4087 results about "Trajectory planning" patented technology

The invention relates to an automatic driving vehicle trajectory planning method, which comprises the following steps of: extracting comprehensive spatio-temporal information representation of a driving scene from automatic driving multi-modal data by adopting an end-to-end branch, and predicting and generating a trajectory sequence predicted by a vehicle in a future set time period; a visual language model branch is adopted to embed visual features related to the text instruction into a large language model, and a plurality of different track sequences in a future set time period are obtained through prediction; and fusing the trajectory sequences output by the two branches according to the loss value and the danger situation of the current driving scene to obtain a final planning trajectory. Compared with the prior art, the method has the advantages of high safety and reliability.

The invention discloses a concrete surface intelligent construction method and system based on multi-modal sensing. The method comprises the following steps: firstly, receiving multi-source sensing data, and generating standardized feature data and defect feature vectors through standardization processing and feature extraction; performing time sequence alignment processing on the sensing data, and generating time sequence alignment data in combination with multi-scale analysis; constructing a state evaluation model based on the dynamic Bayesian network, and generating an environment state vector and a construction difficulty graph; carrying out region segmentation and optimizing task allocation by adopting a spectral clustering algorithm, and generating a task allocation scheme and a collaboration strategy; then, construction parameters are determined through multi-objective optimization, tool configuration is planned, and an optimization parameter set and a tool configuration scheme are generated; and finally, trajectory planning is carried out based on an improved A * algorithm, and a multi-robot cooperative construction trajectory is generated through comprehensive optimization. Full-process control of intelligent construction of the concrete surface is achieved, and the construction quality and efficiency are improved.

The invention provides a remote operation space manipulator trajectory planning method based on deep reinforcement learning (DRL). The trajectory planning problem caused by communication delay is effectively solved. The method comprises the steps that a kinematic model and a reinforcement learning framework of the rigid mechanical arm are established; constructing a teleoperation framework comprising a master end, a data chain and a slave end; a delay processing module (DIP) is adopted at a main end to process communication delay, so that the real-time performance of states and rewards is ensured; a DRL decision module is utilized to update the intelligent agent, and learning is carried out based on an experience playback pool and an action playback pool; the mechanical arm is guided to complete the task through interaction of the intelligent agent and the environment. According to the method, the DRL is integrated into the remote control framework, so that the decision-making ability of the intelligent agent is enhanced, the performance is excellent especially in an inherent delay environment, good robustness is shown under different noise and dynamic parameter conditions, and additional parameter adjustment is not needed.

The invention discloses an unmanned aerial vehicle trajectory planning and tracking method, system and device based on deep reinforcement learning and adaptive nonlinear model predictive control, and a medium. The method comprises the following steps: constructing various static multi-obstacle and dynamic multi-obstacle simulation environments; constructing a kinetic model of the unmanned aerial vehicle; constructing an adaptive nonlinear model predictive control (ANMPC) algorithm; constructing a reward function of the tracking performance of the unmanned aerial vehicle to the reference trajectory generated by the adaptive nonlinear model predictive control algorithm; constructing a network framework based on deep reinforcement learning and an adaptive nonlinear model predictive control algorithm; setting network parameters; training a network framework, and selecting an optimal weight file; outputting a test result; the system, the device and the medium are used for realizing the unmanned aerial vehicle trajectory planning and tracking method. The method can effectively cope with changes of targets and environments, shows strong obstacle avoidance capability and anti-interference performance when facing dynamic obstacles and wind noise interference, and embodies a high intelligent decision-making level.

This document describes trajectory planning in a three-dimensional (3D) search space with a space-time artificial potential field. An example system includes a processor that obtains an initial pose, a goal pose, and an obstacle map for an environment. The processor uses a parking trajectory algorithm to determine a trajectory by searching in a space-time artificial potential field. The trajectory includes a series of 3D waypoints, including two-dimensional (2D) positional coordinates and time coordinates, to navigate from the initial pose towards the goal pose. Operation of the host vehicle is then controlled to maneuver along the trajectory using an assisted-driving or autonomous-driving system. In this way, path searching is performed in the entire 3D search space rather than iterating between two 2D search planes. This allows motion planning for autonomous parking, especially with static and dynamic objects present, to determine an optimal trajectory in a single iteration.

The embodiment of the invention relates to robot path planning, in particular to a self-adaptive robot trajectory planning method and system based on deep reinforcement learning, and the method can completely present the motion condition of a robot by obtaining a real-time trajectory data set covering an environment interaction state and a motion attitude sequence; key features can be accurately extracted through dynamic track feature extraction processing; a self-adaptive trajectory optimization strategy is generated based on a pre-trained deep reinforcement learning strategy network, so that the strategy can be flexibly adjusted according to dynamic characteristics; incremental trajectory correction processing is carried out on the robot motion posture sequence, the trajectory can be optimized step by step, and an optimized trajectory sequence conforming to dynamic environment adaptability is generated; and the optimized trajectory sequence is synchronized to the motion control system, so that the robot can quickly and accurately execute the optimized trajectory, and the motion planning capability and execution efficiency of the robot in a complex dynamic environment are remarkably enhanced.

Disclosed in the present invention are a multi-agent vehicle-road-cloud integrated collaborative decision-making and control architecture system and method based on federated reinforcement learning. A multi-agent federated reinforcement learning decision-making and control framework having embedded vehicle dynamics characteristics is used, so as to solve the problem of in-depth integration of an intelligent traffic system and intelligent vehicles, and realize autonomous driving with vehicle-traffic in-depth decision-making and control collaboration; a semantic matrix is generated at a road side to serve as an input for vehicle-side reinforcement learning, so as to construct vehicle-side global and local trajectory planning guided by the road side; an integrated reward function for vehicle-side reinforcement learning is designed on the basis of a driving safety field constructed by the road side, so as to realize comprehensive consideration of vehicle-side safety and comfort; on the basis of road-side federated learning, vehicle-side neural network parameters are uploaded by means of V2I communication, so as to solve the problem of vehicle-road information asymmetry caused by privacy awareness; and for different environmental sample distributions, a local optimal policy for a current environment is selected by means of neural network screening, so as to synthesize a shared model benefiting from different environments, thus realizing a balance between sample efficiency and model robustness.

The invention provides a reinforcement learning-based desilting strategy optimization method and system, and relates to the technical field of intelligent water area desilting, and the method comprises the steps: carrying out the multi-scale decomposition, adaptive histogram equalization, contrast optimization and edge sharpening processing of a collected image, and obtaining an optimized desilting environment image; then constructing a three-dimensional voxel grid model based on the optimized image, and establishing an environment interference source mathematical model and a dynamic evolution rule of sludge distribution; and finally, inputting the image features into a dredging strategy optimization network, through interaction with a simulation environment, updating network parameters based on a dual time sequence difference algorithm, generating a motion track planning scheme and an operation parameter configuration scheme of the dredging robot, and optimizing a value function on line according to an actual dredging effect. The desilting efficiency can be effectively improved, and the desilting cost is reduced.

The disclosure provides a method and system for trajectory tracking control of a vehicle-manipulator coupling system with finite time prescribed performance. Specifically, a coupling weaken trajectory planning method is designed to reduce the system's coupling effects. A finite time performance function is designed to constrain the trajectory tracking error. In a case the constraint conditions corresponding to the finite time performance function are satisfied, the trajectory tracking error is converted to obtain a transformed error. The sliding mode surface is designed based on the transformed error to control the transformed error to converge in a finite time, and the external disturbance of the vehicle-manipulator coupling system is observed based on non-linear disturbance observer. The control input of the vehicle-manipulator coupling system is designed based on the sliding mode surface and the non-linear disturbance observer output. This ensures that the vehicle-manipulator coupling system can operate precisely along the desired trajectory.

The invention discloses a dynamic weight correction and path deviation probability prediction method for a vehicle track, which comprises the following steps of: acquiring vehicle data and multi-source dynamic data of the vehicle track in real time through an optical sensor, a radio wave sensor and an inertial navigation sensor, carrying out space-time calibration, extracting obstacle characteristics and road structure characteristics, and predicting the path deviation probability of the vehicle track. The obstacle movement trend is quickly captured through a space-time diagram sequence and a diagram convolutional neural network, real-time obstacle avoidance is realized in combination with dynamic weight adjustment, a driving intention is predicted by using a Bayesian neural network, a trajectory planning strategy is adjusted through weight correction, and uncertainty is reduced by using multi-source data fusion and probabilistic prediction. A closed-loop feedback mechanism continuously optimizes the model, and efficient operation is kept in complex scenes such as intersections and roundabout through real-time weight adjustment and closed-loop feedback, so that the purpose of quickly responding to dynamic obstacles or driving behavior changes can be achieved, and the precision of the path deviation prediction probability is improved.

The invention relates to the technical field of unmanned aerial vehicle dynamic dust suppression intelligent decision making based on multi-sensor data fusion, in particular to a loess photovoltaic construction dust suppression unmanned aerial vehicle spraying dynamic regulation and control device and method, and the method comprises the steps: building a dynamically updated four-dimensional concentration field through a sensor cooperation unit in combination with a turbulence diffusion model of a dust field reconstruction engine; and the strategy knowledge base is optimized to shorten the flight path planning decision-making period from the minute level of the existing offline planning to the second level response. And the anti-interference execution unit realizes accurate spray trajectory tracking under a complex wind field condition. And a real-time evaluation closed loop of the dust suppression effect is constructed by a dual-spectrum imaging and deep learning analysis technology of the efficiency feedback unit, so that a dust field model can dynamically correct boundary condition parameters. The response lag time of an existing dust suppression system is shortened, meanwhile, the spray coverage rate is increased, energy consumption is reduced on the premise that the dust suppression effect is guaranteed, and an intelligent solution is provided for photovoltaic construction flying dust treatment.

The invention relates to the technical field of equipment control, and provides an autonomous tracking anti-interference control method and system.The confidence coefficient of a sensor is determined by combining the historical precision of the sensor and the current signal quality through a sensing recognition module, and the fusion weight is dynamically adjusted based on the confidence coefficient, so that the target tracking state can accurately reflect the actual motion characteristics of a target; the trajectory planning module takes an interference type, an interference degree and a target tracking state as input parameters cooperatively, and combines an extended state space and a reward function containing an anti-interference reward, so that an explored tracking trajectory can actively adapt to an interference scene; meanwhile, the predicted collision probability is compared with a probability threshold value, so that the global updating triggering opportunity is ensured to be accurate, and the collision risk caused by an unreasonable track is effectively avoided; and the control optimization module generates a targeted feed-forward compensation amount according to the interference type and the interference degree, and generates a control instruction after superposing the basic control amount, thereby realizing cooperation of anti-interference compensation and trajectory tracking control.

The invention discloses an intersection entrance lane mixed vehicle team cooperative guidance control method, which overcomes the problems of large calculation amount and difficulty in achieving a global optimal state in the prior art, and comprises the following steps: 1) obtaining road information; 2) dividing intelligent agents; and 3) establishing a multi-agent ecological cooperative control model of the intersection entrance lane mixed vehicle fleet: firstly, establishing a single-agent speed trajectory planning model, calculating an optimal passing trajectory of a single agent, and then establishing a multi-agent cooperative control model by taking the overall operation efficiency of the vehicle fleet as an optimization target on the basis of the optimal passing trajectory of the single agent, so as to realize the multi-agent ecological cooperative control of the intersection entrance lane mixed vehicle fleet. Cooperative control among a plurality of agents is realized, and a model is trained through a reinforcement learning method after model construction is completed; and 4) the controllable agents execute the optimized trajectory: issuing the established and trained model to each controllable agent, adopting a rolling time domain updating strategy, calculating the speed trajectory of each agent passing through the intersection by using road traffic information, and inputting the speed trajectory to a CAV controller for execution.

The embodiment of the invention provides a lifting hook track prediction method and device based on Internet of Things sensing, accurate environment sensing and obstacle recognition are achieved by fully utilizing data of a multi-source sensor, the intelligent track planning capacity is achieved, and the real-time performance and smoothness of a control system can be guaranteed. And advanced technologies such as deep learning and multi-sensor fusion are introduced, so that the overall performance and reliability of the system are improved, and the requirements of modern construction are better met.

The invention belongs to the technical field of laser processing, and particularly relates to a special-shaped curved glass laser cutting track planning method. According to the method, the instantaneous thermal effect and the historical thermal accumulation effect are subjected to coupling calculation, high-precision prediction and compensation of thermal deformation in the laser cutting process are achieved, the accuracy of the cutting track is improved, contour deviation caused by thermal deformation is avoided, and the geometric precision is improved; according to the local geometric complexity of the special-shaped curved glass, regions are divided, and differential virtual scanning layers and scanning modes are matched, so that the dynamic balance of efficiency and precision is guaranteed, the processing quality of regions with high curvature, thin walls and the like is guaranteed, the cutting speed of flat regions is increased, and the processing period is shortened; by monitoring the temperature and feeding back actual thermal historical parameters during cutting, model parameters are reversely optimized by using contour precision data after cutting is completed, so that robustness and stability are enhanced, and the yield and process reliability of laser cutting of the special-shaped curved glass are improved.

The invention relates to the technical field of automatic driving, and discloses an automatic driving lane changing trajectory planning method based on deep learning, and the method comprises the steps: carrying out the data collection and preprocessing of a multi-modal sensor; performing spatial feature extraction and time sequence modeling on the preprocessed multi-modal data by adopting a CNN-LSTM hybrid architecture, performing feature fusion through an attention mechanism, and outputting a first feature extraction vector; taking the detected vehicles as graph nodes to construct a traffic graph, learning an interaction relationship between the vehicles through a graph attention network and a message passing mechanism, and calculating a scene urgency score and a safety score; generating a lane changing decision based on the deep Q network and the strategy gradient; and generating a trajectory based on the generative adversarial network. The technical problems that an existing lane changing track planning method cannot adapt to the dynamic traffic environment, lacks the ability of understanding complex multi-vehicle interaction and is difficult to balance safety and urgent conflict requirements are solved, and intelligent, safe and efficient automatic driving lane changing track planning is achieved.

The invention relates to a mechanical arm track optimization method based on deep reinforcement learning. The mechanical arm track optimization method comprises the following steps that firstly, kinematics modeling is conducted on a mechanical arm; 2, multi-objective optimization problem modeling is carried out, trajectory planning of the mechanical arm is regarded as a multi-objective optimization problem, and the main objective of optimization comprises three aspects of trajectory precision, trajectory smoothness and energy consumption; and 3, optimizing a PPO reinforcement learning algorithm by using a near-end strategy, and designing a trajectory planning algorithm.

The invention provides an industrial robot control system and method. The system comprises a trajectory planning module, a dynamic compensation module, a feedback control module, an execution module, a sensor module and a data storage module. The trajectory planning module generates an expected trajectory of an end effector of the robot; the dynamic compensation module calculates a dynamic compensation torque based on the expected trajectory and a robot dynamics model; the feedback control module generates feedback control torque according to the deviation between the real-time pose data acquired by the sensor module and the expected trajectory; the execution module drives robot joints to move according to the synthesized moment of the dynamic compensation moment and the feedback control moment; the sensor module collects robot joint angle, angular velocity and torque data in real time; the data storage module stores robot dynamic model parameters, control algorithm parameters and historical motion data. High-precision and smooth robot motion control can be achieved, the dynamic response and stability of the system are improved, and energy consumption and motion errors are reduced.

The invention relates to the technical field of unmanned aerial vehicles, in particular to an intelligent flight path planning and energy management system and method for a long-endurance fixed-wing unmanned aerial vehicle. Comprising an environment sensing unit; the flight path planning unit is used for planning a flight path meeting task requirements, safety requirements and energy constraints based on the flight environment information of the unmanned aerial vehicle acquired by the environment sensing unit and pre-stored performance parameters of the unmanned aerial vehicle; and the energy management unit realizes energy dynamic management and optimization according to the real-time energy state of the unmanned aerial vehicle, the flight task and the planning result of the flight path planning unit. The flight path planning unit can call working condition energy consumption data such as navigational speed and height output by the energy management unit in real time, and dynamically adjust the weight of the path to avoid high-energy-consumption flight segments; the energy management unit synchronously and intelligently adjusts a main / standby battery charging and discharging strategy to optimize energy distribution according to a task time sequence (such as waypoint priority and track curvature) of a track.

The invention relates to the technical field of intelligent laser processing path planning, and discloses a laser flight processing path planning method and device for a complex curved surface, and the method comprises the steps: obtaining the geometric continuity features of the curved surface, carrying out the region division and boundary feature extraction, obtaining the geometric features of the boundary points of each region, and obtaining the geometric features of the boundary points of each region; performing track generation based on boundary geometric features to obtain an initial processing track path, then performing heat accumulation analysis and track screening, identifying a track section needing to be adjusted, executing multi-target path scheduling optimization, and obtaining adjusted track execution feature data; processing sequence optimization is carried out based on the feature data, and an optimized processing sequence is obtained; performing thermal input analysis and parameter correction according to the processing sequence to obtain an updated processing parameter set; and finally, performing global coordination based on a simulated annealing algorithm, generating a final processing track set, completing track optimization and instruction set generation, and outputting a complete processing scheme. According to the method, the problem of insufficient track fitting degree can be solved.

A multi-degree-of-freedom drive-by-wire unmanned vehicle obstacle avoidance path planning method mainly comprises the following steps that based on environment perception information, surrounding obstacles are analyzed and processed, and an environment safety boundary is established; on the basis of an environment safety boundary, speed sampling is carried out based on dynamic window trajectory planning of hierarchical response, and an optimal local trajectory is calculated and selected; in the driving and obstacle avoidance process, according to obstacle distribution and road condition fluctuation real-time information, the posture of a vehicle body is dynamically adjusted, speed sampling is updated, and path planning is updated. According to the method, the optimal obstacle avoidance path can be planned in real time, so that the unmanned vehicle can quickly respond in a complex scene, and potential collision risks can be avoided in time; the characteristics that the multi-degree-of-freedom drive-by-wire unmanned vehicle is suspended and the vehicle body posture is adjustable are fully utilized, vehicle posture adjustment is fused into an obstacle avoidance strategy, and the feasibility of an obstacle avoidance planning track and the stability of vehicle execution are improved.

The invention discloses a goaf unmanned aerial vehicle inspection system based on monitoring and early warning, and the system comprises an observation data collection module which is used for collecting settlement and fracture main variables to form a time stamp observation set; the data fusion module is used for generating a unified monitoring data set by adopting a fractal small-world network coding consensus algorithm; the initial route planning module is used for constructing a route sequence based on a main variable evolution tensor and a risk map; the flight path execution module is used for collecting a flight path and environment data; the fault-tolerant control module triggers a fractional order sliding mode fault-tolerant and degradation mechanism based on the consistency error; and the closed-loop optimization module is used for dynamically updating the main variable tensor and the path cost function and outputting an optimized track and a structured early warning result. The system has high dynamic responsiveness and multi-source risk adaptability.

The invention discloses a multi-aircraft cooperative formation flight path planning method based on a leader and follower model, and relates to the technical field of environment perception and unmanned aerial vehicle cluster cooperation. The method comprises the following steps of: firstly, designing a multi-agent double delay depth deterministic strategy gradient (LFMATD3) based on a leader-follower model, and converting an optimization problem model into a Markov decision process model by introducing an artificial potential field model and a reward function; and secondly, constructing an independent agent for each unmanned aerial vehicle, optimizing a behavior strategy of the unmanned aerial vehicle by combining a reward function based on an algorithm framework of deep reinforcement learning, and performing flight path planning and realizing dynamic formation control. The method provided by the invention can effectively improve the formation stability and collaboration of the unmanned aerial vehicles in a complex environment.

The invention discloses an end-to-end automatic driving method based on dynamic multi-modal fusion in a complex scene, and belongs to the technical field of automatic driving. In order to solve the problems of sensor perception deficiency, cross-modal feature mismatching, unstable trajectory planning and the like easily occurring in night, low-illumination and complex dynamic environments in the existing end-to-end automatic driving method, texture details of a camera mode and geometric structure features of a laser radar mode are respectively enhanced through a double-flow feature refining mechanism; the characteristic difference between different modes is relieved; an information-driven dynamic fusion strategy is designed, the fusion weight is adaptively adjusted according to scene factors such as environment illumination and obstacle density, and the scene sensitivity and discrimination ability of the model are improved; asymmetric convolution and a low-rank-sparse decoupling technology are introduced, multi-order reconstruction of key channels is carried out on the multi-modal features, and the path change modeling capability is enhanced; and in combination with time sequence dependence of waypoints, outputting a future trajectory through an autoregression decoder to realize high-precision trajectory prediction and stable decision control.

The invention relates to the field of navigation, and more particularly discloses a gradient optimization driven unmanned aerial vehicle real-time obstacle avoidance multi-stage trajectory planning method, which comprises the following steps of: in a trajectory initialization stage, firstly, searching a collision-free geometric path considering steering limitation of an unmanned aerial vehicle on an occupied grid map by utilizing an improved algorithm to generate an initial B-spline control point; then, in a trajectory optimization stage, constructing a multi-target trajectory optimization problem, introducing an obstacle avoidance constraint based on an Euclidean distance field map, and optimizing the initial control point set in combination with unmanned aerial vehicle parameters and optimization weights to obtain a trajectory meeting an obstacle avoidance requirement; and finally, for the optimized trajectory, performing dynamic feasibility evaluation based on unmanned aerial vehicle kinematics limitation in a trajectory correction stage, and if the trajectory does not meet the constraint, performing correction based on the minimum curvature constraint on the control point to ensure that the finally generated trajectory is not only obstacle-avoiding but also feasible in dynamics, and finally, determining that the trajectory does not meet the constraint. Therefore, the real-time obstacle avoidance capability of the unmanned aerial vehicle in a complex environment is effectively improved.

The invention relates to the field of risk assessment of intelligent driving vehicles, in particular to a dynamic instability risk assessment method for a driving track of an intelligent driving vehicle, a dynamic instability risk assessment system for the driving track of the intelligent driving vehicle, computer equipment and a storage medium. And the future vehicle trajectory information given by the trajectory planning and predicting module is used as input, and the front wheel turning angle and the vehicle speed required by the vehicle tracking trajectory are obtained. And then the model is used as the input of a nonlinear two-degree-of-freedom vehicle dynamic model based on a UniTile-Ctrl tire model to describe the nonlinear dynamic response of the vehicle under the complex working condition, and the prediction of the dynamic state of the vehicle is realized. On the basis, a vehicle stability evaluation method based on a phase plane is introduced, and evaluation and pre-judgment of the dynamic instability risk of the vehicle driving track are achieved. The method is of great significance in solving the dynamic instability risk evaluation of the driving track of the intelligent driving vehicle under the complex working condition.

The invention discloses a deep learning-based arm trajectory planning method and control system for an intelligent humanoid robot with a body. The method comprises the following steps: acquiring a three-dimensional grid map of a multi-modal data construction environment; generating an initial feasible path through a path planning strategy network based on deep reinforcement learning; extracting the collision probability of each path node on the initial feasible path; according to the collision probability of each path node, judging an area in which local re-planning needs to be triggered; and carrying out smoothing processing to obtain a smooth obstacle avoidance path. The initial feasible path is generated through the path planning strategy network based on deep reinforcement learning. According to the collision probability of each node, an area needing local re-planning is screened out, and the path of the area is adjusted through an artificial potential field method, so that the capability of avoiding dynamic obstacles in the path planning process is improved, the collision risk in the path planning is reduced, and the path planning efficiency is improved. And the self-adaptive capability of the arm path planning complex environment of the intelligent humanoid robot with the body is improved.

The invention relates to an autonomous energy-saving soaring flight path planning method for a small-sized low-cost aircraft, belongs to the technical field of aircraft trajectory planning, solves the problem of low-cost wind field energy acquisition of the small-sized low-cost aircraft in the prior art, and comprises the following steps: S1, configuring a sensor for the aircraft, and measuring through the sensor to obtain observation parameters; s2, establishing a state vector of the aircraft; s3, establishing an aerodynamic force model, introducing a dynamic equation and a state transition equation, and performing accurate modeling on aerodynamic force; s4, performing multi-source data fusion by adopting extended Kalman filtering, establishing an extended Kalman filter of a nonlinear system, and executing real-time wind vector high-precision sensing; and S5, performing global wind field modeling, estimating a wind field environment, and performing energy-obtaining flight path planning to obtain an optimal energy-obtaining soaring flight path planning scheme.

The invention relates to the technical field of intelligent driving, and discloses an obstacle avoidance analysis system for intelligent driving. The system comprises a data acquisition module, a road feature extraction module, a lane type judgment module, a virtual marking generation module, an obstacle detection and trajectory prediction module, a dynamic obstacle avoidance decision module and a system verification and optimization module. The method comprises the following steps: acquiring data through a laser radar, a camera and the like; fusing point cloud and an image to extract the width and curvature of a road; judging the type of a lane according to the width; generating a virtual marking line on a marking-free road, fitting by using a B-spline curve when the curvature is large, fusing the point cloud and the image to detect an obstacle, and predicting a track by using Kalman filtering or a social force model. In combination with virtual marking and risk assessment, a safe trajectory is generated through an OccupanyGrid map, an A * algorithm and MPC, and a simulation and real road test optimization system is adopted, so that the problem of marking-free road trajectory planning deviation is solved, and the obstacle avoidance precision and the road condition adaptability are improved.

The invention relates to a wheel type double-arm humanoid robot motion track planning and obstacle avoidance method. The method comprises the steps that a robot system is started for self-inspection; the first sensor obtains environment information and constructs a real-time three-dimensional point cloud obstacle information graph; the second sensor obtains chassis state information and mechanical arm state information; a target task is set, and a moving path of a chassis and a moving path of a mechanical arm are planned based on the state information of the target task; and the system controls the chassis to move according to the planned moving path through the cooperative control model, and the mechanical arm moves according to the planned moving track. Through construction and real-time updating of the real-time three-dimensional point cloud obstacle information graph, the robot can effectively recognize and avoid obstacles, the risk of collision with the surrounding environment is reduced, meanwhile, the robot can adapt to the dynamically changing environment, path planning is rapidly updated through the D * Lite algorithm, and the path planning efficiency is improved. And the path can be adjusted in time when the obstacle moves or a new obstacle appears.