Real-time Perception meets Reactive Motion Generation

TL;DR

This paper compares different robotic manipulation architectures emphasizing the importance of continuous real-time perception and reactive motion generation in dynamic, uncertain environments, through extensive real-world experiments.

Contribution

It provides a comprehensive evaluation of three common robotic control architectures with real-time perception, highlighting the benefits of tight perception-action integration in dynamic manipulation.

Findings

Reactive planner outperforms traditional approaches in dynamic scenarios

Real-time feedback improves robustness and accuracy significantly

Extensive experiments validate the importance of perception-action integration

Abstract

We address the challenging problem of robotic grasping and manipulation in the presence of uncertainty. This uncertainty is due to noisy sensing, inaccurate models and hard-to-predict environment dynamics. We quantify the importance of continuous, real-time perception and its tight integration with reactive motion generation methods in dynamic manipulation scenarios. We compare three different systems that are instantiations of the most common architectures in the field: (i) a traditional sense-plan-act approach that is still widely used, (ii) a myopic controller that only reacts to local environment dynamics and (iii) a reactive planner that integrates feedback control and motion optimization. All architectures rely on the same components for real-time perception and reactive motion generation to allow a quantitative evaluation. We extensively evaluate the systems on a real robotic platform in four scenarios that exhibit either a challenging workspace geometry or a dynamic environment. In 333 experiments, we quantify the robustness and accuracy that is due to integrating real-time feedback at different time scales in a reactive motion generation system. We also report on the lessons learned for system building.