Multi-agent quadrotor testbed control design: integral sliding mode vs. reinforcement learning
- 1 January 2005
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3712-3717
- https://doi.org/10.1109/iros.2005.1545025
Abstract
The Stanford Testbed of Autonomous Rotorcraft for Multi-Agent Control (STARMAC) is a multi-vehicle testbed currently comprised of two quadrotors, also called X4-flyers, with capacity for eight. This paper presents a comparison of control design techniques, specifically for outdoor altitude control, in and above ground effect, that accommodate the unique dynamics of the aircraft. Due to the complex airflow induced by the four interacting rotors, classical linear techniques failed to provide sufficient stability. Integral sliding mode and reinforcement learning control are presented as two design techniques for accommodating the nonlinear disturbances. The methods both result in greatly improved performance over classical control techniques.Keywords
This publication has 6 references indexed in Scilit:
- Real-Time Stabilization and Tracking of a Four-Rotor Mini RotorcraftIEEE Transactions on Control Systems Technology, 2004
- Quadrotor control using dual camera visual feedbackPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Design and control of an indoor micro quadrotorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Multiple Model-Based Reinforcement LearningNeural Computation, 2002
- Customer Retention via Data MiningArtificial Intelligence Review, 2000
- Locally Weighted LearningArtificial Intelligence Review, 1997