18results about How to "Improve navigation performance" patented technology

The invention relates to the technical field of electric wheelchair control, in particular to a multi-mode navigation control method and system of an electric wheelchair controller. The method comprises the following steps: acquiring a real-time environment monitoring video based on an electric wheelchair high-definition camera; video jitter distortion compensation and dynamic object frame-by-frame continuous optical flow tracking are carried out on the real-time environment monitoring video, and a moving track of each dynamic object is generated; performing environment static obstacle accurate identification on the real-time environment monitoring video, and performing dynamic environment perception modeling based on a moving track of each dynamic object so as to generate a dynamic environment map; a navigation mode switching decision is made based on a real-time wheelchair operation instruction of the user to obtain a current navigation mode of the user, and the current navigation mode of the user comprises a rocker control mode and an intelligent navigation mode. According to the invention, efficient and intelligent multi-mode control of the electric wheelchair is realized, so that the electric wheelchair can more flexibly and safely cope with a complex environment.

The invention relates to the technical field of automatic loading and unloading of logistics forklifts, in particular to a novel automatic loading and unloading system of an unmanned forklift in a van environment, and the system comprises a positioning map binding module which is used for binding platform areas where a plurality of trucks are parked on a positioning map; and the task issuing module is configured to receive a task issued by a driver through a pad system when a truck arrives and transmit the task to a warehouse management system (WMS), and the WMS issues a cargo taking and placing task of a corresponding map point position according to a platform number. And the visual servo system adopting the solid-state laser radar provides high-precision and high-stability navigation capability for the AGV.

The invention relates to the technical field of path planning, in particular to a laser forklift goods taking path re-planning and self-adaptive optimization method. The method comprises the following steps: setting all parameter values required in calculation; the cargo tray position and the inclination angle recognized by the camera are obtained; according to the position and angle information of the tray, a third-order Bezier curve type goods taking route with the current position of the AGV as a starting point is planned; and according to the length and width of the fork of the forklift and the width of the tray, the planned route is adaptively optimized and adjusted, so that the forklift does not collide with the tray when running on the route. By comprehensively considering the current position and orientation of the AGV and the conversion relation among multiple coordinate systems, an accurate third-order Bezier curve type goods taking route is planned, adaptive optimization of the route is carried out, and the distance between control points is flexibly adjusted so as to balance the collision risk and the route curvature change, so that the accuracy of goods taking is improved. The safe distance between the forklift and the tray in the driving process is guaranteed, and collision is avoided.

The application discloses a heterogeneous flight cluster inertial navigation error cooperative correction method based on pseudo observation, which is composed of multiple unmanned aerial vehicles (UAVs) and the UAVs observe each other, and comprises the following steps: S1, acquiring inertial navigation positions of the UAVs at a current time and inertial navigation position estimation noises; S2, selecting a reference anchor point, and obtaining relative distance observation, relative azimuth observation and relative pitch angle observation among the UAVs in the cluster; S3, establishing an observation equation of the heterogeneous cluster UAVs according to the observation data obtained in the step S2; S4, constructing a pseudo observation equation according to whether the observation equation is sufficient; S5, classifying according to the rank of an observation matrix, and solving the observation equation; and S6, updating the inertial navigation position, attitude and speed of each UAV. The inertial navigation position information after correction is combined with the inertial navigation information to correct and update the navigation position, attitude and speed, and better overall positioning precision of the cluster can be obtained when the available observation quantity is insufficient.

The invention discloses a real-time imaging dynamic navigation system for a breast tumor interventional operation, which comprises an acousto-optic scanning device, a Redis client, a Redis server, a database, a modeling platform, a Three.js dynamic driving engine and a display terminal, and is characterized in that the acousto-optic scanning device is arranged above a breast tumor and performs scanning and data acquisition in a non-contact manner during the operation; the Redis client, the Redis server and the database respectively acquire, distribute and store the acquired data, and the modeling platform performs model construction on the received data. A Three.js dynamic driving engine composed of a breast tumor data input end, an initial data driving unit, an incremental data driving unit, a rendering unit and a dynamic image output end carries out data processing on the model in a data driving mode. According to the dynamic navigation system, real-time data acquisition, transmission and data processing are realized, the generated navigation image is visual and dynamic, high-quality image guidance is provided for an operation, and the success rate and accuracy of the operation are improved.

The invention discloses an indoor robot sensing method based on point cloud multi-sensor fusion mapping, and relates to an indoor intelligent robot sensing method, which comprises the following steps of: obtaining multi-frame point cloud images of surrounding environment and obstacles by using a binocular camera and a laser radar; processing and fusing the three-dimensional point cloud images respectively acquired by the two three-dimensional point cloud images; in order to improve the robustness of perception, the three-dimensional point cloud is preprocessed before fusion, and interference of point cloud noise on subsequent matching is avoided; based on the target point cloud data corresponding to each frame of image, the point cloud map is accurately registered, so that the intelligent robot can specifically understand the external environment. According to the method, fusion mapping is carried out based on the point cloud data obtained by different sensors, the environment information of the intelligent equipment is determined, the wrong point cloud determined according to the depth corresponding to each point cloud is filtered out from the target point cloud data, and the mapping effect is optimized by filtering out the wrong point cloud influencing the accuracy of the volume measurement result, so that the accuracy of the volume measurement result is improved. The mapping error is obviously reduced, the sensing precision of the robot is improved, and the robustness of the system is improved.

The present invention discloses a visual language navigation method integrating a grid map and a topological map, belonging to the field of navigation technology. The method receives RGB and depth information through a waypoint predictor and linearly fuses them into RGBD information, thereby generating useful reachable nodes; in short-term reasoning, a grid map is used to model local historical observations during navigation, and time and space information is used to describe the environment of local visits; in long-term reasoning, a topological map is used to spontaneously update the topological map through the waypoints generated by the waypoint predictor, and the waypoints are effectively added to the dynamic topological map; then, a path is planned across modalities through visual and semantic information, and long-term and short-term navigation scores are dynamically integrated to make navigation actions. The present invention improves the accuracy of navigation.

The invention relates to the technical field of water surface three-dimensional collaborative navigation scheme design, in particular to a water surface three-dimensional collaborative navigation method and system and electronic equipment. The underwater electromagnetic wave communication frequency automatic modulation model is trained, and after model training is completed and submarine position data of a target submarine are obtained through a sonar detector arranged on a water surface platform, the distance between the submarine position data and GPS position information of an underwater subsurface buoy is calculated; and inputting the distance into an underwater electromagnetic wave communication frequency automatic modulation model, and controlling the underwater subsurface buoy to communicate with the target submarine through electromagnetic waves according to a predicted electromagnetic wave frequency output by the model. The underwater electromagnetic wave communication frequency is automatically modulated, the technical problems that the influence on signal transmission is also increased due to the increase of the transmission distance, and the transmission frequency is difficult to be reasonably modulated in a threshold value calculation mode are effectively solved, and the positioning and navigation effects of the navigation system of the submarine are further improved to a great extent.

The present invention relates to a UAV visual navigation method and device based on deep learning, including: obtaining a visual image collected by a UAV visual system, extracting features from the visual image, and obtaining an image feature representation; performing type analysis on the image feature representation to obtain scene data, depth information, and continuous image frames; performing scene recognition on the scene data to obtain recognition results of obstacles and passable areas; performing optical flow estimation on the continuous image frames and the depth information through a preset optical flow algorithm to obtain a pose estimation result; obtaining the mission requirements of the UAV to obtain a navigation control strategy with environmental adaptability; optimizing the adaptive hybrid learning model based on the feedback information combined with a preset attention mechanism and reward shaping conditions to obtain the optimized adaptive hybrid learning model. The present invention can improve the adaptability of UAVs in complex and dynamic environments.

This invention belongs to the field of intelligent robotics and visual navigation technology, and discloses a spatiotemporal graph-based object navigation method based on target correlation. It constructs a target-related object relationship graph and combines local relationship modeling with a global serialized information propagation mechanism to effectively model object relationships in the environment. Simultaneously, by introducing target correlation to control the information propagation order, node features can be updated progressively according to target correlation, thereby enhancing the modeling ability of long-distance dependencies. Combining temporal feature modeling with action decision-making processes, it achieves efficient robot navigation in complex environments. This invention can utilize the relationship information between objects in target object navigation tasks to improve target orientation capabilities; enhance long-distance dependency modeling capabilities through a serialized information propagation mechanism to improve navigation success rate; and exhibit stronger decision-making stability and environmental adaptability in complex environments and long-path tasks, thus improving overall navigation performance.

The invention belongs to the field of artificial intelligence technology, and specifically relates to a binocular vision navigation method for an unmanned vehicle based on an improved artificial potential field method. Firstly, a semi-global stereo matching algorithm in binocular vision is used to realize real-time perception of depth information of a scene, an FPGA implementation framework of the semi-global stereo matching algorithm based on block comparison is designed, the semi-global stereo matching algorithm is modularized, parallel operation is adopted within the module, and pipeline operation is adopted between modules to accelerate it, thereby reducing resource usage and improving the real-time performance of the stereo matching algorithm. Then, binarization, median filtering, connected domain detection and other operations are performed on the current scene, and the obstacle distance of the current scene is output in combination with a disparity map. Finally, in view of the local minimum value problem in the traditional artificial potential field method, the invention effectively solves the local minimum value problem by autonomously establishing a virtual target point, and realizes the path planning of the unmanned vehicle. The method of the invention is verified on a built unmanned vehicle system, and experimental results show the feasibility and superiority of the method of the invention.

The invention provides a mobile robot navigation method and system based on a rotary imaging radar and satellite positioning, and relates to the technical field of mobile robot navigation. Synchronously acquiring surrounding environment three-dimensional point cloud data, satellite positioning data and inertial measurement data; feature information is extracted and integrated to generate positioning attitude data; distinguishing static and dynamic characteristics according to the three-dimensional point cloud data, and generating a dynamic local environment map; when the satellite positioning signal fails, dead reckoning is carried out by combining the three-dimensional point cloud data, the inertial measurement data and the positioning attitude data before failure, and the positioning attitude data is updated; and combining the new positioning attitude data and the dynamic local environment map with the target driving data to generate an initial navigation control instruction, continuously collecting a data dynamic adjustment instruction, and controlling the robot to complete navigation. The method can adapt to a complex dynamic environment and realize high-precision reliable navigation.

The invention relates to the field of robot terrain perception, and provides an illumination condition adaptive soil humidity estimation method based on multi-modal data fusion. The method comprises the following steps: firstly, providing an optimal exposure time calculation method for constructing a multi-modal soil humidity data set; secondly, soil image shadows are removed through an SS-GAN algorithm, a channel attention mechanism ECA and a standard convolutional layer are improved in combination with environmental information, ResNet-50 is embedded as a network backbone, and soil humidity estimation sub-models adapted to different illumination conditions are designed; then, training each sub-model by using an improved loss function to enable the sub-model to adapt to a specific illumination condition; finally, a sub-model fusion and switching method is provided, and a soil humidity estimation map is generated through gray value mapping. According to the invention, multi-modal data fusion is carried out through the improved neural network model, and a fusion and switching algorithm of the sub-models is designed, so that the soil humidity estimation precision of the robot under a complex illumination condition can be improved, and thus the terrain perception capability is improved.

The application provides a polarization tailing error estimation method based on meta-learning in a high dynamic environment, and belongs to the field of bionic polarization navigation, and comprises the following steps: a polarization angle error database caused by tailing interference under different rotating speeds is established; in an offline stage, a rotating speed related network and a rotating speed independent network are trained based on a meta-learning strategy, polarization angle errors are decoupled into rotating speed related features and rotating speed independent features; in an online stage, when performing linear motion, a polarization / inertial navigation correction dynamic model three-dimensional attitude error is used; in turning motion, the rotating speed related features are taken as states, the polarization angle inverted by a carrier dynamic model is taken as a measurement, the rotating speed independent features are taken as a measurement matrix, the rotating speed related features are estimated, the rotating speed related features and the rotating speed independent features are fused, and the estimation of the polarization tailing error is completed. The application combines offline and online learning to complete adaptive estimation and compensation of the polarization tailing error under different rotating speeds in a high dynamic environment, and improves the navigation performance of a bionic polarization integrated navigation system.

The application discloses a grid mapping optimization method and system based on an adaptive control factor, and belongs to the technical field of artificial intelligence.The application comprises a semantic map establishing module, a point cloud map establishing module, a semantic database, a map gridding module and a post-rendering module.The application carries out image preprocessing after camera image data is collected, and establishes a semantic map; carries out filtering after laser radar point cloud data is collected, and establishes a point cloud map; according to the data information of the corresponding importance score Score, the distance Dis from the central observation position and the multi-material composition Mat in the semantic database in the semantic model for establishing the point cloud map, the adaptive control factor delta of each individual model in the point cloud map is determined; according to the determined adaptive control factor, the connection between spatial points is realized in the map gridding module, and a gridded map is formed; according to pixel normal interpolation calculation of a light source, the map is restored and reconstructed through a rendering module, and the authenticity and integrity of the reconstructed map are improved.

The application provides a kind of mobile robot navigation method based on deep reinforcement learning, realizes guiding to accelerate convergence before the training of deep reinforcement learning strategy, so that mobile robot can complete safe and efficient autonomous navigation only relying on on-board sensor in complex dynamic environment.The application comprises the following steps: S1, collecting data online, comprising the following steps: S11, training navigation model in simulation environment;Define the state space of mobile robot in simulation environment, and form state vector;S12, send state vector into graph attention network, obtain state representation;S13, policy network takes state representation as input, and outputs control action;The reference action of linear velocity and angular velocity is calculated by artificial potential field method;S2, during the training phase of navigation model, train critic network, policy network and graph attention network;S3, after the training of navigation model is completed, deploy navigation model on mobile robot.

The application provides an unmanned navigation method and system applied to forage harvesting, relates to the technical field of agricultural machinery automation, and first captures forage growth state signals, terrain interaction feedback signals and operation track residual signals in a work area, constructs a track residual dynamic linkage model; generates track evolution rules containing track bending amplitude adjustment, elevation compensation and offset avoidance modes based on the track residual dynamic linkage model; collects real-time signals and current operation track data of equipment in the operation process through a global perception component; inputs the same into the track residual dynamic linkage model to generate track deviation correction parameters; generates dynamic track adjustment instructions to drive equipment to update the operation track according to the track deviation correction parameters and the track evolution rules, and inputs the updated data into the model in reverse to complete cyclic optimization. The application improves the precision and adaptability of the forage harvesting unmanned navigation, and improves the harvesting efficiency and quality.

This invention discloses a scene-generalizable end-to-end autonomous navigation method based on imitation-reinforcement learning, belonging to the field of robotics technology. Addressing the problems of unstable action output and susceptibility to local optima in existing robot navigation methods, this invention constructs a TD3 network architecture, continuously interacting with the environment in a Gazebo simulation to acquire experience. The network parameters are iteratively optimized and trained using an experience replay buffer. The trained neural network outputs continuous linear and angular velocity commands for the robot based on the input state, which, after scaling, drive the robot's movement, achieving obstacle avoidance and target point navigation. Target approach rewards, collision penalties, and motion process rewards are designed to guide the policy network to improve its stable navigation ability to the target point while ensuring safe obstacle avoidance. Imitation learning is introduced to optimize the robot's motion posture; the Actor network is fine-tuned by collecting expert datasets to ensure the robot maintains posture stability during movement.