Special issue: CFP: Variable Impedance Control And Learning In Complex Interaction Scenarios: Challenges And Opportunities

Fares Abu-Dakka (Guest editor), Matteo Saveriano (Guest editor), Meghan E. Huber (Guest editor), Thiago Boaventura Cunha (Guest editor)

Research output: Contribution to journalSpecial issueScientificpeer-review

Abstract

Advancements in robotics research are allowing robots to move from traditional caged environments on factory floors into human environments, which are highly unstructured, dynamic, and uncertain. Such a move requires robots to autonomously interact with their environment and physically cooperate with people, which significantly increases the demand for reliable perception, planning and control. However, there are still several fundamental research problems that must addressed to ensure the success of robots in human-inhabited environment, for example: how to design physical interaction control systems that can work with potentially uncertain environment models and uncertain sensory feedback; how to deal with unpredictable and complex physical interactions with human beings; and how to adapt the robot dynamic behavior in real-time.

This special issue aims at collecting different points of view about learning and impedance control. In principle, the combination of these two tools can afford robots the ability to enhance their manipulation and locomotion skills in unstructured environments, as well as their capacity to handle perturbations and uncertainty during physical interaction. Enabling robots to acquire knowledge autonomously and use it to interact with the world around them more intelligently will lead to future developments in this area, enforcing safety and reliability while building upon the principles of AI.
Original languageEnglish
JournalIEEE Robotics and Automation Letters
Volume7
Issue number4
Publication statusPublished - 17 Oct 2022
MoE publication typeC2 Edited books

Fingerprint

Dive into the research topics of 'Special issue: CFP: Variable Impedance Control And Learning In Complex Interaction Scenarios: Challenges And Opportunities'. Together they form a unique fingerprint.

Cite this