Hearing Touch:
Audio-Visual Pretraining for Contact-Rich Manipulation
Jared Mejia¹, Victoria Dean², Tess Hellebrekers³, Abhinav Gupta¹
¹Carnegie Mellon University ²Olin College of Engineering ³Meta AI
Embedded Files
Finalist for the Best Paper Award in Robot Manipulation at ICRA 2024
Paper Code coming soon!
hearing-touch-video-website.m4vAbstract: Although pre-training on a large amount of data is beneficial for robot learning, current paradigms only perform large-scale pretraining for visual representations, whereas representations for other modalities are trained from scratch. In contrast to the abundance of visual data, it is unclear what relevant internet-scale data may be used for pretraining other modalities such as tactile sensing. Such pretraining becomes increasingly crucial in the low-data regimes common in robotics applications. In this paper, we address this gap by using contact microphones as an alternative tactile sensor. Our key insight is that contact microphones capture inherently audio-based information, allowing us to leverage large-scale audio-visual pretraining to obtain representations that boost the performance of robotic manipulation. To the best of our knowledge, our method is the first approach leveraging large-scale multisensory pre-training for robotic manipulation.
Page updated
Google Sites
Report abuse