4 results about "Visual navigation system" patented technology

This invention provides a fruit stalk clamping and shearing agricultural robot and its harvesting control method. The robot includes a control cabinet, a robotic arm, and a visual navigation system mounted on a tracked chassis support platform. The control cabinet contains a host computer control system and a slave computer control system. A movable end effector with an identification and positioning system and a supplementary lighting device is installed at the end of the robotic arm. The movable end effector can flexibly adapt to the harvesting needs of different crops and complex working conditions. The host computer control system combines data collected by a depth camera and LiDAR, and uses the YOLOv8-MC model to identify target crops and their key points in the images, significantly improving the crop identification accuracy in complex environments, reducing the probability of missed or incorrect harvesting, and minimizing damage to the fruit. When constructing a global map, the host computer control system performs depth correction and map optimization for changes in illumination, further improving the robot's path planning and operational accuracy.

This invention discloses a visual navigation method and system for agricultural robots based on vehicle speed adaptive gimbal perspective, belonging to the field of agricultural robot autonomous driving technology. The method includes: real-time acquisition of driving speed and dynamic adjustment of camera pitch angle; simultaneous acquisition of color and depth images, obtaining a binary image of crop rows from the color image; generating skeleton lines in the binary image of crop rows using a regional centroid slicing connection method, fitting a global navigation line, fusing depth information, and using the Zhang Zhengyou calibration method to transform the endpoints of the global navigation line to the world coordinate system, calculating the heading angle and lateral deviation of the agricultural robot; then, performing a self-vehicle coordinate system transformation to obtain the actual control deviation; finally, sending the machine vision navigation results to the steering controller via protocol-based instructions. This invention achieves adaptive control of the inter-row observation perspective applicable to multiple operating scenarios, significantly enhancing the adaptability and reliability of the visual navigation system in complex field operating environments.

A system, method, and non-transitory computer readable medium for autonomous vehicle navigation and visual inspection utilizing a deep Q-network and reinforcement learning includes at least one camera mounted to the vehicle for capturing continuous image frames of a scene, and processing circuitry configured with a reinforcement learning engine that generates a next control action for vehicle movement based on the captured image frames and a reward for a previous control action. A self-supervised learning engine fine-tunes the deep Q-network, and a vehicle actuator maneuvers the vehicle accordingly. The visual inspection system includes a remote display terminal, an unmanned aerial vehicle (UAV) with an embedded transceiver for communicating captured image frames of a scene to the remote display terminal, and processing circuitry configured to control movement of the UAV to avoid moving objects based on the deep Q-network and reinforcement learning engine, displaying the captured image frames on the remote display terminal.