Learning Vision-based Reactive Policies for Obstacle Avoidance
Authors
Elie Aljalbout (Technical University of Munich)*; Ji Chen (Technical University of Munich); Konstantin Ritt (Technical University of Munich); Maximilian Ulmer (Technical University of Munich); Sami Haddadin (Technical University of Munich)
Interactive Session
2020-11-17, 11:10 - 11:40 PST | PheedLoop Session
Abstract
In this paper, we address the problem of vision-based obstacle avoidance for robotic manipulators. This topic poses challenges for both perception and motion generation. While most work in the field aims at improving one of those aspects, we provide a unified framework for approaching this problem. The main goal of this framework is to connect perception and motion by identifying the relationship between the visual input and the corresponding motion representation. To this end, we propose a method for learning reactive obstacle avoidance policies. We evaluate our method on goal-reaching tasks for single and multiple obstacles scenarios. We show the ability of the proposed method to efficiently learn stable obstacle avoidance strategies at a high success rate while maintaining closed-loop responsiveness required for critical applications like human-robot interaction.