Transfer learning of gaits on a quadrupedal robot
Learning new gaits for compliant robots is a challenging multi-dimensional optimization task. Furthermore, to ensure optimal performance, the optimization process must be repeated for every variation in the environment, for example for every change in inclination of the terrain. This is unfortunately not possible using current approaches, since the time required for the optimization is simply too high. Hence, a sub-optimal gait is often used. The goal in this manuscript is to reduce the learning time of a particle swarm algorithm, such that the robot's gaits can be optimized over a wide variety of terrains. To facilitate this, we use transfer learning by sharing knowledge about gaits between the different environments. Our findings indicate that using transfer learning new robust gaits can be discovered faster compared to traditional methods that learn a gait for each environment independently.
Published in: Adaptive behavior, 10.1177/1059712314563620, Sage Publications
- Dieser Beitrag ist mit Zustimmung des Rechteinhabers aufgrund einer (DFG geförderten) Allianz- bzw. Nationallizenz frei zugänglich.
- This publication is with permission of the rights owner freely accessible due to an Alliance licence and a national licence (funded by the DFG, German Research Foundation) respectively.