13 results about "Distance error" patented technology

The invention discloses a multi-task fixation point estimation method, which relates to the technical field of computer vision and deep learning, and comprises the following steps of: firstly, constructing a data set for providing associated data from tasks to labels and supporting multi-task cooperative training, and then constructing an MTHGaze model, through a semi-structured framework, deep learning, a geometric constraint fitting model and key tasks of cooperative processing are fused, a loss function is designed and trained, defects of each task are solved through targeted loss function design, and a scientific training process enables the model to be iteratively optimized. Finally, the targets of improving the estimation precision of the fixation point, ensuring the physical rationality and enhancing the environmental robustness are achieved; and finally, performing fixation point mapping. According to the estimation method, through data set construction, data consistency can be guaranteed, training noise can be reduced, a real reference can be provided for loss function calculation, error back propagation can be realized, and Euclidean distance errors can be minimized through L2 norms of real fixation point coordinates and prediction coordinates.

The embodiment of the invention provides a distance measurement method and device, relates to the field of wireless communication, and can reduce distance errors corresponding to different loads and improve the accuracy of distance measurement. The method comprises the following steps: sending indication information, wherein the indication information indicates a second communication device to send a sound wave signal; receiving N sound wave signals; and determining a distance deviation value according to the N relative coordinates, the N receiving times and the first time difference. Wherein the N sound wave signals correspond to the N relative coordinates respectively, the N phase coordinates are coordinates of the N signal receiving positions relative to the reference position respectively, and N is a positive integer greater than or equal to 3; the N receiving times are the receiving times corresponding to the N sound wave signals respectively, the first time difference is the time difference of the signals between the first communication device and the second communication device, and the distance deviation value is used for determining the distance between the first communication device and the second communication device.

The present application belongs to the technical field of nuclear power plant operation optimization, and discloses a position correction method, device, computer equipment and storage medium, wherein the position correction method comprises the following steps: in the track robot inspection process, obtaining a to-be-registered image obtained by shooting a target image at a preset position of a track robot; obtaining a standard image corresponding to the preset position, the standard image comprising at least one mark image block; searching for an image block between the mark image block and the to-be-registered image block, which satisfies a similarity condition, to obtain a target image block corresponding to the mark image block; obtaining a position difference between the mark image block and the target image block to obtain a target offset pixel value; obtaining a conversion parameter between a previously determined motion distance and the offset pixel value, converting the target offset pixel value based on the conversion parameter to obtain a motion distance error of the track robot; and correcting the preset position of the track robot based on the motion distance error.

The invention provides a following control method and device of mobile equipment, electronic equipment and a storage medium, target stability is maintained by performing consistency judgment on candidate targets in sensing data, and target confirmation and locking are realized when an interaction trigger instruction corresponding to the candidate targets is detected; in a locking state, target area information is continuously output, depth / distance information is fused to calculate a relative pose, then the relative pose is converted into a distance error and an angle error to generate a chassis control instruction, and closed-loop adjustment of the following process is achieved. Therefore, the false following probability in a multi-person scene can be reduced, the stability and controllability of target locking and following are improved, and a smoother and more accurate following effect is kept when the target moves and the environment changes.

The application discloses a kind of multi-agent preset time formation control methods based on backstepping method under distance rigidity matrix, comprising: 1) based on the double integrator dynamics model of multi-agent system is established based on rigidity graph theory, define the minimum and infinitesimal rigidity frame corresponding to the expected formation;2) introduce backstepping design framework, define virtual speed error variable;3) introduce time-varying scaling function to construct time scale transformation;4) design distributed preset time controller;5) through numerical simulation and physical platform are verified, verify the effectiveness of distance error in user preset time under different initial conditions converges to the vicinity of zero.The application is fused by backstepping and preset time scaling function, for the first time in only local relative measurement distance rigidity formation Convergence time user self-defined preset is realized, and convergence time upper bound is independent of initial condition and controller parameter, provides reliable, engineering implementation solution for time-critical multi-agent cooperative task.

The present application relates to a kind of radar sea surface target measurement error correction method and system based on AIS.The method comprises: obtaining radar sea surface measurement target and the AIS target corresponding thereto;Error coefficient is determined using least square method according to the above-mentioned target;The distance error of radar sea surface measurement target is estimated according to error coefficient;According to distance error, the corresponding rectangular coordinate system is established;According to the bearing of radar sea surface measurement target and the corresponding rectangular coordinate system, the acute angle obtained by the intersection of the straight line of the position point of the target after correction and the position point of radar sea surface measurement target and the longitude line where radar sea surface measurement target is located is estimated;The latitude and longitude error of radar sea surface measurement target is estimated according to distance error;The position of radar sea surface measurement target is corrected according to the bearing of radar sea surface measurement target and latitude and longitude error.Using the above method can solve the problem of measurement error when radar detects sea surface target, improve the identification accuracy of radar officer to sea surface target.

The application belongs to the technical field of unmanned aerial vehicles, and relates to a method for surrounding control of an unmanned aerial vehicle based on quadratic programming, which comprises the following steps: acquiring the position and speed of the unmanned aerial vehicle, and the position and speed of a target; determining the distance r(t) between the unmanned aerial vehicle and the target according to the position of the unmanned aerial vehicle and the position of the target; determining a distance error Cost r according to r(t) and a distance expected value r0; determining a speed error Cost v according to the position of the unmanned aerial vehicle and the position of the target; constructing a target function J based on the distance error and the speed error; transforming the target function into a quadratic programming problem according to the speed of the unmanned aerial vehicle and the speed of the target in combination with a speed constraint and an acceleration constraint; obtaining optimal control instructions V u (t) by solving the quadratic programming problem based on a quadratic programming solver; and performing surrounding control on the unmanned aerial vehicle based on real-time control instructions V u (t). The method has the beneficial effect of realizing accurate and stable surrounding control of the unmanned aerial vehicle around a moving target (such as a ship) in a complex dynamic environment.

The application discloses a target capturing method based on vision and 3D radar, and belongs to the field of data processing, aiming to solve the problem of high precision requirement of 3D laser radar in identifying target objects. In the method, the target object is detected in real time through visual recognition, and when the target object is detected, the central angle thereof is output and transmitted to the 3D laser radar algorithm part through ROS2 topic communication. After the 3D laser radar receives the output angle value a0, data processing is performed to obtain a fifth distance; and then the obtained M fifth distances are sequentially subjected to average filtering, low-pass filtering, Kalman filtering and difference filtering, so that the final distance is obtained. The application can realize real-time capturing and positioning of the target object at a frequency of more than 10 Hz at a low cost, and complete the target object tracking task with long distance, high precision, high reliability and high frame rate. The final distance error obtained by the method is less than 5 cm.

The invention discloses a self-adaptive path tracking control method and device for an unmanned ship, and relates to the technical field of unmanned ships. The method comprises the following steps of S1, dynamically generating real-time position, speed and course information of a virtual pilot ship based on input expected path geometric information and expected speed, and enabling the virtual pilot ship to move along an expected path at the expected speed; s2, acquiring navigation information of the unmanned ship in real time, and calculating a relative distance error and a relative speed error between the unmanned ship and the virtual pilot ship; and S3, constructing a sliding mode surface on the basis of the relative distance error and the relative speed error. According to the method, the concept of dynamic virtual pilot ships is introduced, a complex path tracking problem is converted into a visual queue tracking problem, and the defect that a traditional method depends on an accurate dynamic model is overcome. And sliding mode control based on relative errors is combined with a single adaptive law, so that the structure of the controller is remarkably simplified, and the parameter setting difficulty is reduced.

This invention discloses a method, apparatus, medium, and device for evaluating camera distortion correction effects. The method includes: performing affine transformation processing on a target object image after distortion removal, ensuring the target object is within the image range and that the feature points in the middle and edge portions of the processed target object image have consistent scales; detecting all feature points in the processed target object image and performing line fitting on feature points located on the same straight line to obtain the straight line containing each feature point; calculating the distance error from the feature point to the straight line containing the feature point for each feature point, and converting the distance error corresponding to the feature point into an angular error from the feature point to the principal point of the camera lens; and evaluating the distortion correction effect based on the angular errors corresponding to all feature points. This invention, by converting the straightness error from distance error to angular error, enables the use of a unified evaluation standard, thereby achieving a unified evaluation of the camera distortion correction effect.

The invention discloses a model-free adaptive control method for a motorcade under trust mapping-driven hybrid attacks. The method comprises the following steps of: 1, processing a vehicle state and communication characteristics by utilizing a multi-layer perceptron, outputting a continuous trust value, mapping the continuous trust value into a weight factor through a cumulative distribution function, and correcting an expected distance and a control law in real time; 2, designing a distributed control law based on the expected distance and the relative state error, and constructing an equivalent data model based on input and output data under a model-free adaptive control framework; establishing an exponential stability and serial stability criterion by using a functional and linear matrix inequality, and solving a control gain; and 3, realizing real-time robust suppression and smooth recovery of various attacks of false data injection, replay, camouflage and denial of service by cyclically executing the first two steps. According to the method, the speed consistency and the rapid convergence of the spacing error can be realized in a mixed attack environment, and the robustness and the engineering implementation of fleet control are remarkably improved.

The application discloses a performance evaluation method for a teleoperation system and application thereof, and belongs to the technical field of teleoperation, and comprises the following steps: S1, mapping a master end action sequence of the teleoperation system into a target sequence of a slave device according to task requirements, and recording a corresponding slave device output sequence; calculating a distance error matrix between the target sequence and the output sequence; S2, constructing a matching path constraint condition of the target sequence and the output sequence of the teleoperation system under constant targets and switching targets based on kinematic characteristics of the slave device; and S3, performing path search on the distance error matrix under the matching path constraint condition to obtain a distance cumulative value between each target value and a corresponding output value on a shortest matching path. The application considers the influence caused by system motion characteristics, so that the shortest matching path obtained by searching for the mapping of the target sequence and the output sequence can meet an objective motion law of the teleoperation system, and the accuracy of performance evaluation of the teleoperation system is greatly improved.

The application provides a ranging method, device and depth sensor with error compensation, the method comprising: rough ranging a target in a rough measurement mode, outputting histogram data of the rough ranging, confirming a time bin corresponding to a rough distance of the target, and obtaining the rough distance of the target; in the rough measurement mode, counting the number of received photons from the start of reception, and when the number of counted received photons reaches a preset threshold, recording the time at this moment as a full-counting detection duration; fine ranging the target in a fine measurement mode, starting fine ranging from the time bin corresponding to the rough distance, and obtaining a fine distance of the target; calculating a corresponding error value according to the full-counting detection duration; and calculating the distance of the target according to the rough distance, the fine distance and the error value. The full-counting detection duration is recorded to represent the error value during ranging, error compensation can be achieved without transmitting complete histogram data, and the ranging accuracy is improved without losing the ranging efficiency.