Name
Abstract | ||
|---|---|---|
Tensegrity robots, composed of rigid rods connected by elastic cables, have a number of unique properties that make them appealing for use as planetary exploration rovers. However, control of tensegrity robots remains a difficult problem due to their unusual structures and complex dynamics. In this work, we show how locomotion gaits can be learned automatically using a novel extension of mirror descent guided policy search (MDGPS) applied to periodic locomotion movements, and we demonstrate the effectiveness of our approach on tensegrity robot locomotion. We evaluate our method with real-world and simulated experiments on the SUPERball tensegrity robot, showing that the learned policies generalize to changes in system parameters, unreliable sensor measurements, and variation in environmental conditions, including varied terrains and a range of different gravities. Our experiments demonstrate that our method not only learns fast, power-efficient feedback policies for rolling gaits, but that these policies can succeed with only the limited onboard sensing provided by SUPERball's accelerometers. We compare the learned feedback policies to learned open-loop policies and hand-engineered controllers, and demonstrate that the learned policy enables the first continuous, reliable locomotion gait for the real SUPERball robot. Our code and supplementary material is available from http://rll.berkeley.edu/drl_tensegrity. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1109/ICRA.2017.7989079 | 2017 IEEE International Conference on Robotics and Automation (ICRA) |
Keywords | Field | DocType |
deep reinforcement learning,tensegrity robot locomotion,rigid rods,elastic cables,planetary exploration rovers,complex dynamics,locomotion gaits,mirror descent guided policy search,MDGPS,periodic locomotion movements,SUPERball tensegrity robot,unreliable sensor measurements,power-efficient feedback policies,rolling gaits,onboard sensing,SUPERball accelerometers,open-loop policies,hand-engineered controllers,reliable locomotion gait,SUPERball robot | Complex dynamics,Gait,Accelerometer,Simulation,Control engineering,Tensegrity,Robot locomotion,Planetary exploration,Engineering,Robot,Reinforcement learning | Conference |
Volume | Issue | ISBN |
2017 | 1 | 978-1-5090-4634-8 |
Citations | PageRank | References |
6 | 0.52 | 10 |
Authors | ||
8 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Marvin Zhang | 1 | 19 | 2.47 |
| Xinyang Geng | 2 | 71 | 4.43 |
| Jonathan Bruce | 3 | 11 | 2.68 |
| Ken Caluwaerts | 4 | 18 | 4.29 |
| Massimo Vespignani | 5 | 139 | 11.02 |
| Vytas SunSpiral | 6 | 36 | 7.03 |
| Pieter Abbeel | 7 | 6363 | 376.48 |
| Sergey Levine | 8 | 3377 | 182.21 |