Learning Diverse Skills for Local Navigation under Multi-constraint Optimality

TL;DR

This paper introduces a constrained optimization approach to learn diverse local navigation skills for robots, balancing multiple reward-based constraints to generate varied, effective behaviors that transfer well to real robots.

Contribution

It proposes a novel constrained optimization framework for achieving diverse policies under multiple reward constraints in robotic navigation.

Findings

Effective diverse navigation policies learned in simulation

Successful transfer of policies to real quadruped robot Solo12

Policies exhibit diverse, agile obstacle traversal behaviors

Abstract

Despite many successful applications of data-driven control in robotics, extracting meaningful diverse behaviors remains a challenge. Typically, task performance needs to be compromised in order to achieve diversity. In many scenarios, task requirements are specified as a multitude of reward terms, each requiring a different trade-off. In this work, we take a constrained optimization viewpoint on the quality-diversity trade-off and show that we can obtain diverse policies while imposing constraints on their value functions which are defined through distinct rewards. In line with previous work, further control of the diversity level can be achieved through an attract-repel reward term motivated by the Van der Waals force. We demonstrate the effectiveness of our method on a local navigation task where a quadruped robot needs to reach the target within a finite horizon. Finally, our trained policies transfer well to the real 12-DoF quadruped robot, Solo12, and exhibit diverse agile behaviors with successful obstacle traversal.