Abstract
Much of robotics research aims to develop control solutions that exploit the machine’s dynamics in order to achieve an extraordinarily agile behaviour [1]. This, however, is limited by the use of traditional model-based control techniques such as model predictive control and quadratic programming. These solutions are often based on simplified mechanical models which result in mechanically constrained and inefficient behaviour, thereby limiting the agility of the robotic system in development [2]. Treating the control of robotic systems as a reinforcement learning (RL) problem enables the use of model-free algorithms that attempt to learn a policy which maximizes the expected future (discounted) reward without inferring the effects of an executed action on the environment.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gangapurwala, S., et al.: Generative adversarial imitation learning for quadrupedal locomotion using unstructured expert demonstrations (2018)
Mastalli, C., et al.: Trajectory and foothold optimization using low-dimensional models for rough terrain locomotion (2017)
Hwangbo, J., et al.: Learning agile and dynamic motor skills for legged robots. Sci. Robot. 4(26), eaau5872 (2019). https://doi.org/10.1126/scirobotics.aau5872
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017)
Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889–1897, 1 June 2015
Rohmer, E., Signgh, S. P. N., Freese, M.: V-REP: a versatile and scalable robot simulation framework. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (2013)
Hutter, M., et al.: ANYmal - a highly mobile and dynamic quadrupedal robot. In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, pp. 38–44 (2016). https://doi.org/10.1109/IROS.2016.7758092
Liang, J., et al.: GPU-accelerated robotic simulation for distributed reinforcement learning. CoRL (2018)
Acknowledgments
This research is supported by the UKRI and EPSRC (EP/R026084/1, EP/R026173/1, EP/S002383/1) and the EU H2020 project MEMMO (780684). This work has been conducted as part of ANYmal Research, a community to advance legged robotics.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Jones, W., Gangapurwala, S., Havoutis, I., Yoshida, K. (2019). Towards Generating Simulated Walking Motion Using Position Based Deep Reinforcement Learning. In: Althoefer, K., Konstantinova, J., Zhang, K. (eds) Towards Autonomous Robotic Systems. TAROS 2019. Lecture Notes in Computer Science(), vol 11650. Springer, Cham. https://doi.org/10.1007/978-3-030-25332-5_42
Download citation
DOI: https://doi.org/10.1007/978-3-030-25332-5_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-25331-8
Online ISBN: 978-3-030-25332-5
eBook Packages: Computer ScienceComputer Science (R0)