Vision Based Autonomous Tracking of UAVs Based on Reinforcement Learning
- 6 November 2020
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2020 Chinese Automation Congress (CAC)
- p. 2682-2686
- https://doi.org/10.1109/cac51589.2020.9326946
Abstract
Air-ground cooperation is of great importance in certain extreme environment missions, which require real-time tracking of the unmanned aerial vehicle (UAV) on the ground vehicle. As reinforcement learning (RL) has achieved great success in many challenges of planning and control, a research on path planning of UAVs for object tracking based on RL is presented, considering images from a visual sensor as the input. Convolutional neural networks (CNN) and a spatial soft-max layer are used to detect the object in the images. The tracking results of a filter CSR-DCF based on OpenCV are combined with the output of CNN to improve training efficiency and obtain better tracking performance. Three independent experiments are conducted with different conditions in simulated environments where a quadcopter is trained to track a ground robot based on V-REP. Valid results show that the UAV has good performance in the tracking work with MAE of 0.23m in x and 0.19m in y.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 11 references indexed in Scilit:
- Detection, Tracking, and Geolocation of Moving Vehicle From UAV Using Monocular CameraIEEE Access, 2019
- Robust Visual-Aided Autonomous Takeoff, Tracking, and Landing of a Small UAV on a Moving Landing Platform for Life-Long OperationApplied Sciences, 2019
- Visual detection and tracking with UAVs, following a mobile objectAdvanced Robotics, 2019
- A Vision-Based Neural Network Controller for the Autonomous Landing of a Quadrotor on Moving TargetsRobotics, 2018
- Autonomous Landing of a UAV on a Moving Platform Using Model Predictive ControlDrones, 2018
- Navigation control of the Khepera IV model with OpenCV in V-REP simulatorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- Multiple sclerosis identification by convolutional neural network with dropout and parametric ReLUJournal of Computational Science, 2018
- Autonomous landing of an UAV on a moving platform using model predictive controlPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Wireless communications with unmanned aerial vehicles: opportunities and challengesIEEE Communications Magazine, 2016
- Human-level control through deep reinforcement learningNature, 2015