Header logo is

Learning optimal gait parameters and impedance profiles for legged locomotion


Conference Paper


The successful execution of complex modern robotic tasks often relies on the correct tuning of a large number of parameters. In this paper we present a methodology for improving the performance of a trotting gait by learning the gait parameters, impedance profile and the gains of the control architecture. We show results on a set of terrains, for various speeds using a realistic simulation of a hydraulically actuated system. Our method achieves a reduction in the gait's mechanical energy consumption during locomotion of up to 26%. The simulation results are validated in experimental trials on the hardware system.

Author(s): Elco Heijmink and Andreea Radulescu and Brahayam Ponton and Victor Barasuol and Darwin Caldwell and Claudio Semini
Book Title: Proceedings International Conference on Humanoid Robots
Year: 2017
Month: November
Publisher: IEEE

Department(s): Autonomous Motion
Bibtex Type: Conference Paper (conference)
Paper Type: Conference

Event Name: 2017 IEEE-RAS 17th International Conference on Humanoid Robots
Event Place: Birmingham, UK

Links: paper


@conference{Reinforcement Learning,
  title = {Learning optimal gait parameters and impedance profiles for legged locomotion},
  author = {Heijmink, Elco and Radulescu, Andreea and Ponton, Brahayam and Barasuol, Victor and Caldwell, Darwin and Semini, Claudio},
  booktitle = {Proceedings International Conference on Humanoid Robots},
  publisher = {IEEE},
  month = nov,
  year = {2017},
  month_numeric = {11}