Towards Open-World Mobile Manipulation in Homes: Lessons from the Neurips 2023 HomeRobot Open Vocabulary Mobile Manipulation Challenge

TL;DR

This paper presents the NeurIPS 2023 HomeRobot Challenge focused on open vocabulary mobile manipulation in home environments, highlighting the progress, challenges, and lessons learned in developing versatile robotic assistants.

Contribution

It introduces a new benchmark task for open vocabulary manipulation, reports on a competitive challenge, and analyzes methods that improve perception and decision-making in robots.

Findings

Best solutions improved success rate from 0.8% to 10.8%.

Error detection and perception-decision integration are key factors.

Robust generalization remains a major challenge.

Abstract

In order to develop robots that can effectively serve as versatile and capable home assistants, it is crucial for them to reliably perceive and interact with a wide variety of objects across diverse environments. To this end, we proposed Open Vocabulary Mobile Manipulation as a key benchmark task for robotics: finding any object in a novel environment and placing it on any receptacle surface within that environment. We organized a NeurIPS 2023 competition featuring both simulation and real-world components to evaluate solutions to this task. Our baselines on the most challenging version of this task, using real perception in simulation, achieved only an 0.8% success rate; by the end of the competition, the best participants achieved an 10.8\% success rate, a 13x improvement. We observed that the most successful teams employed a variety of methods, yet two common threads emerged among the best solutions: enhancing error detection and recovery, and improving the integration of perception with decision-making processes. In this paper, we detail the results and methodologies used, both in simulation and real-world settings. We discuss the lessons learned and their implications for future research. Additionally, we compare performance in real and simulated environments, emphasizing the necessity for robust generalization to novel settings.