Vision-Based Proprioceptive Sensing for Soft Inflatable Actuators

TL;DR

This paper introduces a vision-based sensing method for soft inflatable actuators that predicts their position in real-time, enabling effective closed-loop control with accuracy comparable to traditional sensors.

Contribution

The paper presents a novel vision-based sensing pipeline for soft actuators that operates in real-time and achieves accuracy similar to existing distance sensors.

Findings

Real-time 40 Hz sensing on standard laptops

Comparable accuracy to off-the-shelf distance sensors

Successful closed-loop elongation control

Abstract

This paper presents a vision-based sensing approach for a soft linear actuator, which is equipped with an integrated camera. The proposed vision-based sensing pipeline predicts the three-dimensional position of a point of interest on the actuator. To train and evaluate the algorithm, predictions are compared to ground truth data from an external motion capture system. An off-the-shelf distance sensor is integrated in a similar actuator and its performance is used as a baseline for comparison. The resulting sensing pipeline runs at 40 Hz in real-time on a standard laptop and is additionally used for closed loop elongation control of the actuator. It is shown that the approach can achieve comparable accuracy to the distance sensor.