Title: Robot Learning via Human Adversarial Games
Author: Jiali Duan
Much work in robotics has focused on “humanin-the-loop” learning techniques that improve the efficiency of the learning process. However, these algorithms have made the strong assumption of a cooperating human supervisor that assists the robot. In reality, human observers tend to also act in an adversarial manner towards deployed robotic systems. We show that this can in fact improve the robustness of the learned models by proposing a physical framework that leverages perturbations applied by a human adversary, guiding the robot towards more robust models. In a manipulation task, we show that grasping success improves significantly when the robot trains with a human adversary as compared to training in a self-supervised manner. We validate our approach in a self-brewed simulator for human-robot interaction. Our work has been selected as Best Paper Finalist for IROS 2019 and more details can be found at: https://arxiv.org/abs/1903.00636.
Before training:
After training: