RONov 2, 2020

Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition

arXiv:2011.01387v2224 citations
AI Analysis

This work addresses the problem of intuitive and reliable gait specification for roboticists, though it is incremental in improving reward design for legged locomotion.

The authors tackled the challenge of specifying reward functions for learning diverse bipedal gaits via sim-to-real reinforcement learning, proposing a framework based on composing periodic costs and successfully transferring learned gaits like walking and running to the Cassie robot.

We study the problem of realizing the full spectrum of bipedal locomotion on a real robot with sim-to-real reinforcement learning (RL). A key challenge of learning legged locomotion is describing different gaits, via reward functions, in a way that is intuitive for the designer and specific enough to reliably learn the gait across different initial random seeds or hyperparameters. A common approach is to use reference motions (e.g. trajectories of joint positions) to guide learning. However, finding high-quality reference motions can be difficult and the trajectories themselves narrowly constrain the space of learned motion. At the other extreme, reference-free reward functions are often underspecified (e.g. move forward) leading to massive variance in policy behavior, or are the product of significant reward-shaping via trial-and-error, making them exclusive to specific gaits. In this work, we propose a reward-specification framework based on composing simple probabilistic periodic costs on basic forces and velocities. We instantiate this framework to define a parametric reward function with intuitive settings for all common bipedal gaits - standing, walking, hopping, running, and skipping. Using this function we demonstrate successful sim-to-real transfer of the learned gaits to the bipedal robot Cassie, as well as a generic policy that can transition between all of the two-beat gaits.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes