61results about How to "Realize trajectory tracking" patented technology

The invention discloses a vehicle multi-target detection and trajectory tracking method based on re-identification, and belongs to the field of computer vision technology and video monitoring. The method comprises the following steps that firstly, a model capable of effectively extracting vehicle visual features on each track is trained by utilizing a vehicle re-identification technology; then, vehicle detection is carried out on each frame of image in the camera; and finally, in combination with the vehicle appearance features extracted by the re-identification model, motion prediction and visual similarity discrimination are fused, and single-camera multi-target tracking is executed, so that the driving trajectories of all matched vehicles are obtained. According to the method, multi-target matching of front and rear frames of images is successfully achieved in the aspect of tracking, the problem of tracking target shielding is effectively solved, and the appearance characteristics of the vehicle images shot by the multi-angle camera are extracted by adopting a re-identification technology aiming at the possible instability of algorithm detection performance caused by multiple visual angles and are fused into a tracking scheme, re-identification which occurs again after the tracking target is lost is achieved, and the track tracking capability is further improved.

The embodiment of the application discloses an adaptive prediction time domain steering control method and device for an autonomous vehicle. The method comprises the following steps: acquiring a vehicle running reference track, and forming a vehicle running reference track under a global coordinate system according to the acquired track; performing fitting based on map information acquired by a vehicle global positioning system (GPS) and a differential system to form a vehicle running expected track curve; building a prediction model with a course deviation between a vehicle running path and the reference track based on a vehicle kinematic model and the vehicle running expected track curve; designing an adaptive variable sampling period; and periodically adjusting the track of the vehiclein the running process based on the sampling period to realize track following. According to the method in the embodiment of the application, the reference track is followed in an adaptive period prediction control manner, and the vehicle has a very good track following control effect after the adoption of an adaptive period considering the road curvature change, so that the control accuracy is improved, and relatively high stability is achieved in the control process.

The invention relates to a wheeled mobile robot trace tracking control method based on energy saving consideration, and belongs to the field of robot control. The method comprises the following steps that according to energy consumption characteristics of a wheeled mobile robot, the energy consumption optimization of a driving motor during cruising of the robot is intensively considered, and a motor energy consumption model is built; according to the trace tracking characteristic of the wheeled mobile robot, a kinematic model and a tracking error model are built, and a kinematic tracking sub controller is designed; a correlation model of the kinematic model and the motor energy consumption model is built according to an inherent correlation mechanism between the kinematic model and the motor energy consumption model; finally, an energy-saving sub controller is obtained, so that the wheeled mobile robot trace tracking control method based on energy saving consideration is obtained. The wheeled mobile robot trace tracking control method has the advantages that the global stability of a system and the high-precision and low-energy-consumption control of the whole process of the wheeled mobile robot can be controlled, so that the precise trace tracking is realized, and meanwhile, the energy optimization is realized.

The invention discloses a vehicle safety navigation system for a locomotive. The system comprises locomotive vehicle-mounted navigation devices, a ground locomotive monitoring center and railway track precise electronic maps, wherein the locomotive vehicle-mounted navigation devices and the ground locomotive monitoring center are connected through a wireless communication network; the railway track precise electronic maps are respectively installed in the locomotive vehicle-mounted navigation devices and a computer of the ground locomotive monitoring center; the ground locomotive monitoring center receives track state data and differential data of a satellite base station and locomotive precise position data transmitted by a wireless network; the data which are comprehensively resolved by central server software are sent to display screens of all locomotive vehicle-mounted navigation devices in the system to drive voice broadcast, sound-light alarm and alarm prompt, so that safe navigation of locomotive driving is realized. Compared with the prior art, the vehicle safety navigation system has the advantages that safe navigation of railway locomotive in the transport process is realized, remote monitoring, dynamic tracking and safe management of locomotives are realized, and the system has promotional and applicable values.

The invention discloses a building indoor floor plan establishment method based on a laser ranging sensor, and relates to the technical field of indoor positioning. By means of the building indoor floor plan establishment method based on the laser ranging sensor, trajectory tracking of an indoor moving object can be achieved, and the problem that an indoor map is lacked in the process of rapidly establishing Radio Map in the field of indoor positioning is solved. The building indoor floor plan establishment method based on the laser ranging sensor is characterized in that building indoor laser measurement data are obtained; laser measurement data images are spliced, the rotation matrix and the translation matrix of two adjacent sets of the laser measurement data are obtained, the laser measurement data are converted to a point set within a former coordinate system by means of the obtained corresponding rotation matrix and translation matrix, forward iteration is continuously conducted, and splicing of the laser measurement data images is completed; geometric correction of errors, deletion of redundant data and filtering removing of noise points are sequentially conducted on the spliced images. According to the building indoor floor plan establishment method based on the laser ranging sensor, in the process of rapidly establishing the Radio Map in the indoor environment, the requirement of a user for rapidly establishing an indoor two-dimensional map is met, and meanwhile trajectory tracking of indoor moving objects can be achieved.

The invention provides a remote state tracking and control method and a system for an AUV platform. The system is composed of an underwater acoustic communication MODEM-A, a communication MODEM-B, an ultra short baseline array, a satellite communication module and a display control platform. The method uses underwater acoustic communication range finding and ultra short baseline direction finding functions in a joint mode and the AUV updates the position information in real time during an operation process. During an underwater navigation process of the AUV, the AUV-end communication MODEM-A is started to transmit a positioning signal, the underwater base station-end ultra short baseline array receives the positioning signal, measurement on a horizontal angle and an elevation angle is completed, and the direction finding result is sent to the AUV end via the underwater base station-end underwater acoustic communication MODEM-B. Due to the design method of arranging the ultra short baseline array at the underwater base station end, the mounting load of the AUV platform end is reduced, and the AUV end signal processing complexity is reduced.

The invention discloses a switching system-based modeling and adaptive control method for a cargo handling unmanned gyroplane, relates to a modeling and adaptive control method for a cargo handling unmanned gyroplane, and aims at solving the problems that the motion mode of the unmanned gyroplane is disturbed and the flight stability is affected due to massive sudden increase or sharp reduction of the unmanned gyroplane at the moments of cargo grabbing and delivery. The method comprises the following steps of (1) building a position dynamics switching model of the cargo handling unmanned gyroplane; (2) determining an attitude dynamics model of the cargo handling unmanned gyroplane; (3) building an error dynamics model for trace tracking of the cargo handling unmanned gyroplane; (4) designing a switching adaptive controller and an adaptive updating law; (5) proving the system stability of two sub-modes of the cargo handling unmanned gyroplane and determining tracking time; and (6) proving the overall stability of the unmanned gyroplane in executing a cargo handling task and determining mode dependence dwell time. The switching system-based modeling and adaptive control method is applied to the field of unmanned plane flight control.

The invention provides an image processing-based intelligent tracking method, system and device for a target object and a readable medium, and the method comprises the steps: carrying out the retrieval matching in a video monitoring system through the biological feature information of the target object, and obtaining a matching result; determining a corresponding target search area according to the matching result; tracking the target object by calling a mobile device in the target search area; thus, trajectory tracking of personnel in a specific public place is realized, directional search isperformed in combination with the mobile device in a target search area where the target personnel finally appear or possibly appear, accurate personnel search can be realized, and the influence on all personnel in the public place is reduced through directional search.

The invention discloses a continuous vehicle speed detection method based on laser radar, relates to the fields of a laser radar speed detection technology and a vehicle speed detection technology andsolves the problems that vehicle and non-vehicle objects cannot be classified through 2D laser radar detection and the cost of high-cost 64-wire 3D laser radar is too high in existing technologies for performing vehicle speed detection through laser radar. A 16-wire laser radar is adopted for continuously acquiring road scene data of traffic lanes, then, vehicles are associated with a method forassociating vehicles in multi-frame data, the vehicle speeds are detected, the problem that measurement is affected due to frame loss of the laser radar is completely solved, and the problem that measurement is affected due to mutual shielding of vehicles is also solved. The method realizes measurement of continuous speed change curves of vehicles and has great significance in further analyzing vehicle behaviors. The method can be applied to various vehicle speed measurement places in the traffic engineering.

The invention relates to the field of vehicle trajectory tracking, and in particular to a method for determining vehicle trajectory tracking points based on preview. The method converts the discrete points of a desired path in the geodetic coordinate system into the vehicle coordinate system by utilizing coordinate system conversion, comparing the discrete points with a preview distance, and quickly obtaining trajectory tracking points on the desired path according to the comparison result to obtain preview points determined by the preview distance and a lateral displacement error of the trajectory tracking points, thereby calculating the front wheel angle of the vehicle. The method provided by the invention has simple principle as well as fast and accurate calculation process, and can realize trajectory tracking of intelligent vehicles.

The invention belongs to the technical field of robots, and discloses an incomplete constraint wheeled robot locus tracking control method based on a look-up table method. The method comprises the steps: solving a robot kinematic model through an Euler numerical value, and building a movement locus (x, y) relation table between system input (v, omega) and the robot under the condition of saturation constraint; determining a control input quantity according to a proposed shortest Euclidean distance criterion look-up table; finally employing the determined control input quantity for the robot, and enabling the movement locus of the robot to be tracked to a specific reference locus. The effectiveness of the method provided by the invention is verified based on Matlab through the tracking simulation results of linear, sine, cosine and circular loci.

The invention relates to a distributed space-time correlation model trajectory tracking method based on statistical inference. Beacon nodes are deployed in the shape of an equidistant grid in a locating space according to longitudinal and transverse directions, and beacon node information is saved in each unknown node; the beacon nodes receiving notification information transmitted by the unknown nodes emit locating signals at a fixed frequency, and the unknown nodes receive and form multiple time sequences according to the beacon nodes; each unknown node constructs a boundary time sequence to detect a boundary crossing event and determine a corresponding time point; each unknown node constructs regional time window statistical quantity and infers the current region; the position of the intersection points of the trajectories and the boundary is inferred; and the trajectories are formed and the result is uploaded to aggregation nodes. According to the method, RSSI locating information probability distribution characteristics in the trajectory tracking problem and space-time data mining are overall considered, and the boundary crossing event and regional information are discovered through the method of time-space information statistical inference so that trajectory tracking can be realized.

The invention relates to the technical field of autonomous water surface robot control, in particular to an integral sliding mode obtaining method and system for autonomous water surface robot trajectory tracking. The method comprises the following steps: establishing an autonomous water surface robot containing external interference and a kinematics and dynamics model of a tracked expected trajectory, then, introducing an auxiliary variable, converting a model containing external interference and based on the autonomous water surface robot into a tracking error system model, designing an integral sliding mode surface and a fixed-time interference observer, and designing a trajectory tracking integral sliding mode control scheme of the autonomous water surface robot based on an interference estimation value. The method can effectively reduce the influence of external interference on the autonomous water surface robot, achieves the precise control, and is suitable for the fixed-time trajectory tracking control of the autonomous water surface robot.

The invention provides a track following method. The track following method comprises the steps of (1) acquiring the turning angle of an active steering axle when a vehicle drives along a curve; (2) determining the expected turning angles of all steering axles in the vehicle through a preset steering axle relation model according to the turning angle of the active steering axle; and (3) determining the expected turning angles of wheels on the two sides of the steering axles correspondingly according to the turning angles of the steering axles. Through the track following method, the moving tracks of the axles in the vehicle steering process, and accordingly, track following of the vehicle is realized. Meanwhile, through the track following method, the steering radius and the passage widthof the vehicle can be reduced. The track following method is particularly suitable for operation control over articulated vehicles.

The invention discloses a trajectory tracking system and method based on face recognition, and the method comprises the steps: firstly obtaining a face image and auxiliary information, carrying out the preprocessing of the face image, carrying out the feature extraction through employing the face recognition technology, and obtaining the corresponding face features, wherein the auxiliary information comprises the image collection time and the corresponding position information; employing a face recognition module for calculating a corresponding similar set and a deflection angle according to the face features, and carrying out the trajectory tracking based on face recognition; storing the face recognition result, calculating the moving direction according to the deflection angle, and driving the next data generation module to collect the face image; and finally, according to the image acquisition time, displaying and connecting all the position information to obtain a corresponding trajectory, thereby realizing trajectory tracking.

The embodiment of the invention provides a vehicle tracking system. The system comprises a plurality of cameras, the cameras are used for shooting monitoring images on a monitoring road section at intervals, each camera shoots different monitoring sub-road sections of the monitoring road section, and the monitoring sub-road sections monitored by the cameras with adjacent serial numbers have overlapping areas; sending the shot monitoring image to the terminal server; the terminal server is used for receiving the monitoring images sent by the plurality of cameras and acquiring vehicle information of vehicles existing in the monitoring images; determining a target vehicle in all vehicles in which the images of the plurality of cameras exist based on the similarity of the vehicle information;and obtaining global coordinates of the target vehicle in a global coordinate system when the plurality of cameras shoot the target vehicle, wherein the global coordinates are used for displaying a track of the target vehicle in the global coordinate system. And long-distance continuous vehicle trajectory tracking can be realized.

The invention discloses an epidemic situation close contact person trajectory determination method, system and device and a storage medium, and the method comprises the steps: obtaining road network topology information and first positioning information of a plurality of persons, and determining the first trajectory data of the plurality of persons according to the road network topology information and the first positioning information; establishing an R-Tree spatial index according to the first trajectory data; acquiring a preset epidemic situation personnel trajectory, and matching in the R-Tree spatial index according to the epidemic situation personnel trajectory to obtain a trajectory of a person closely contacted with the epidemic situation. According to the invention, space positioning information and a road network topological structure are combined to determine the trajectory data of the personnel, the real-time performance and accuracy of trajectory tracking are improved, the R-tree spatial index is established, and the epidemic situation trajectory data are quickly queried and matched for retrieval, so that the trajectory of the personnel in close contact with the epidemic situation is quickly and accurately searched, the method improves the efficiency and accuracy of trajectory tracking of people in close contact with epidemic situations, and can be widely applied to the technical field of personnel trajectory tracking.

The invention relates to a Backstepping-based lower limb exoskeleton control method, which comprises the following steps of: 1, establishing a lower limb exoskeleton dynamical model, and converting the lower limb exoskeleton dynamical model into a control system state equation; 2, designing a Backstepping controller, and carrying out the control of the Backstepping controller; 3, improving an RBF disturbance observer, including designing the RBF disturbance observer and an RBF neural network adaptive law; and 4, performing control implementation, and enabling the lower limb exoskeleton to move according to the expected track. According to the method, for external random disturbance, the approximation characteristic of an RBF neural network is utilized, a disturbance observer is designed, and the external random disturbance is approximated; and aiming at the network approximation error existing in the RBF neural network, the disturbance observer is further improved, and the auxiliary variable is introduced to compensate the network approximation error, so that the external random disturbance is compensated, the approximation of the external random disturbance is closer to a real value, and the approximation error of the RBF neural network is reduced.

The invention belongs to the technical field of automatic control and relates to a hip joint rehabilitation robot track and speed tracking self-adaptive control method. Under the condition that model parameters are uncertain, a self-adaptive control law is designed so that a hip joint rehabilitation robot can guarantee rehabilitation training of patients at a proper speed. The method includes the main steps that firstly, an expected tracking track of rehabilitation training is designed according to hip joint physiological functions of a human body; secondly, according to the expected tracking track of rehabilitation training, output change ranges of drivers in the dynamic process are limited; thirdly, an unknown function in a kinetic equation and a bound function of unknown control gain are given; fourthly, track tracking errors and speed tracking errors are calculated; fifthly, the self-adaptive control law is designed by means of a layered fuzzy logic system and a fuzzy logic system. The method has the advantages of being safe, reliable, high in control precision and good in instantaneity.

The invention discloses a mobile robot trajectory tracking control method based on strategy iteration. The mobile robot trajectory tracking control method is characterized by establishing two neural networks for a known mobile robot system, wherein the neural networks are respectively an actor neural network and a critic neural network, the actor neural network is used for evaluating and improving a system control strategy, the critic neural network is mainly used for calculating a value function under the current control strategy, and the value function is used for evaluating the current strategy. The method comprises the following steps of: 1) establishing a kinematic model of a mobile robot; 2) designing the Actor neural network; 3) designing the Critic neural network; and 4) designing an online algorithm of an Actor / Critic structure. Based on the data-driven control algorithm, the value function is utilized to evaluate the strategy function, the value function and the strategy function are considered in the learning process, and trajectory tracking of the mobile robot can be well achieved.

The invention provides a pedestrian trajectory tracking method, and relates to the field of image processing, and the method comprises the steps: obtaining image data; performing feature extraction on the image data, and constructing a candidate relation mask; extracting a historical frame feature set of the pedestrian trajectory library, and performing feature calculation on the historical frame feature set and the candidate frames in the candidate frame relation mask to obtain a person frame feature distance matrix and a frame person feature distance matrix; calculating the feature distance between the target pedestrian and the candidate box, and classifying the target candidate box, the feature distance between which and the target pedestrian satisfies the minimum distance, into the trajectory of the target pedestrian until no detection box satisfying the condition exists in the current frame detection box; and updating the pedestrian trajectory library, and outputting the pedestrian index set of the target pedestrian and the corresponding position trajectory. The problem of insufficient feature richness in the pedestrian tracking process can be effectively solved, and the pedestrian tracking detection precision is improved. The invention also provides a pedestrian trajectory tracking system, a computer readable storage medium and electronic equipment, which have the above beneficial effects.

The invention discloses a trajectory tracking method and device for a foot type robot, terminal equipment and a computer readable storage medium, and the method comprises the steps: determining an expected pose trajectory parameter of the foot type robot, and constructing a position proportion and a feedforward and differential control channel of a body pose trajectory of the foot type robot according to the expected pose trajectory parameter; a first variable damping controller inversely proportional to the distance is designed according to the expected pose trajectory parameters; and performing trajectory tracking for the foot type robot according to a first expected force and a torque which are output according to the position proportion and a feed-forward and differential control channel, and a second expected force and a torque which are output based on the first variable damping controller. By the adoption of the technical scheme, the requirement for steady-state high-dynamic quick response can be met during trajectory tracking control of the foot type robot.

The invention discloses an electronic license plate for an electric vehicle based on smart city Internet of Things, and belongs to the technical field of Internet of Vehicles and traffic supervision, the electronic license plate comprises an electronic license plate, and a two-dimensional code unit is arranged on the outer wall of the electronic license plate close to the top end; license plate fixing holes are symmetrically formed in the two sides of the two-dimensional code unit; an electric vehicle physical license plate number is arranged on the outer wall of the electronic license plate close to the top end; an antenna is arranged at the top end in the electronic license plate, and an electronic tag is arranged on the upper left portion of the antenna. a positioning tag is arranged on the upper right portion of the antenna, and a power supply circuit is installed in the center of the interior of the electronic license plate. The invention designs an electronic license plate for an electric vehicle and an electric vehicle violation management and control system, which are based on a wireless radio frequency technology. The system is matched with an electronic license plate, so that trajectory tracking and punishment management and control of traffic violation behaviors of the electric vehicle can be achieved, and normalized supervision of the electric vehicle can be achieved.

The invention discloses a wheeled robot data-driven iterative learning control method under DOS attacks. The wheeled robot data-driven iterative learning control method comprises three steps of constructing a bottom layer data model, designing a kinematics controller and setting an event triggering mechanism. On the premise of ensuring the expected stability performance, the updating times of the controller are reduced, and bandwidth resources are saved; meanwhile, the controller is designed only by using I / O measurement data generated by the dynamical model without depending on specific parameters of the dynamical model, so that the difficulty in the aspect of model decoupling is reduced, and the method is suitable for WMR systems with different types of mechanical structures and is more beneficial to practical engineering popularization; in addition, the method can introduce an iteration domain to get rid of the constraint of an early convergence process under the condition of considering network malicious DOS attacks and introducing an event triggering mechanism, and achieves complete trajectory tracking of the wheeled mobile robot in the whole time domain, thereby greatly improving the stability and reliability of the operation of the wheeled robot.

According to the building management method and system based on the user portraits, user portraits of people entering a building are recognized, user type judgment and trajectory tracking are achieved, an abnormal behavior recognition algorithm is combined, intelligent recognition alarm of abnormal behavior points is conducted, the behavior norms of the people entering the building are guaranteed; when the abnormal behavior is judged to exist, an alarm is given in time, so that the situation that all possible potential safety hazards are handled, solved and eradicated in time before a safety event occurs is ensured, the safety of articles and personnel in the building is ensured, a safe, comfortable and reliable working and living environment is provided for building owners and resident personnel, and the satisfaction degree of property service is improved.

An automatization discriminating video monitoring method has the steps: first building a refernence label array, adjusting the power of the RF reader to ensure the reading range to entirely cover the label array; then computing the mean of each electrical label signal intensity in the refernence label array and the signal intensity changing range when objects passby, getting the signal intensity threshold through the statistical analysis; and then, recording the signal intensity of all the labels including the refernence label in the whole monitoring process, and forming the signal intensity sequence through completing the missing items anf removing the abnormal value; reconverting the signal intensity sequence to form the trace set, and generating the frequent trace set from the trace set; finally judging the present behavior to be the permissive activity by the system through the detecting process. The invention not only provides the similar accuracy as the traditional art, but alsoprovides the realtime monitoring function, saves the cost of human resources and the cost of the video realtime discriminating technology.

The invention discloses an output feedback trajectory tracking control method with predetermined performance and dead zone input constraints for an electromechanical system. The method comprises the following steps: firstly, establishing an electromechanical system model containing dead zone input, carrying out linear processing on a dead zone model, and giving a reference tracking trajectory; secondly, defining a tracking error, introducing a predetermined performance function, and converting an original system into a system with predetermined performance constraints; in order to solve the problem that the angular position, the angular speed and the motor current in the electromechanical system are not easy to measure or the measurement precision is not high, designing a neural network state observer to estimate the state of the electromechanical system; and finally, solving the problem of complexity explosion in the traditional backstepping method by adopting a command filter technology, and constructing adaptive output feedback control in combination with an adaptive backstepping method and a neural network state observer under predetermined performance control and dead zone input constraints. The method effectively improves the transient and steady-state performance of a system with an unknown state, accurately realizes trajectory tracking, and is suitable for electromechanical system control with accurate positioning.

The invention discloses a dog information intelligent management platform and management method. The platform comprises an Internet dog comprehensive management system, a dog comprehensive service system, a public security network dog management and control system and a dog convenience service system. The invention provides the dog information intelligent management platform and a management method, based on the canine information intelligent management platform, data synchronization, extraction, data formatting, analysis and overall conception of a pre-alarm method are carried out, required information is extracted from front-end service acquisition data by using a constructed service information subsystem. And the comprehensive application of dog-related industry information extraction,summarization, analysis, query and statistics is realized. The dog information intelligent management platform is an application system constructed based on a multi-layer architecture system, a unified dog-related industry integrated platform is constructed, each business sub-platform is composed of a plurality of components and services, and different data applications can be realized through configuration of the components and the services.

The invention discloses a finite time fault-tolerant control method for a distributed unmanned ship formation. The method comprises the following steps: step 1, establishing an unmanned ship formation dynamics model based on external interference and actuator faults, and determining a control target; step 2, based on the unmanned ship formation dynamics model in the step 1, establishing a filtering compensation mechanism virtual speed control instruction; step 3, based on the virtual speed control instruction in the step 2, establishing a finite time fault-tolerant controller; and step 4, based on the finite time fault-tolerant controller in the step 3, verifying the stability and robustness of closed-loop control of the unmanned ship formation system. The invention aims to realize the cooperative control of the unmanned ship formation.