Deep reinforcement learning for quadrotor path following with adaptive velocity

View/Open
Cita com:
hdl:2117/334076
Document typeArticle
Defense date2020-10-24
Rights accessOpen Access
Abstract
This paper proposes a solution for the path following problem of a quadrotor vehicle based on deep reinforcement learning theory. Three different approaches implementing the Deep Deterministic Policy Gradient algorithm are presented. Each approach emerges as an improved version of the preceding one. The first approach uses only instantaneous information of the path for solving the problem. The second approach includes a structure that allows the agent to anticipate to the curves. The third agent is capable to compute the optimal velocity according to the path’s shape. A training framework that combines the tensorflow-python environment with Gazebo-ROS using the RotorS simulator is built. The three agents are tested in RotorS and experimentally with the Asctec Hummingbird quadrotor. Experimental results prove the validity of the agents, which are able to achieve a generalized solution for the path following problem.
CitationRubi, B.; Morcego, B.; Perez, R. Deep reinforcement learning for quadrotor path following with adaptive velocity. "Autonomous robots", vol. 45, p. 119-134.
ISSN0929-5593
Publisher versionhttps://link.springer.com/article/10.1007/s10514-020-09951-8
Files | Description | Size | Format | View |
---|---|---|---|---|
manuscript.pdf | Manuscrit | 4,107Mb | View/Open |
All rights reserved. This work is protected by the corresponding intellectual and industrial
property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public
communication or transformation of this work are prohibited without permission of the copyright holder