Continuum Robot State Estimation Using Gaussian Process Regression on $SE(3)$

TL;DR

This paper presents a Gaussian process regression method for continuous shape and strain estimation of continuum robots modeled with Cosserat rods, achieving high accuracy in simulations and experiments.

Contribution

It adapts GP regression for shape estimation along arclength, incorporating pose and strain measurements with uncertainty quantification.

Findings

Achieved average end-effector errors as low as 3.5mm and 0.016° in simulation.

Estimated shape with errors around 3.3mm and 0.035° in unloaded experiments.

Maintained errors around 6.2mm and 0.041° under load during experiments.

Abstract

Continuum robots have the potential to enable new applications in medicine, inspection, and countless other areas due to their unique shape, compliance, and size. Excellent progess has been made in the mechanical design and dynamic modelling of continuum robots, to the point that there are some canonical designs, although new concepts continue to be explored. In this paper, we turn to the problem of state estimation for continuum robots that can been modelled with the common Cosserat rod model. Sensing for continuum robots might comprise external camera observations, embedded tracking coils or strain gauges. We repurpose a Gaussian process (GP) regression approach to state estimation, initially developed for continuous-time trajectory estimation in $SE(3)$. In our case, the continuous variable is not time but arclength and we show how to estimate the continuous shape (and strain) of the robot (along with associated uncertainties) given discrete, noisy measurements of both pose and strain along the length. We demonstrate our approach quantitatively through simulations as well as through experiments. Our evaluations show that accurate and continuous estimates of a continuum robot's shape can be achieved, resulting in average end-effector errors between the estimated and ground truth shape as low as 3.5mm and 0.016$^\circ$ in simulation or 3.3mm and 0.035$^\circ$ for unloaded configurations and 6.2mm and 0.041$^\circ$ for loaded ones during experiments, when using discrete pose measurements.