RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards

TL;DR

This paper introduces a control framework for legged robots that uses keyframing and a multi-critic reinforcement learning algorithm with a transformer encoder to achieve high-level locomotion objectives effectively in simulation and hardware.

Contribution

It proposes a novel learning-based control method combining multi-critic RL and transformer encoding to handle variable high-level goals in robot locomotion.

Findings

Multi-critic RL reduces hyperparameter tuning effort.

Transformer architecture improves goal anticipation and accuracy.

Framework successfully achieves target keyframes in experiments.

Abstract

This paper presents a novel learning-based control framework that uses keyframing to incorporate high-level objectives in natural locomotion for legged robots. These high-level objectives are specified as a variable number of partial or complete pose targets that are spaced arbitrarily in time. Our proposed framework utilizes a multi-critic reinforcement learning algorithm to effectively handle the mixture of dense and sparse rewards. Additionally, it employs a transformer-based encoder to accommodate a variable number of input targets, each associated with specific time-to-arrivals. Throughout simulation and hardware experiments, we demonstrate that our framework can effectively satisfy the target keyframe sequence at the required times. In the experiments, the multi-critic method significantly reduces the effort of hyperparameter tuning compared to the standard single-critic alternative. Moreover, the proposed transformer-based architecture enables robots to anticipate future goals, which results in quantitative improvements in their ability to reach their targets.