and provides a distributed reasoning method, device and equipment based on a hybrid expert architecture, and a medium, and the distributed reasoning method based on the hybrid expert architecture applied to an edge computing power gateway comprises the steps: determining a plurality of target intelligent vehicles participating in a reasoning task if the reasoning task is received; obtaining an expert reasoning model, and deploying the expert reasoning model to each target intelligent vehicle; wherein the expert reasoning model comprises a plurality of expert reasoning modules, and at least one expert reasoning module is deployed in each target intelligent vehicle; sending the reasoning task to each target intelligent vehicle, so that each target intelligent vehicle executes the reasoning task based on the expert reasoning module to obtain a reasoning result; and aggregating the reasoning results of the target intelligent vehicles to obtain a target reasoning result. Through the technical scheme provided by the invention, the computing power resource of the idle intelligent vehicle is fully utilized.

The invention discloses an intelligent vehicle automatic parking path planning optimization method, system and device and a storage medium. The method comprises the following steps: planning a parking path of a vehicle from a current position to a target parking space by using a search algorithm; a virtual parking environment is constructed, a simulation test is carried out in the virtual parking environment, different parking scenes and environment changes are simulated, and whether a parking path is safe or not is verified; when the parking path is verified to be safe, the vehicle is controlled to be parked according to the parking path; and when the vehicle is parked, the environment change is monitored in real time through a sensor, and the parking path is dynamically adjusted by using a path-finding algorithm and reinforcement learning. An A * algorithm is used for carrying out preliminary path planning and optimization, the reliability of the algorithm is verified through simulation testing, path planning and control strategies are continuously optimized, environment changes are monitored in real time and paths are dynamically adjusted by fusing data of various sensors such as a laser radar, a camera and an ultrasonic radar, and it is ensured that a vehicle safely avoids obstacles.

The invention relates to the technical field of intelligent traffic, in particular to an intelligent networked PHEV multi-driving-mode autonomous decision control method based on deep learning. The method comprises the steps of designing a state space and an action space based on a deterministic strategy gradient algorithm by constructing three driving modes of a cruise scene, a car-following scene and a passing scene; a multi-target award function is constructed for driving safety, riding comfort and energy consumption economy, a Markov decision process is utilized to construct a multi-target driving mode autonomous decision control model, and it is ensured that when the intelligent network connection PHEV is driven in a complex environment, the optimal target vehicle speed can be planned by autonomously deciding different driving modes. The comprehensive optimization of safety, trafficability and energy consumption economy of the intelligent networked PHEV in the driving process is realized, and the decision-making ability of the intelligent vehicle in a complex traffic environment is further improved.

The invention discloses an intelligent vehicle maintenance management system and method based on big data analysis, and relates to the technical field of intelligent vehicle maintenance, and the method comprises the following steps: collecting various kinds of vehicle driving data in real time in the vehicle driving process through a data collection device, and providing a reliable basis for subsequent analysis and decision making. Through real-time analysis of vehicle driving data and combination of a machine learning model, the system can dynamically adjust the detection frequency and the maintenance strategy, and it is ensured that maintenance better fits the actual use environment. For a rugged road surface, the system accurately recognizes a high-risk state according to the impact load, the vehicle body rolling acceleration and other characteristics, early warning is conducted in time, the maintenance frequency is optimized, excessive maintenance is avoided, meanwhile, the safety is improved, and the maintenance cost is reduced.

The invention relates to the technical field of vehicle lamp systems, in particular to an intelligent vehicle lamp system based on DLP projection, a control method and a vehicle. The intelligent vehicle lamp system based on DLP projection comprises an optical system, an intelligent control system, an execution module and a power management system, the system collects environment data in real time through a sensor, a central processing unit fuses multi-source information and generates a control instruction through an AI algorithm, and the light source brightness, the irradiation angle and the road surface projection content are dynamically adjusted; meanwhile, voice interaction and remote control are supported, and the self-adaptive lighting and safety warning functions are achieved. Through the intelligent control and DLP projection technology, the vehicle lamp performance is improved, the lighting effect is optimized, and the night driving safety is enhanced; self-adaptive adjustment is realized, and the driving experience is improved; the energy consumption is reduced by more than 30%; the battery life is prolonged; v2X communication is supported, and intelligent early warning is realized; a voice control function is provided, and operation is more convenient and safer; a road surface projection function is added, navigation arrows and warning marks can be displayed, and visual driving assistance is provided.

The invention provides a tunnel congestion node real-time estimation method and system based on digital twinning, and the construction of a digital twinning system physical scene of a tunnel is realized based on a Unity engine and SUMO software by determining the spatial characteristics, traffic information, camera information and the like of the tunnel. And then, dynamic and static data information of the vehicle is obtained through a CornerNet image detection network and a Deepsort tracking algorithm, the driving condition of the lost vehicle is deduced and simulated according to an acceleration distance control car-following model and a safe distance lane changing model, and dynamic target projection and full tracking of the digital twin system are realized based on an improved Hungary algorithm. And finally, node division of vehicles in the tunnel is realized according to the proposed intelligent traffic flow node model, node saturation is introduced, a node coupling congestion identification model is proposed, and tunnel congestion event sensing and congestion node positioning are realized. According to the invention, on one hand, traffic management resumption in the tunnel can be carried out by means of the digital twin system, and the congestion process and reasons are deeply analyzed; and on the other hand, the traffic flow congestion condition in the tunnel can be detected in real time, and the congestion node can be determined, so that the congestion traffic flow can be dredged in advance, and the accident occurrence probability in the tunnel can be reduced. And the method is of great significance to future digital and intelligent traffic flow research.

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 provides an intelligent vehicle lane changing trajectory planning method based on model predictive control, which comprises the following steps: firstly, sensing environment information in real time, calculating an emergency braking distance and an expected safety distance, and deciding behaviors of an intelligent vehicle; secondly, on the basis that a vehicle point quality model serves as a prediction model, an improved artificial potential field method and a model are combined to predict, control and plan a lane changing track, and the current optimal lane changing reference track selected from the sine lane changing reference track cluster is included; and finally, tracking the trajectory by adopting a trajectory tracking controller based on model predictive control. The improved artificial potential field method is adopted to fully adapt to the position, speed and acceleration changes of surrounding obstacle vehicles, the dynamic obstacle avoidance effect is remarkable, and the lane changing safety of the intelligent vehicle is guaranteed; the situations of following the front vehicle, canceling lane change and the like are also considered, and the adaptive scene is wider.

Systems and methods for on-board selection of data logs for training a machine learning model. The methods include, by an autonomous vehicle, receiving sensor data logs corresponding to surroundings of the autonomous vehicle from a plurality of sensors, identifying one or more events within each sensor data log. The methods also include, for each sensor data log: analyzing features of the identified one or more events within that sensor data log for determining whether that sensor data log satisfies one or more usefulness criteria for training a machine learning model, and transmitting that sensor data log to a remote computing device for training the machine learning model if that sensor data log satisfies one or more usefulness criteria for training the machine learning model. The features can include spatial features, temporal features, bounding box inconsistencies, or map-based features.

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 discloses an intelligent automobile lamp assembly which is used in the technical field of automobile lamps and comprises a sensor module, an instrument prompting module, a processing module, an intelligent light control module and an executing mechanism. The sensor module is used for collecting key data of a vehicle state and an external environment; the instrument prompting module is used for displaying the state of the vehicle lamp system and information related to driving in real time; the processing module is used for analyzing the vehicle state and the key data of the external environment and generating a vehicle lamp adjusting strategy; the intelligent light control module is used for receiving the vehicle lamp adjusting strategy and converting the vehicle lamp adjusting strategy into a specific control instruction; and the execution mechanism is used for executing the control instruction and adjusting the brightness and direction of the vehicle lamp based on the control instruction. Based on the fuzzy logic reasoning method, complex and fuzzy data input can be processed, the vehicle lamp adjustment strategy is flexibly generated according to different driving conditions, and vehicle lamp adjustment has better scene adaptability.

Disclosed are systems, apparatuses, processes, and computer-readable media for wireless communications. For example, an example of a process includes receiving, by an onboard unit (OBU) of a vehicle, sensor data from a plurality of sensors of the vehicle. The process may include determining, by the OBU based on the sensor data, a score level for an event associated with the vehicle. The process may further include determining the score level is greater than a threshold score level and, based on the score level being greater than the threshold score level, broadcasting an alert message related to the event to one or more devices.

The embodiment of the invention provides an intelligent vehicle scheduling method based on multi-factor dynamic optimization, and the method comprises the steps: a data collection step, which is used for collecting orders, vehicles, drivers and external environment time, and carrying out the cleaning and standardization processing of the data; a scheduling algorithm determination step: according to the data output in the data collection step, raising a preliminary scheduling and route planning scheme; initial constraints and targets are set, and optimization targets are set; operating an optimization algorithm to iteratively solve an optimal scheme; wherein the optimization targets include but are not limited to reduction of transportation time, reduction of cost and improvement of service quality; the scheme evaluation step is used for evaluating the candidate schemes output by the scheduling algorithm determination step in a multi-dimensional mode, selecting an optimal scheduling scheme and issuing a scheduling instruction; and a monitoring and feedback step: monitoring the data of the vehicle and the transportation process through the Internet of Things equipment and the sensor, and dynamically adjusting the optimal scheduling scheme in real time according to the data.

A lane-changing trajectory planning method, an autonomous driving method, and a related apparatus. The autonomous driving method comprises: on the basis of first motion state information of an intelligent driving device and second motion state information of an opponent, controlling the intelligent driving device to change to a target lane within a first lane-changing time period and to be located in front of the opponent, wherein the opponent is located on the target lane for the intelligent driving device, and is located between a first position and a second position, wherein the first position is located behind the intelligent driving device and longitudinally distant from the intelligent driving device by a first distance, and the second position is located in front of the intelligent driving device and longitudinally distant from the intelligent driving device by a second distance. The technical solution of the present application can be applied to intelligent vehicles such as a new energy vehicle and an electric vehicle, and facilitates improvement of lane-changing success rates and traffic efficiency when the vehicles are in an autonomous driving mode in complex lane-changing scenarios such as merging into congested roads and merging into ramps.

The invention belongs to the technical field of intelligent driving decision, and discloses a no-signal crossroad intelligent vehicle decision method, which comprises the following steps: constructing a no-signal crossroad intelligent vehicle decision model including a strategy network and a value network; each of the strategy network and the value network is composed of an LSTM neural network and a full connection layer; the method comprises the following steps of: forming state parameters by self-vehicle information, traffic participation vehicle information, relative position information of a traffic intersection and a self-vehicle and relative position information of a target task point and the self-vehicle from a # imgabs0 # moment to a # imgabs1 # moment as input variables of a strategy network; using an accelerator control signal, a steering wheel angle control signal and a brake control signal corresponding to the # imgabs2 moment state parameter to form an action parameter as an output variable of the strategy network; optimizing the decision model by adopting a PPO algorithm and taking the minimum loss function of the strategy network and the value network as an optimization target to obtain an optimal decision model; and outputting a vehicle decision by using the optimal decision model.

The invention relates to an intelligent car insurance quotation system based on multi-modal data processing. The intelligent car insurance quotation system comprises a multi-source data acquisition module, a risk domain construction module and a dynamic quotation module, the multi-source data acquisition module analyzes the driving behavior characteristics, the vehicle condition characteristics and the driving environment characteristics of the target vehicle based on the acquired image data, the structured text data and the sensor time sequence data; the risk domain construction module constructs a driving behavior risk curve of the target vehicle based on the driving behavior characteristics, constructs a vehicle condition risk curve of the target vehicle based on the vehicle condition characteristics, and then constructs a driving environment risk curve of the target vehicle based on the driving environment characteristics. And finally, constructing a dynamic quotation domain of the target vehicle based on the driving behavior risk curve, the vehicle condition risk curve and the driving environment risk curve. And the dynamic quotation module performs quotation analysis on the dynamic quotation domain to obtain the vehicle insurance quotation of the target vehicle.

The invention belongs to a man-machine cooperative control technology in the field of intelligent driving, and particularly discloses a lane departure early warning and correction method based on driver behavior prediction. And in combination with vehicle state parameters (such as vehicle speed, yaw velocity, lane departure distance and the like), a Transformer-CNN hybrid model is adopted to predict the steering intention of the driver, so that accurate behavior judgment is realized. Multi-source data are fused through a graph neural network (GNN), the lane departure risk is dynamically evaluated, integration with an electric power steering system (EPS) is achieved, damping and torque of a steering wheel are adjusted in real time, and a vehicle is actively corrected to a safe lane. Meanwhile, the system provides multi-mode early warning such as sound, vibration and head-up display (HUD) according to the risk level, and it is ensured that a driver responds in time.

The invention relates to a dynamic path planning method in a PFC-DWA complex environment based on an improved DWA algorithm, and belongs to the technical field of intelligent driving. The method is a window reduction algorithm for dynamic prediction in an environment with a large scene change rate. According to the algorithm, the kinematics constraint of the Ackerman steering trolley is considered, a dynamic obstacle collision evaluation window reduction strategy according to the dynamic obstacle and intelligent vehicle motion state information is provided, the dynamic window range is optimized through the motion state information and a kinematics constraint equation by using an analytic geometry method, and the dynamic obstacle avoidance capability of the intelligent vehicle is improved. In order to solve the problem that the evaluation function of the DWA algorithm lacks evaluation of the obstacle state change trend, the proposed algorithm predicts the future position information of the obstacle based on the least square method according to the historical position information of the obstacle, the future position information is fused into the evaluation function of the algorithm, and the evaluation performance of the algorithm on the simulated trajectory in the dynamic environment is improved. The problem of low arrival rate of a path planned by a conventional algorithm in a frequent scene change environment is solved.