A simple learning strategy for high-speed quadrocopter multi-flips
Top Cited Papers
- 1 May 2010
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2010 IEEE International Conference on Robotics and Automation
- p. 1642-1648
- https://doi.org/10.1109/robot.2010.5509452
Abstract
We describe a simple and intuitive policy gradient method for improving parametrized quadrocopter multi-flips by combining iterative experiments with information from a first-principles model. We start by formulating an N-flip maneuver as a five-step primitive with five adjustable parameters. Optimization using a low-order first-principles 2D vertical plane model of the quadrocopter yields an initial set of parameters and a corrective matrix. The maneuver is then repeatedly performed with the vehicle. At each iteration the state error at the end of the primitive is used to update the maneuver parameters via a gradient adjustment. The method is demonstrated at the ETH Zurich Flying Machine Arena testbed on quadrotor helicopters performing and improving on flips, double flips and triple flips.Keywords
This publication has 11 references indexed in Scilit:
- Policy search via the signed derivativePublished by Robotics: Science and Systems Foundation ,2009
- Performing aggressive maneuvers using iterative learning controlPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Real-time indoor autonomous vehicle test environmentIEEE Control Systems, 2008
- Learning for control from multiple demonstrationsPublished by Association for Computing Machinery (ACM) ,2008
- Quadrotor Helicopter Flight Dynamics and Control: Theory and ExperimentPublished by American Institute of Aeronautics and Astronautics (AIAA) ,2007
- Energy-efficient Autonomous Four-rotor Flying Robot Controlled at 1 kHzProceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (cat. No.01ch37164), 2007
- Trajectory generation and control for four wheeled omnidirectional vehiclesRobotics and Autonomous Systems, 2005
- Multi-agent quadrotor testbed control design: integral sliding mode vs. reinforcement learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Near-optimal dynamic trajectory generation and control of an omnidirectional vehicleRobotics and Autonomous Systems, 2004
- PID vs LQ control techniques applied to an indoor micro quadrotorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004