Aggressive Quadrotor Flight Using Curiosity-Driven Reinforcement Learning
- 25 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 69 (12) , 13838-13848
Abstract
The ability to perform aggressive movements,which are called aggressive flights, is important for quadrotors during navigation. However, aggressive quadrotor flights are still a great challenge to practical applications. The existing solutions to aggressive flights heavily rely on a predefined trajectory, which is a time-consuming preprocessing step. To avoid such path planning, we propose a curiosity-driven reinforcement learning method for aggressive flight missions and a similarity-based curiosity module is introduced to speed up the training procedure. A branch structure exploration strategy is also applied to guarantee the robustness of the policy and to ensure the policy trained in simulations can be performed in real-world experiments directly. The experimental results in simulations demonstrate that our reinforcement learning algorithm performs well in aggressive flight tasks, speeds up the convergence process and improves the robustness of the policy. Besides, our algorithm shows a satisfactory simulated to real transferability and performs well in real-world experiments.Keywords
All Related Versions
Funding Information
- Ministry of Science and Technology of the People's Republic of China (2018AAA0101602)
- National Natural Science Foundation of China (62136003)
- Introducing Talents of Discipline to Universities (B17017)
- Program of Shanghai Academic Research Leader (20XD1401300)
- Chinesisch-Deutsche Zentrum für Wissenschaftsförderung (M-0066)
This publication has 32 references indexed in Scilit:
- Robust Attitude Stabilization for Nonlinear Quadrotor Systems With Uncertainties and DelaysIEEE Transactions on Industrial Electronics, 2017
- Estimation, Control, and Planning for Aggressive Flight With a Small Quadrotor With a Single Camera and IMUIEEE Robotics and Automation Letters, 2016
- Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search2016
- Aggressive quadrotor flight using dense visual-inertial fusion2016
- Data-Driven Optimal Consensus Control for Discrete-Time Multi-Agent Systems With Unknown Dynamics Using Reinforcement Learning MethodIEEE Transactions on Industrial Electronics, 2016
- Human-level control through deep reinforcement learningNature, 2015
- Toward a Fully Autonomous UAV: Research Platform for Indoor and Outdoor Urban Search and RescueIEEE Robotics & Automation Magazine, 2012
- Collaborative mapping of an earthquake‐damaged building via ground and aerial robotsJournal of Field Robotics, 2012
- Nonlinear Robust Tracking Control of a QuadrotorUAVonSE(3)Asian Journal of Control, 2012
- Exact indexing of dynamic time warpingKnowledge and Information Systems, 2005