Deep Feature Representation Based Imitation Learning for Autonomous Helicopter Aerobatics
- 21 January 2021
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 2 (5), 437-446
- https://doi.org/10.1109/tai.2021.3053511
Abstract
The drastic changes in flight parameters during aerobatics and the high instability of the system make the control of autonomous aerobatics unusually difficult. In this paper, we propose a deep feature representation based imitation learning method for autonomous aerobatics, which leverages expert demonstrations to efficiently learn the mapping of highdimensional flight observations onto continuous actions (pitch, tail, and thrust). Different from the existing methods, our proposed method requires neither trajectory so it can greatly simplify the controller solution steps and reduce the computational burden. Particularly, our method uses the proposed deep feature representation network (DFR-network) to directly map the experts’ demonstration trajectory to a deep representation space spanned by a set of learned subspaces which represent the motion patterns with the same statistical property among demonstration trajectories. Various aerobatic maneuvers can be encoded in the deep representation space through a simple combination of embedding features. Accordingly, the proposed method can perform arbitrary aerobatic maneuvers by observing a limit set of expert demonstrations. The effectiveness of the deep feature representation based imitation learning method is verified on the real-world flight data. Experiments show that compared with the existing methods, our proposed method has higher control accuracy, stronger robustness and anti-interference ability.Keywords
Funding Information
- National Key Research and Development Projects of China (2018AAA0100800, 2018YFE0106800)
- National Natural Science Foundation of China (61773360, 61725304, 61673361, 61872327)
- Major Science and Technology Projects of Anhui Province (912198698036)
- Fundamental Research Funds for the Central Universities (WK2380000001)
- Huawei Technologies Co. Ltd.
- China Postdoctoral Science Foundation (2020M682036)
This publication has 20 references indexed in Scilit:
- Deep learning helicopter dynamics modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- On Replacing PID Controller with Deep Learning Controller for DC Motor SystemJournal of Automation and Control Engineering, 2015
- Autonomous Helicopter Aerobatics through Apprenticeship LearningThe International Journal of Robotics Research, 2010
- Dynamic Time WarpingPublished by Springer Science and Business Media LLC ,2007
- Dynamics systems vs. optimal control — a unifying viewProgress in Brain Research, 2007
- Autonomous Inverted Helicopter Flight via Reinforcement LearningPublished by Springer Science and Business Media LLC ,2006
- Universal approximation theorem for uninorm-based fuzzy systems modelingFuzzy Sets and Systems, 2003
- (Almost) exact path tracking control for an autonomous helicopter in hover manoeuvresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- UAVs: an overviewAir & Space Europe, 1999
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951