Learning agile and dynamic motor skills for legged robots

Citations Over TimeTop 1% of 2019 papers

Abstract

Legged robots pose one of the greatest challenges in robotics. Dynamic and agile maneuvers of animals cannot be imitated by existing methods that are crafted by humans. A compelling alternative is reinforcement learning, which requires minimal craftsmanship and promotes the natural evolution of a control policy. However, so far, reinforcement learning research for legged robots is mainly limited to simulation, and only few and comparably simple examples have been deployed on real systems. The primary reason is that training with real robots, particularly with dynamically balancing systems, is complicated and expensive. In the present work, we introduce a method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby leveraging fast, automated, and cost-effective data generation schemes. The approach is applied to the ANYmal robot, a sophisticated medium-dog-sized quadrupedal system. Using policies trained in simulation, the quadrupedal machine achieves locomotion skills that go beyond what had been achieved with prior methods: ANYmal is capable of precisely and energy-efficiently following high-level body velocity commands, running faster than before, and recovering from falling even in complex configurations.

Related Papers

• → Using Elastically Actuated Legged Robots in Rough Terrain: Experiments with DLR Quadruped bert(2020)15 cited
• Realization and motion analysis of multi-legged Passive Dynamic Walking(2010)
• → Demonstration and Analysis of Quadrupedal Passive Dynamic Walking(2009)38 cited
• Development of Super-multi-legged Passive Dynamic Walking robot “Jenkka-III”(2011)
• → From Morphologies of Six-, Four- and Two-Legged Animals to the HexaQuaBip Robot’s Reconfigurable Kinematics(2009)2 cited