Contact Localization for Robot Arms in Motion without Torque Sensing

TL;DR

This paper presents a neural network-based method for localizing contacts on moving robot arms without torque sensors, using domain randomization and a novel surface encoding, achieving high accuracy and practical obstacle mapping.

Contribution

It introduces a contact localization approach that works in motion without torque sensing, employing domain randomization and a cylindrical surface encoding for convolutional processing.

Findings

Contact detection accuracy of 91.5%

Mean contact localization error of 3.0cm

Effective obstacle mapping in simulation and real-world

Abstract

Detecting and localizing contacts is essential for robot manipulators to perform contact-rich tasks in unstructured environments. While robot skins can localize contacts on the surface of robot arms, these sensors are not yet robust or easily accessible. As such, prior works have explored using proprioceptive observations, such as joint velocities and torques, to perform contact localization. Many past approaches assume the robot is static during contact incident, a single contact is made at a time, or having access to accurate dynamics models and joint torque sensing. In this work, we relax these assumptions and propose using Domain Randomization to train a neural network to localize contacts of robot arms in motion without joint torque observations. Our method uses a novel cylindrical projection encoding of the robot arm surface, which allows the network to use convolution layers to process input features and transposed convolution layers to predict contacts. The trained network achieves a contact detection accuracy of 91.5% and a mean contact localization error of 3.0cm. We further demonstrate an application of the contact localization model in an obstacle mapping task, evaluated in both simulation and the real world.