AirExo: Low-Cost Exoskeletons for Learning Whole-Arm Manipulation in the Wild

TL;DR

This paper introduces AirExo, a low-cost dual-arm exoskeleton that enables scalable in-the-wild demonstrations, significantly reducing data collection time for robot learning of complex manipulations, and improving robustness and generalization.

Contribution

We develop AirExo, a portable exoskeleton for efficient data collection, and demonstrate its effectiveness in enabling robots to learn robust manipulation policies from minimal teleoperated data.

Findings

Robots trained with AirExo data outperform those with longer teleoperation data.

The approach improves task success rates under disturbances.

Only 3 minutes of teleoperation data suffices when combined with in-the-wild demonstrations.

Abstract

While humans can use parts of their arms other than the hands for manipulations like gathering and supporting, whether robots can effectively learn and perform the same type of operations remains relatively unexplored. As these manipulations require joint-level control to regulate the complete poses of the robots, we develop AirExo, a low-cost, adaptable, and portable dual-arm exoskeleton, for teleoperation and demonstration collection. As collecting teleoperated data is expensive and time-consuming, we further leverage AirExo to collect cheap in-the-wild demonstrations at scale. Under our in-the-wild learning framework, we show that with only 3 minutes of the teleoperated demonstrations, augmented by diverse and extensive in-the-wild data collected by AirExo, robots can learn a policy that is comparable to or even better than one learned from teleoperated demonstrations lasting over 20 minutes. Experiments demonstrate that our approach enables the model to learn a more general and robust policy across the various stages of the task, enhancing the success rates in task completion even with the presence of disturbances. Project website: https://airexo.github.io/