Towards a learnt neural body schema for dexterous

Authors: Ajaz Ahmad Bhat Sharath Chandra Akkaladevi Vishwanathan Mohan Christian Eitzinger Pietro Morasso

Publish Date: 2016/04/04

Volume: 41, Issue: 4, Pages: 945-966

PDF Link

Abstract

During any goal oriented behavior the dual processes of generation of dexterous actions and anticipation of the consequences of potential actions must seamlessly alternate This article presents a unified neural framework for generation and forward simulation of goal directed actions and validates the architecture through diverse experiments on humanoid and industrial robots The basic idea is that actions are consequences of an simulation process that animates the internal model of the body namely the body schema in the context of intended goals/constraints Specific focus is on a Learning how the internal model of the body can be acquired by any robotic embodiment and extended to coordinated tools b Configurability how diverse forward/inverse models of action can be ‘composed’ at runtime by coupling/decoupling different body body + tool chains with task relevant goals and constraints represented as multireferential force fields and c Computational simplicity how both the synthesis of motor commands to coordinate highly redundant systems and the ensuing forward simulations are realized through wellposed computations without kinematic inversions The performance of the neural architecture is demonstrated through a range of motor tasks on a 53DoFs robot iCub and two industrial robots performing real world assembly with emphasis on dexterity accuracy speed obstacle avoidance multiple taskspecific constraints taskbased configurability Putting into context other ideas in motor control like the Equilibrium Point Hypothesis Optimal Control Active Inference and emerging studies from neuroscience the relevance of the proposed framework is also discussedTo perform any reaching movement several joints—shoulder elbow wrist fingers move cooperatively forming a synergy in a flexible and dynamic fashion While groups of fingers may operate synergistically while playing a guitar chord individual fingers are controlled while playing a lead One of the basic problems of motor control is to understand how neural control structures quickly and flexibly organize and engage different parts of the body schema to cooperate synergistically in a movement sequence The above TBG can be used to dynamically couple and decouple synergies in different ways based on task specification In sum by selecting two parameters of the TBG t f and beta a family of timevarying signals can be generated From the point of view of realtime implementation it is possible to use any scalar function of time satisfying the properties of described above or a lookup table etc

Keywords: