Robust Collision Detection for Robots with Variable Stiffness Actuation by Using MAD-CNN: Modularized-Attention-Dilated Convolutional Neural Network

TL;DR

This paper introduces MAD-CNN, a novel neural network architecture designed for rapid and robust collision detection in collaborative robots with variable stiffness actuators, even with limited training data.

Contribution

The paper presents MAD-CNN, a new attention-based neural network that enhances data efficiency and robustness for collision detection in variable stiffness robots, outperforming existing models.

Findings

MAD-CNN detects all collisions with minimal delay across stiffness levels.

It outperforms existing models in collision sensitivity and robustness.

Effective with only four minutes of training data.

Abstract

Ensuring safety is paramount in the field of collaborative robotics to mitigate the risks of human injury and environmental damage. Apart from collision avoidance, it is crucial for robots to rapidly detect and respond to unexpected collisions. While several learning-based collision detection methods have been introduced as alternatives to purely model-based detection techniques, there is currently a lack of such methods designed for collaborative robots equipped with variable stiffness actuators. Moreover, there is potential for further enhancing the network's robustness and improving the efficiency of data training. In this paper, we propose a new network, the Modularized Attention-Dilated Convolutional Neural Network (MAD-CNN), for collision detection in robots equipped with variable stiffness actuators. Our model incorporates a dual inductive bias mechanism and an attention module to enhance data efficiency and improve robustness. In particular, MAD-CNN is trained using only a four-minute collision dataset focusing on the highest level of joint stiffness. Despite limited training data, MAD-CNN robustly detects all collisions with minimal detection delay across various stiffness conditions. Moreover, it exhibits a higher level of collision sensitivity, which is beneficial for effectively handling false positives, which is a common issue in learning-based methods. Experimental results demonstrate that the proposed MAD-CNN model outperforms existing state-of-the-art models in terms of collision sensitivity and robustness.