Supervision via Competition: Robot Adversaries for Learning Tasks

TL;DR

This paper introduces an adversarial learning framework where robot adversaries challenge the robot, leading to more robust task learning and improved grasping performance on novel objects.

Contribution

The work presents a novel adversarial framework for robot learning that enhances robustness and performance compared to traditional self-supervised methods.

Findings

Robots with adversaries grasp 82% of novel objects versus 68% without adversaries.

Adversarial training improves the robustness of the robot's grasping model.

Adversarial setting outperforms collaborative multi-robot strategies in learning efficiency.

Abstract

There has been a recent paradigm shift in robotics to data-driven learning for planning and control. Due to large number of experiences required for training, most of these approaches use a self-supervised paradigm: using sensors to measure success/failure. However, in most cases, these sensors provide weak supervision at best. In this work, we propose an adversarial learning framework that pits an adversary against the robot learning the task. In an effort to defeat the adversary, the original robot learns to perform the task with more robustness leading to overall improved performance. We show that this adversarial framework forces the the robot to learn a better grasping model in order to overcome the adversary. By grasping 82% of presented novel objects compared to 68% without an adversary, we demonstrate the utility of creating adversaries. We also demonstrate via experiments that having robots in adversarial setting might be a better learning strategy as compared to having collaborative multiple robots.