# On Model Adaptation for Sensorimotor Control of Robots

## TL;DR

This paper develops adaptive sensorimotor models for robotic control under uncertainty, enabling robots to handle uncalibrated sensors and unknown object properties through novel computational methods.

## Contribution

It introduces new methods for building adaptive sensorimotor models, addressing uncalibrated sensors and uncertain object properties in robotic control.

## Key findings

- Effective shape control of deformable objects demonstrated.
- Successful soft manipulation of ultrasonic probes with uncalibrated sensors.
- Analysis of computational methods for adaptive sensorimotor modeling.

## Abstract

In this article, we address the problem of computing adaptive sensorimotor models that can be used for guiding the motion of robotic systems with uncertain action-to-perception relations. The formulation of the uncalibrated sensor-based control problem is first presented, then, various computational methods for building adaptive sensorimotor models are derived and analysed. The proposed methodology is exemplified with two cases of study: (i) shape control of deformable objects with unknown properties, and (ii) soft manipulation of ultrasonic probes with uncalibrated sensors.