Vision-Based Online Key Point Estimation of Deformable Robots

TL;DR

This paper introduces a neural network-based method for real-time, marker-less 3D key point estimation of deformable robots using dual camera images, improving accuracy and robustness over existing techniques.

Contribution

It presents a novel supervised learning approach for online shape estimation of soft robots without markers, enhancing accuracy and robustness.

Findings

Outperforms state-of-the-art marker-less methods by up to 4.5% in accuracy

Operates online at 25 Hz with dual camera inputs

Demonstrates effectiveness on various deformable robotic systems

Abstract

The precise control of soft and continuum robots requires knowledge of their shape, which has, in contrast to classical rigid robots, infinite degrees of freedom. To partially reconstruct the shape, proprioceptive techniques use built-in sensors resulting in inaccurate results and increased fabrication complexity. Exteroceptive methods so far rely on expensive tracking systems with reflective markers placed on all components, which are infeasible for deformable robots interacting with the environment due to marker occlusion and damage. Here, a regression approach is presented for 3D key point estimation using a convolutional neural network. The proposed approach takes advantage of data-driven supervised learning and is capable of online marker-less estimation during inference. Two images of a robotic system are taken simultaneously at 25 Hz from two different perspectives, and are fed to the network, which returns for each pair the parameterized key point or PCC shape representations. The proposed approach outperforms marker-less state-of-the-art methods by a maximum of 4.5% in estimation accuracy while at the same time being more robust and requiring no prior knowledge of the shape. Online evaluations on two types of soft robotic arms and a soft robotic fish demonstrate our method's accuracy and versatility on highly deformable systems.