Autonomous Helicopter Flight via Reinforcement Learning

  title={Autonomous Helicopter Flight via Reinforcement Learning},
  author={Andrew Y. Ng and Hyoun Jin Kim and Michael I. Jordan and S. Shankar Sastry},
Autonomous helicopter flight represents a challenging cont rol problem, with complex, noisy, dynamics. In this paper, we describe a s uccessful application of reinforcement learning to autonomous helic opter flight. We first fit a stochastic, nonlinear model of the helicopter dy namics. We then use the model to learn to hover in place, and to fly a number of maneuvers taken from an RC helicopter competition. 
Highly Influential
This paper has highly influenced 15 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 357 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.
Showing 1-10 of 200 extracted citations

Safe reinforcement learning in high-risk tasks through policy improvement

2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) • 2011
View 7 Excerpts
Highly Influenced

Policy Improvement through Safe Reinforcement Learning in High-Risk Tasks

Javier Garćıa
View 8 Excerpts
Highly Influenced

Predictive State Representations for grounding human-robot communication

2010 IEEE International Conference on Robotics and Automation • 2010
View 5 Excerpts
Highly Influenced

The Current State of Autonomous Helicopter Flight

Samuel Moczygemba
View 11 Excerpts
Highly Influenced

357 Citations

Citations per Year
Semantic Scholar estimates that this publication has 357 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 12 references

Shaping and policy search in reinforcement learning

Andrew Y. Ng
PhD thesis, • 2003
View 2 Excerpts

: A policy search method for large MDPs and POMDPs

Andrew Y. Ng, Michael I. Jordan. P EGASUS
Proc . 16 th Conf . Uncertainty in Artificial Intelligence • 2000

EGASUS: A policy search method for large MDPs and POMDPs

Andrew Y. Ng, P MichaelI.Jordan.
Proc. 16th Conf. Uncertainty in Artificial Intelligence • 2000
View 1 Excerpt

Schaal and A . Moore . Locally weighted learning

S. Atkeson
AI Review • 2000

Hierarchical flight control system synthesis for rotorcraftbased unmanned aerial vehicles

Hyunchul Shim

Locally weighted lear ning

C. Atkeson S. Schaal, A. Moore
AI Review, • 1997

and R

G. Balas, J. Doyle, K. Glover, A. Packard
Smith. -analysis and synthesis toolbox user’s guide • 1995
View 1 Excerpt

Cao.Pertubation analysis of discrete event dynamic systems

X. Y. Ho

Similar Papers

Loading similar papers…