1253 results about "Kinematical model" patented technology

The invention relates to the technical field of intelligent driving, in particular to a method for generating an obstacle avoidance and planning cooperative path in an urban complex environment, which comprises the following steps: acquiring environment real-time sensing data through a vehicle-mounted multi-sensor, and constructing a dynamic semantic traffic matrix in combination with high-precision map static semantic information; based on the matrix, a multi-objective optimization algorithm is adopted to calculate the security cost, the efficiency cost and the rule conformity cost of the path, and a global optimization path is generated; inputting the global optimization path and the dynamic obstacle motion vector into an intention prediction model, generating dynamic obstacle future trajectory probability distribution and interactive intention classification, and further generating an avoidance strategy and adjusting a local path in real time; and inputting the adjusted local path into a kinematics model to carry out kinematics feasibility verification, and outputting an executable track or path re-planning. According to the method, the integration of dynamic environment understanding, path planning and obstacle avoidance strategies is realized, and the method is suitable for the path generation task of an automatic driving system in an urban complex traffic scene.

The invention relates to the technical field of robots, and discloses a multi-source data fusion method of a tracked robot, which realizes dynamic environment adaptation and autonomous decision optimization through a multi-source sensing cooperation mechanism, and comprises the following steps: dynamically adjusting exposure parameters of a visual module based on environment illumination intensity, and avoiding overexposure or underexposure of an image through a feedback adjustment mechanism; fusing data of the accelerometer and the gyroscope to generate attitude angle compensation parameters; the heat dissipation system is intelligently regulated and controlled by comparing infrared thermal imaging and temperature sensor data; dynamic task priority distribution is realized; optimizing an advancing route to reduce complex terrain navigation deviation, in addition, establishing a multi-source sensing coordination mechanism, monitoring health indexes such as motor temperature and vibration frequency in real time, and triggering abnormal state judgment; track optimization is implemented in combination with pavement mechanical characteristics and a kinematic model; and executing the staged energy management strategy. According to the method, the environment sensing precision and the motion control reliability of the tracked robot in a complex environment are remarkably improved.

The invention discloses an intelligent logistics scheduling method and device based on a dynamic weight and a medium, and the method comprises the steps: carrying out the fusion processing of the operation environment data of a logistics carrier, so as to construct a dynamic environment model, and carrying out the fusion processing of the operation environment data of the logistics carrier based on a reinforcement learning model according to a real-time environment state and a multi-target optimization demand. Dynamically adjusting the weight vector of each logistics parameter in the logistics carrier; predicting the space-time trajectory of each logistics carrier based on the kinematic model of the logistics carrier, mapping the space-time trajectory to a three-dimensional grid, identifying a potential conflict area between the logistics carriers, and calculating a corresponding conflict severity index; based on the dynamic weight vector and the conflict severity index, generating an obstacle avoidance path of the logistics carrier by adopting a global path re-planning algorithm, and optimizing the obstacle avoidance path through a local track to generate a corresponding smooth track; and executing a scheduling instruction corresponding to the smooth trajectory, and collecting an execution feedback result in real time to update the reinforcement learning model parameters and the dynamic weight strategy.

The invention relates to the technical field of intelligent mechanical arm control, and discloses a mechanical arm track optimization method and system based on deep learning and a fuzzy algorithm, and the method comprises the steps: building a kinematic model of a mechanical arm, determining the working space of the mechanical arm, carrying out the high-density random sampling, and generating a three-dimensional point cloud picture of a reachable region at the tail end of the mechanical arm; constructing a path planning model, designing a state space and an action space, and constructing a reward function; time-impact double-target optimization is carried out on the tail end path point sequence, a smooth joint trajectory is constructed, and balance between the shortest trajectory execution time and the minimum joint impact is achieved on the premise that speed and acceleration constraints are met; and tracking control is carried out on the trajectory, external disturbance and unmodeled dynamics are estimated and compensated in real time, a parameter adaptive law is designed, and the trajectory tracking precision of the system in a complex environment is improved. The autonomy, the accuracy and the anti-interference capability of the hot-line work mechanical arm in a complex environment are improved.

The invention relates to the technical field of electric vehicle control, and discloses a stability control method and system for an electric vehicle, and the method comprises the steps: collecting vehicle driving data in real time, and dynamically estimating the state parameters of the vehicle through an unscented Kalman filtering algorithm; according to the state parameters of the vehicle, combined with the kinematic model and the foresight trajectory, the expected yawing moment in a short time in the future is calculated, and the longitudinal traction requirement of the vehicle is obtained; and according to the state parameters of the vehicle and the longitudinal traction requirement of the vehicle, the yawing moment and the traction force are decoupled and distributed to the four electric driving wheel ends, and stable control over the electric vehicle is achieved. Compared with a traditional stable control system only based on closed-loop feedback, the stable control system has the advantages that the control response is faster, the yawing intervention is more accurate, and better control performance and vehicle safety are shown under the low-adhesion road surface and high-load working conditions.

The invention belongs to the technical field of robot control, and discloses a bionic robot control method and system based on a muscle fiber model.The method comprises the steps that a multi-scale muscle model is constructed based on a scale division mechanism, and the multi-scale muscle model is optimized by means of physiological state variables and fatigue accumulation variables to obtain a muscle fiber model; according to the muscle group cooperation relation and the kinematics model of the robot limbs, geometric structure adaptation is carried out on the model in combination with a deformation compensation strategy; on the basis of the fused multi-sensor data, a muscle fiber model and a model after geometric structure adaptation are utilized to construct a feedback adjustment mechanism; and on the basis of an adaptive neural network algorithm, the muscle fiber model, the model after geometric structure adaptation and a feedback adjustment mechanism are optimized, solving is carried out in combination with a multi-objective optimization algorithm, and command information of the limbs of the bionic robot is obtained and executed. Accurate control over the limb joint position, the torque and the impedance of the bionic robot is achieved.

The invention provides an intelligent inspection equipment control method for construction quality evaluation, and relates to the technical field of construction quality detection, and the method comprises the following steps: constructing a virtual twin model of a construction site, and combining an inspection kinematics model of a motion mechanism of inspection equipment based on the virtual twin model to obtain an inspection kinematics model; forming a three-dimensional navigation topological graph containing detection target priorities, obstacle avoidance weights, equipment reachable pose nodes and path curvature constraints; taking the three-dimensional navigation topological graph as input, performing multi-step state prediction and accumulative reward evaluation in a virtual space by adopting a double-estimation reinforcement learning algorithm, and generating a multi-step global motion control strategy; carrying out feasibility verification on the control strategy, and if the verification is passed, issuing a multi-step global motion control strategy to an inspection equipment execution mechanism; the inspection equipment is controlled to conduct three-dimensional laser scanning on the target component according to the verified path, high-density point cloud data are obtained, the control precision of the inspection equipment is improved, and the inspection efficiency is improved.

The invention discloses an intelligent ship autonomous collision avoidance method based on COLREGs and a DDPG algorithm, and relates to the technical field of an intelligent ship technology and an autonomous collision avoidance algorithm, and the method comprises the steps: building an intelligent ship kinematics model based on the motion parameters of a ship in a north-east coordinate system; aIS, radar and visual information are fused, COLREGs rule constraints are embedded, an environment model is constructed, and a ship size safety threshold value is calculated. According to the method, COLREGs and a DDPG algorithm are combined, a high-precision environment model is constructed by utilizing multi-source sensing data, and an algorithm structure is optimized aiming at a typical collision avoidance scene, so that the intelligent ship can automatically identify the meeting situation type, determine the way-giving responsibility or the direct navigation obligation and generate an optimal collision avoidance path in a complex marine environment; compared with a traditional collision avoidance method depending on manual driving and fixed rules, the autonomous collision avoidance capability of the ship in dynamic and complex ocean traffic scenes is remarkably improved, and the collision risk caused by human factors is reduced.

The invention relates to the technical field of flight simulation control and precision measurement, provides a precise positioning method, system and device for a three-dimensional adjustable connecting piece of a flight simulator and a storage medium, and solves the problems of flight simulation control and precision measurement. The method comprises the following steps: acquiring the real-time stroke length of a motion control rod, rotation angle change data and a connecting piece vibration image, outputting a displacement prediction parameter through a platform kinematics model, and generating three-dimensional point cloud data; performing sub-pixel identification and distortion compensation on the image through a mark point identification algorithm to generate a three-dimensional visual coordinate; fusing the point cloud and the visual data, and processing through a Kalman filter to obtain a space pose offset; finally, a displacement compensation instruction is generated, the pose of the connecting piece is adjusted through a closed-loop controller, and accurate positioning of the connecting piece relative to a flight target reference coordinate system is achieved. According to the invention, the accuracy and stability of the pose control of the connecting piece in the dynamic vibration environment are improved.

The invention discloses a cable underwater robot trajectory tracking control method for coping with ocean current disturbance, and belongs to the technical field of underwater robot trajectory tracking, and the method comprises the following steps: S1, constructing a kinematics and dynamics model of a cable underwater robot, and simplifying the kinematics model of the cable underwater robot; s2, combining speed information of a Doppler velocimeter sensor, designing a super-spiral expansion state observer, and compensating a cable underwater robot system; designing a self-adaptive super-spiral expansion state observer by combining a self-adaptive law; and S3, designing a self-adaptive super-spiral integral terminal sliding mode controller based on the self-adaptive super-spiral expansion state observer. The real-time dynamic performance and stability of the underwater robot in sliding mode control are improved, the buffeting problem existing in sliding mode control is solved, it is ensured that under the condition of ocean current disturbance, the ROV can still achieve accurate trajectory tracking, and the robustness is very high.

A vehicle-mounted GNSS positioning method based on multi-motion model interaction includes: establishing a position-constant velocity (PCV) model and a position-constant steering angular velocity (PCSAV) model for two attitudes of a carrier (i.e., linear motion and turning motion) respectively to obtain a state estimation vector and a state transition matrix of the carrier of the PCV model and the PCSAV model at a previous moment, introducing an interacting multiple model (INM), establishing a heuristic position-velocity filtering (HPV)-IMM model based on the IMM model to achieve an information filtering interaction between the PCV model and the PCSAV model, and obtaining a state estimation vector and an error covariance matrix of the carrier at a current moment, so as to obtain a position and velocity of the carrier at the current moment. The present disclosure solves the problem of low accuracy of a traditional single kinematic model in multi-motion attitude vehicle positioning.

The invention provides a mechanical arm time optimal trajectory planning method based on an improved genetic particle swarm algorithm, and belongs to the field of robot control. A mechanical arm kinematic model is established, the mapping relation between a joint space and a Cartesian space of an end effector is derived, and a joint angle sequence corresponding to an end path point is calculated; under the target of time optimization, joint speed and acceleration constraints are combined, a fitness function is constructed, and an improved genetic particle swarm optimization algorithm is used for optimization; a 3-5-3 segmented interpolation method is adopted, and based on the joint angle sequence, joint position, speed and acceleration trajectories are generated; the inertia weight is dynamically adjusted in the optimization process, and the search efficiency is improved; the motion time of each section of track is further optimized, the convergence speed and precision are improved through a hybrid optimization algorithm in combination with a time optimal target and joint motion constraints, finally, the mechanical arm motion track with the optimal time is output, the time for the mechanical arm to complete a target task is effectively shortened, the working efficiency is remarkably improved, and high precision and stability are achieved.

The invention discloses an intelligent cavity operation navigation method and system based on multi-mode perception fusion, and relates to the technical field of surgical medical treatment. Firstly, bionic instrument posture data and cavity environment data are obtained; then, based on the bionic instrument posture data and the orifice environment data, the target curvature of each section is calculated through a bionic kinematics model, and the magnetorheological fluid pressure is dynamically adjusted to control the local rigidity; meanwhile, the cavity point cloud topological graph is converted into an obstacle density graph, and path weight matrixes of different paths are quantified based on a swarm intelligence algorithm; and finally, according to the target curvature, the local rigidity and the path weight matrix, driving a bionic instrument to execute compliant motion and cooperative obstacle avoidance operation. According to the method, multi-modal data (curvature, rigidity and contact force) are fused through a bionic kinematics model, navigation deviation correction is achieved in combination with a curvature-force nonlinear mapping model and three-dimensional Euclidean distance monitoring, and the navigation precision is improved in combination with a path re-planning mechanism.

The invention discloses a flexible surgical instrument-oriented multi-source sensing data adaptive fusion method and a related device. The method comprises the following steps: acquiring optical, mechanical and pose multi-mode sensing data based on a timestamp synchronization technology in a working environment; clock compensation and space coordinate transformation based on an instrument kinematics model are carried out on the multi-modal data, and space-time registration is completed; inputting the registered data into a neural radiation field model to generate continuous space implicit scene representation; inputting the implicit representation into a pre-trained RWKV fusion network to obtain a fusion feature; and superposing the fusion feature and the original low-frequency component through residual connection, and integrating to generate three-dimensional voxelization environment state data. According to the method, multi-source information high-fidelity fusion is achieved through a single path, data redundancy is remarkably reduced, and the real-time performance and precision of intra-operative environment perception are improved.

The invention discloses a dynamic trajectory control method for an SCARA (selective compliance assembly robot arm) robot. According to the kinematics model, a homogeneous transformation matrix is used for analyzing the coordinate transformation relation between each joint and the connecting rod, and an initial pose and a target pose are determined; establishing a kinetic model based on a Lagrange equation, and determining kinetic parameters needing to be identified; performing parameter identification by adopting a random weight particle swarm optimization algorithm; according to an identification result, a sliding mode robust item RBF neural network adaptive controller is constructed, real-time track control is achieved, and the end manipulator is made to move to a target pose along a preset dynamic track; a real-time pose is detected through a sensor and compared with a target pose, and arrival is judged when the error is smaller than a threshold value. Model precision and identification efficiency are improved through modeling and efficient parameter identification, the composite controller effectively compensates uncertainty, disturbance and nonlinear factors of the model, closed-loop control and online adjustment are achieved, and trajectory tracking precision, system stability and dynamic response speed are improved.

Disclosed are a force guidance telerobotic system and control method based on a dual-arm collaborative potential field. A real-time pose of a tool center point of each of the two robotic arms is obtained using a robotic arm kinematic model, and checking is performed to determine whether a shortest distance dp-s,i between a target object and a workspace boundary of each of the two robotic arms is lower than a threshold Ds; a dual-arm symmetric collaboration strategy will be adopted when higher than the threshold; a single-arm primary collaboration strategy will be adopted when lower than the threshold; and a coordination factor δi of each of the robotic arms is determined according to the collaboration strategy; the dual-arm collaborative potential field is constructed according to the collaboration factor, a distance between the target object and the tool center point and a position of obstacle.

The invention provides a visual angle collaborative scheduling method and system for a multi-pan-tilt camera, and relates to the technical field of pan-tilt collaboration, and the method comprises the steps: generating respective priority weight according to the dynamic attribute of each dynamic target; each PTZ camera calculates a bidding value for each dynamic target according to the dynamic state parameters, the dynamic target is allocated to the PTZ camera with the highest bidding value through a bidding allocation mechanism, and an allocation mapping table is generated; extracting the real-time position and priority weight of the dynamic target allocated to each PTZ camera according to the allocation mapping table, and generating an initial rotation path based on an improved RRT algorithm; performing rolling optimization on the kinematics model of the corresponding PTZ camera to generate a real-time rotation angle and a zooming parameter; and on the basis of the real-time rotation angle and the zooming parameter, state monitoring of the dynamic target is executed, a dynamic optimization strategy is triggered when the state does not meet a preset condition, and the tracking and monitoring capability of the multi-pan-tilt camera system on the dynamic target is improved through optimizing the scheduling strategy.

The invention discloses a mine card simulation method and system based on log data, and relates to unmanned driving. The method comprises the following steps: obtaining operation log data of a mine card under multiple working conditions; extracting nonlinear response feature data according to the running log data; taking the historical control instructions and historical vehicle states of continuous N periods as input characteristics, taking the vehicle state of the current period as an output label, and constructing a training set; using the training set to train an LSTM model, inputting a current control instruction, a historical vehicle state and a current load value, and outputting a predicted vehicle response state; and inputting the predicted vehicle speed, acceleration, front wheel turning angle or hinge angle into a vehicle kinematic model, and calculating the position and attitude of the vehicle under the current load condition. Aiming at the problem that the time delay between a control instruction and an actual response in a super-large inertial system cannot be processed due to the fact that a non-linear dynamic response caused by the fact that mine truck large load change cannot be accurately simulated by adopting fixed dynamic parameters in mine truck simulation, the simulation precision is improved.

The invention discloses a dual-mode collaborative end-to-end automatic driving trajectory prediction method based on momentum sensing, and the method comprises the steps: collecting environment information, extracting features, removing noise, and obtaining a bird's-eye view feature tensor; inputting the information into a target detection tracking module and a real-time mapping module to obtain an information tensor; performing trajectory prediction on the detected target, establishing a target kinematic model, and predicting a prediction trajectory point of the target according to historical trajectory data; synchronously inputting the information tensor into a trajectory prediction module to obtain candidate trajectories of a target generated according to the current information, and selecting the candidate trajectory closest to a predicted trajectory point; and carrying out feature level fusion on the obtained candidate trajectory and the prediction tensor to obtain an optimized prediction trajectory. According to the method, noise is eliminated through the lightweight network, the prediction result is used as a prediction generation basis, so that the stability of the prediction trajectory is improved, historical information is fused, normal work under the high-dynamic non-intervisibility condition is ensured, and robustness is enhanced.

The invention relates to the technical field of robot control, and discloses a mechanical arm trajectory planning control method and system based on a BAFARNN model. The method comprises the steps that a mechanical arm kinematics model is established, and a trajectory tracking problem is converted into a time-varying equation; designing a bounded adaptive function to activate a recurrent neural network model, defining an error function and constructing a dynamic equation; designing a piecewise adaptive coefficient function, and dynamically adjusting the gain according to an error norm and time; setting a Lissajous curve as an expected trajectory, and initializing a simulation environment; the joint speed is solved in real time through an ODE numerical method, and the mechanical arm is driven to move; actual motion data is collected and compared with an instruction, and closed-loop feedback control is triggered when the actual motion data exceed a threshold value. According to the method, rapid convergence is achieved through the piecewise adaptive coefficient function, the bounded activation function and the negative feedback mechanism are adopted to suppress noise, and high-precision and real-time trajectory tracking of the mechanical arm in the dynamic environment is achieved.

The invention provides an underwater multi-robot distributed elastic positioning method and system, and relates to the field of underwater robots. Establishing a kinematic model of the target robot and a measurement model of monitoring node fusion distance, depth and attitude information; when the state variation of the target robot exceeds a preset threshold value, communication is triggered; identifying a random delay state of a measurement signal by adopting a binary indicative function, dividing a scene according to a relationship between the current moment and the total time length of a task, and converting random delay information into a non-delay equivalent sequence; on the basis of the kinematic model, the measurement model and the non-delay equivalent sequence, delay channels are selected in different scenes to execute state prediction and elastic gain correction, and a state estimation value of the target robot is obtained; wherein the tight upper bound of the positioning error covariance matrix is constructed, and the optimal positioning gain is solved to iteratively optimize the elastic gain. By adapting time-varying delay and optimizing gain control errors, efficient cooperative positioning in a complex environment is ensured, and reliable pose information is provided for underwater tasks.

The invention relates to the field of robot vision positioning, and discloses an intelligent hand-eye calibration and self-adaptive correction system and method. According to the method, a mechanical arm is controlled to drive a camera to collect multi-modal calibration data, a convolutional neural network is utilized to identify a calibration plate mark point, and a three-dimensional coordinate under a camera coordinate system is calculated in combination with depth information; meanwhile, on the basis of an encoder and torque data, flexible deformation of the mechanical arm is compensated through a kinematic model and a self-adaptive rigidity model, and three-dimensional coordinates under a base coordinate system are obtained. And obtaining a hand-eye transformation matrix by solving a transformation relation between the two point sets. And repeatedly calibrating before and after operation, inputting the difference of the two transformation matrixes into the fault diagnosis neural network, outputting fault type probability distribution, and generating a maintenance strategy. According to the invention, high-precision hand-eye calibration, automatic compensation of flexible deformation and intelligent diagnosis of system state change can be realized, so that the long-term precision and reliability of a visual positioning system are improved.

The invention discloses an intelligent exhibition hall control method and system based on digital twinning, and relates to the field of exhibition hall control, and the method comprises the steps: carrying out the kinematics state calculation of a continuous position flow of a visitor, and precisely mastering the current motion state of the visitor; the key point is that the method is not limited to the current state, but carries out high-precision prediction on the future (moment) movement track of the visitor based on a kinematic model. And along the prediction track, a personalized dynamic environment bubble can be generated in advance in combination with the portrait of the visitor, and the environment atmosphere of the area where the visitor is about to enter is actively and progressively pre-rendered. Finally, the environmental bubbles are reversely analyzed into specific equipment control flows, so that pre-smooth adjustment of lamplight, sound effect and other equipment is realized, and the technical problems of abrupt control and poor experience caused by perception lag and lack of predictive ability of a traditional control scheme are solved.

The invention relates to the technical field of unmanned aerial vehicle monitoring and trajectory processing, and discloses a low-altitude unmanned aerial vehicle dynamic trajectory tracking and predicting method based on multi-base-station cooperation. The method comprises the steps that signal parameters are obtained through multi-base-station collaborative observation, and a multi-modal position prediction set is generated; and performing classification and scoring according to the spatial distribution characteristics of the candidate points and the historical track points, and screening out an optimal prediction position point. And inputting the optimal prediction point and the historical trajectory into a generative model, and dynamically adjusting the number of trajectory points by analyzing the point distribution probability to form a preliminary smooth trajectory. And performing physical feasibility verification and fine adjustment on the trajectory according to kinematics constraints to obtain a final smooth continuous trajectory. And matching degree calculation is carried out by fusing alternative trajectories generated by a multi-kinematic model, and the most probable target trajectory is identified. According to the method, the robustness of trajectory prediction and the structural rationality of the generated trajectory in a complex observation environment are improved.

The invention provides an autonomous unloading control method and system for a carry-scraper, and relates to the technical field of underground carry-scrapers, and the method comprises the steps: collecting roadway environment point cloud data; according to the roadway environment point cloud data, the position and posture of the carry-scraper are calculated; performing path control on the carry-scraper according to the pose of the carry-scraper in combination with the kinematics model of the articulated vehicle and the MPPI algorithm model; according to the target position, environment data of the dump truck are collected, and characteristics of the dump truck are extracted; fusing the characteristics of the dump truck to obtain fused characteristics of the dump truck, performing pose detection on the dump truck, and outputting coordinates of key points; according to the coordinates of the key points, the 3D pose of the dumper container is calculated; according to the 3D poses, key parameters of containers of the carry-scraper and the dumper are calculated; dynamically adjusting the posture of the bucket according to the key parameters; according to the adjusted posture of the bucket, global coordinates of bucket teeth of the bucket are calculated; and according to the global coordinates, the bucket teeth are adjusted so as to control the carry-scraper to carry out autonomous unloading.

The invention belongs to the technical field of automatic driving, and particularly relates to an automatic driving decision-making method and system with dynamic risk perception and attention focusing and a vehicle, and the method comprises the steps: predicting the track of a surrounding vehicle in real time through a multi-feature Gaussian weighted particle filtering algorithm, and improving the prediction precision through combining a vehicle kinematic model and resampling optimization; constructing a comprehensive evaluation model fusing transverse and longitudinal risks, and dynamically quantifying the collision risk of the vehicle and surrounding vehicles; and inputting the risk value as a key state feature into a double-depth Q network based on attention mechanism enhancement, focusing key information through a feature attention distribution mechanism, and generating an optimal driving decision in combination with a multi-target reward function. Compared with the prior art, the method solves the problems of insufficient quantification of uncertainty factors, incomplete risk assessment and low decision-making efficiency of automatic driving in a complex dynamic environment, and significantly improves the risk perception capability and decision-making safety of the automatic driving vehicle.

A system for collaborative steering in steer-by-wire (SBW) vehicles includes sensors, a rack motor altering a position of the vehicle's steerable road wheels and an emulator altering a torque and position of a vehicle hand wheel. A collaborative steering system application (CSSA) obtains, static and dynamic information about the vehicle and the vehicle's environment, and generates a rack torque and / or angle command to the rack motor and an emulator torque and / or angle command to the emulator. The CSSA adjusts between ADAS and manual steering ratios and automatically transitions control between ADAS SBW control and manual control. The CSSA smooths transitions between ADAS SBW control and manual steering control and adjusts hand wheel stiffness by altering the emulator torque command, and causes the rack motor and emulator to operate according to a kinematic model while adapting road wheel response and vehicle operator steering feel based on scenarios and features currently enabled.

The invention relates to a calibration method, device and equipment for an intelligent driving sensor and a storage medium, and the method comprises the steps: extracting dynamic environment features according to pre-obtained multi-dimensional data, constructing an initial external parameter matrix based on the dynamic environment features, carrying out the iterative updating of the initial external parameter matrix through combining a vehicle kinematics model and a Lie group optimization algorithm, and carrying out the calibration of the intelligent driving sensor. And compensating the updated initial external parameter matrix according to a temperature parameter and a vibration parameter which are acquired in advance to obtain a final external parameter matrix, performing cross validation based on millimeter wave radar detection data and a calibrated fusion sensing result, and triggering dynamic re-calibration if a validation result does not meet a preset condition threshold value. According to the method, the problems of low efficiency and poor adaptability of traditional calibration are solved, and the robustness and long-term stability of sensor calibration are remarkably improved through a dynamic compensation and online verification mechanism.

The invention relates to the technical field of behavior recognition, in particular to an image library construction and recognition algorithm under a large-scale incomplete multi-view and multi-modal scene, which comprises the following steps of: deploying a plurality of sensors and cameras in a traffic scene, and unifying multi-modal data into the same space-time coordinate system; fusing the multi-modal data subjected to space-time alignment, predicting a target state and updating a measurement value; dynamically generating multi-view candidate views based on the fused data by using an adversarial generative network under space-time constraint, and complementing missing views in combination with a target kinematics model; a target kinematic model and a deep learning technology are fused, a cross-camera target is tracked, a traffic regulation ontology library is constructed, and traffic illegal behaviors are automatically identified and classified in combination with an image identification technology. According to the method, the consistency of different sensor data in time and space dimensions is ensured, and data chaos and errors caused by space-time differences are avoided.