A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Filters
Autonomous Inverted Helicopter Flight via Reinforcement Learning
[chapter]
2006
Springer Tracts in Advanced Robotics
In this paper, we describe a successful application of reinforcement learning to designing a controller for sustained inverted flight on an autonomous helicopter. ...
Then, a reinforcement learning algorithm was applied to automatically learn a controller for autonomous inverted hovering. ...
Acknowledgments We give warm thanks to Sebastian Thrun for his assistance and advice on this project, to Jin Kim for helpful discussions, and to Perry Kavros for his help constructing the helicopter. ...
doi:10.1007/11552246_35
fatcat:pnla6wrdfjdxtda36nkdpohv3i
An Application of Reinforcement Learning to Aerobatic Helicopter Flight
2006
Neural Information Processing Systems
Autonomous helicopter flight is widely regarded to be a highly challenging control problem. ...
Our experimental results significantly extend the state of the art in autonomous helicopter flight. ...
Acknowledgments We thank Ben Tse for piloting our helicopter and working on the electronics of our helicopter. We thank Mark Woodward for helping us with the vision system. ...
dblp:conf/nips/AbbeelCQN06
fatcat:sgt5dfvr6bhcvc4zdq4wpyvhci
Apprenticeship learning for helicopter control
2009
Communications of the ACM
a Autorotation is an emergency maneuver that allows a trained pilot to descend and land the helicopter without engine power. ...
Since we have expert demonstrations of the desired behavior (namely, following the trajectory) we can alleviate the tuning problem by employing the apprenticeship learning via inverse reinforcement learning ...
In particular, the demonstrations allow us to learn a model of the helicopter dynamics, as well as appropriate choices of target trajectories and reward parameters for input into a reinforcement learning ...
doi:10.1145/1538788.1538812
fatcat:l7eea37tb5hbdpb6brtvmsjfca
Autonomous Autorotation of an RC Helicopter
[chapter]
2009
Springer Tracts in Advanced Robotics
In this paper, we present the first autonomous controller to successfully pilot a remotely controlled (RC) helicopter during an autorotation descent and landing. ...
In case of engine failure, skilled pilots can save a helicopter from crashing by executing an emergency procedure known as autorotation. ...
Acknowledgments We thank Garett Oku for piloting and building our helicopter. This work was supported in part by the DARPA Learning Locomotion program under contract number FA8650-05-C-7261. ...
doi:10.1007/978-3-642-00196-3_45
fatcat:wlc4ljfsqvdjbbh2kuadromezu
Deep Learning and Reinforcement Learning for Autonomous Unmanned Aerial Systems: Roadmap for Theory to Deployment
[article]
2020
arXiv
pre-print
Then we discuss how reinforcement learning is explored for using this information to provide autonomous control and navigation for UAS. ...
Therefore, in this chapter, we discuss how some of the advances in machine learning, specifically deep learning and reinforcement learning can be leveraged to develop next-generation autonomous UAS. ...
Early works of applying reinforcement learning to UAV control problems focused on autonomous helicopters [45, 81, 104, 37] . ...
arXiv:2009.03349v2
fatcat:5ylreoukrfcrtorzzp44mntjum
Autonomous Helicopter Aerobatics through Apprenticeship Learning
2010
The international journal of robotics research
Autonomous helicopter flight is widely regarded to be a highly challenging control problem. ...
These apprenticeship learning algorithms have enabled us to significantly extend the state of the art in autonomous helicopter aerobatics. ...
Acknowledgments We thank Garett Oku for piloting and building our helicopters. This work was supported in part by the DARPA Learning Locomotion program under contract number FA8650-05-C-7261. ...
doi:10.1177/0278364910371999
fatcat:vbovjwfozzfv5cy3ykyq5mbjuq
OATS: Oxford Aerial Tracking System
2007
Robotics and Autonomous Systems
Small robot helicopters are becoming a popular research platform due to the availability of off-the-shelf components and their suitability for useful applications. ...
We describe the Oxford Aerial Tracking System (OATS) that we are commissioning which takes a commercial airframe and low-level flight controller, and adapts these for use in applications requiring the ...
In their latest publications they have reported inverted helicopter flight via reinforcement learning (Ng et al., 2004) and the capability to learn activity-based ground models from a moving UAV helicopter ...
doi:10.1016/j.robot.2007.05.010
fatcat:gwl7nwxyrvburkppkexcnqqyoa
Experiments with Small Unmanned Helicopter Nose-Up Landings
2009
Journal of Guidance Control and Dynamics
Ng, A., Coates, A., Diel, M., Ganapathi, V., Schulte, J., Tse, B., Berger, E., and Liang, E., “Inverted Autonomous Helicopter Flight via Reinforcement Learning,” Proceedings of the International Symposium ...
- 759. doi: 10.2514/1.8980 Abbeel, P., Coates, A., Quigley, M., and Ng, A., “An Application of Reinforcement Learning to Aerobatic Helicopter Flight,” Proceedings of the Neural Information Processing Systems ...
doi:10.2514/1.36470
fatcat:4zjmkawwbzhk5g77ifsjuozhre
Intelligent Vision-based Autonomous Ship Landing of VTOL UAVs
[article]
2022
arXiv
pre-print
Extensive simulations and flight tests were conducted to demonstrate vertical landing safety, tracking capability, and landing accuracy. ...
The central idea involves automating the Navy helicopter ship landing procedure where the pilot utilizes the ship as the visual reference for long-range tracking; however, refers to a standardized visual ...
capability by combining the current control system with reinforcement learning techniques so that the aircraft could robustly fly through the ship wake during the approach and landing phases.
VII. ...
arXiv:2202.13005v2
fatcat:jfyybm5a7redjna33si3aitnhe
Towards an Experimental Autonomous Blimp Platform
2007
European Conference on Mobile Robots
We evaluate the performance of the components and demonstrate their integration in a reinforcement learning setting. ...
In this paper, we present the design of an autonomous indoor blimp. ...
REINFORCEMENT LEARNING AS ONLINE APPLICATION In this section, we introduce how the blimp described so far can be used as an autonomous platform. ...
dblp:conf/emcr/RottmannSZBRS07
fatcat:x3lq2kpq7vee3hhohikkyoiney
Design of DDP controller for autonomous autorotative landing of RWUAV following an engine failure
2016
2016 IEEE Conference on Control Applications (CCA)
Reinforcement learning algorithm often includes learning of some form of system model while determining an optimal policy. ...
Some reinforcement learning problems are [Jategaonkar et al., 2004] : • The issue of high dimension, simple reinforcement learning algorithms based on discretization scale exponentially with the number ...
doi:10.1109/cca.2016.7587814
dblp:conf/IEEEcca/MatlalaP16
fatcat:z3hnlp26o5hjjcigffojqbipci
An Algorithmic Perspective on Imitation Learning
2018
Foundations and Trends in Robotics
it and more familiar frameworks like statistical supervised learning theory and reinforcement learning. ...
This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning. This work provides an introduction to imitation learning. ...
demonstrates acrobatic RC helicopter flight by learning from trajectories demonstrated by a human expert. In this system, the desired (a) Learning of acrobatic RC helicopter maneuvers . ...
doi:10.1561/2300000053
fatcat:4v52sabhnze5ddnuy7sd3vj2ym
Control of autonomous airship
2009
2009 IEEE International Conference on Robotics and Biomimetics (ROBIO)
Then an intelligent navigation control method, reinforcement learning control, is introduced in the autonomous blimp which was used for 2007 UAV Outback Challenge. ...
The control of Autonomous airship is a very important problem for the aerial robots research. ...
Reinforcement learning is one certain intelligent learning technology, which can help facilitate an easier design process for autonomous control system, and reduces human intervention as much as possible ...
doi:10.1109/robio.2009.5420403
dblp:conf/robio/LiuPSN09
fatcat:ihnpgeabw5gwrjn4yvpx2lo5uu
Average-Payoff Reinforcement Learning
[chapter]
2017
Encyclopedia of Machine Learning and Data Mining
AUC
Area Under Curve
Authority Control Record Linkage
Autonomous Helicopter Flight Using Reinforcement Learning
Definition Helicopter flight is a highly challenging control problem. ...
If this trade-off is incorrectly Autonomous Helicopter Flight Using Reinforcement Learning, Fig. 2 Snapshots of an autonomous helicopter performing in-place flips and rolls chosen, the controller may ...
Cross-References Efficient Exploration in Reinforcement Learning Hierarchical Reinforcement Learning Model-Based Reinforcement Learning ...
doi:10.1007/978-1-4899-7687-1_100029
fatcat:jub4ulyg45abnf4qgutimczie4
A/B Testing
[chapter]
2017
Encyclopedia of Machine Learning and Data Mining
AUC
Area Under Curve
Authority Control Record Linkage
Autonomous Helicopter Flight Using Reinforcement Learning
Definition Helicopter flight is a highly challenging control problem. ...
If this trade-off is incorrectly Autonomous Helicopter Flight Using Reinforcement Learning, Fig. 2 Snapshots of an autonomous helicopter performing in-place flips and rolls chosen, the controller may ...
Cross-References Efficient Exploration in Reinforcement Learning Hierarchical Reinforcement Learning Model-Based Reinforcement Learning ...
doi:10.1007/978-1-4899-7687-1_100507
fatcat:bg6sszljsrax5heho4glbcbicu
« Previous
Showing results 1 — 15 out of 1,771 results