On Model Adaptation for Sensorimotor Control of Robots

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.

Vision-based manipulation of deformable and rigid objects using subspace projections of 2D contours

“…In (Navarro-Alarcon et al, 2014) and (Navarro-Alarcon and Liu, 2018), the vision-based deformable objects manipulation is termed as shape servoing. An expository paper on the topic is available in (Navarro-Alarcon et al, 2019). A recent work on vision-based shape servoing of plastic material was presented in (Cherubini et al, 2020).…”

A Lyapunov-Stable Adaptive Method to Approximate Sensorimotor Models for Sensor-Based Control

“…Classical methods in robotics to compute this model (see Sigaud et al, 2011 for a review) can be roughly classified into structure-based and structure-free approaches (Navarro-Alarcon et al, 2019). The former category represents "calibrationlike" techniques [e.g., off-line (Wei et al, 1986) or adaptive (Wang et al, 2008;Liu et al, 2013;Navarro-Alarcon et al, 2015)] that aim to identify the unknown model parameters.…”

“…Their accurate operation is largely due to the fact that industrial robots rely on fixed settings that enable the exact characterization of the tasks' sensorimotor model. Although this full characterization requirement is fairly acceptable in industrial environments, it is too stringent for many service applications where the mechanical, perceptual and environment conditions are not exactly known or might suddenly change (Navarro-Alarcon et al, 2019 ), e.g., in domestic robotics (where environments are highly dynamic), field robotics (where variable morphologies are needed to navigate complex workspaces), autonomous systems (where robots must adapt and operate after malfunctions), to name a few cases.…”

“…For the latter (structure-free) category, we can further distinguish between two main types (Navarro-Alarcon et al, 2019 ): instantaneous and distributed estimation. The first type performs online numerical approximations of the unknown model (whose structure does not need to be known); Some common implementations include e.g., Broyden-like methods (Hosoda and Asada, 1994 ; Jagersand et al, 1997 ; Alambeigi et al, 2018 ) and iterative gradient descent rules (Navarro-Alarcon et al, 2015 ; Yip et al, 2017 ).…”

Vision-based Manipulation of Deformable and Rigid Objects Using Subspace Projections of 2D Contours

“…In [6] and [7], the vision-based deformable objects manipulation is termed as shape servoing. An expository paper on the topic is available in [8]. A recent work on shape servoing of plastic material was presented in [9].…”