Interactive and Explainable Robot Learning: A Comprehensive Review
Authors:
- Esmaeil SerajESEsmaeil Seraj
- Kin Man LeeKLKin Man Lee
- Zulfiqar ZaidiZZZulfiqar Zaidi
- Qingyu XiaoQXQingyu Xiao
- Zhaoxin LiZLZhaoxin Li
- Arthur NascimentoANArthur Nascimento
- Sanne van WaverenSWSanne van Waveren
- Pradyumna TambwekarPTPradyumna Tambwekar
- Rohan PalejaRPRohan Paleja
- Devleena DasDDDevleena Das
- Matthew GombolayMGMatthew Gombolay
Open Access
- 5 June 2024
- journal article
- review article
- Published by Emerald Publishing in Foundations and Trends in Robotics
- Vol. 12 (2-3) , 75-349
Abstract
This review embarks on a comprehensive exploration of approaches, evaluation methods, and ethical considerations in explainable and interactive systems for robotic applications, distinctly focusing on intelligent systems that are specifically designed for learning automated agents. Given the increasing integration of robots in daily life, it is crucial to focus on intelligent systems that can not only learn and adapt, but can also offer clarity and comprehension for their actions. The interactive component of these systems is thoroughly examined, evaluating the algorithms, the modalities used in interaction, and the significance of mixed-initiative and shared autonomy. We spotlight adaptive and adaptable methods, emphasizing the centrality of user-inspired research and personalized approaches in interactive robotics. A rigorous examination of safety and ethical considerations of these intelligent systems anchors the discussion, including aspects of transparency, privacy, accountability, biases, and psychological well-being. The review evaluates existing metrics and benchmarking standards for such systems and explores their practical applications across domains such as healthcare, domestic tasks, and industrial automation. Concluding with key insights and directions for future research, we provide design guidelines and points of consensus for each subject in order to equip readers with a nuanced understanding of current trends and tools in explainable and interactive robotic systems, paving the way for informed research and application in this dynamic field.Keywords
This publication has 642 references indexed in Scilit:
- Patching interpretable And‐Or‐Graph knowledge representation using augmented realityApplied AI Letters, 2021
- Governing AI‐Driven Health Research: Are IRBs Up to the Task?Ethics & Human Research, 2021
- Social interaction with visitors: mobile guide robots capable of offering a museum tourIEEJ Transactions on Electrical and Electronic Engineering, 2019
- Robust Intelligence and Trust in Autonomous Systems2016
- A General‐purpose System for Teleoperation of the DRC‐HUBO Humanoid RobotJournal of Field Robotics, 2015
- Psychophysiological Feedback for Adaptive Human–Robot Interaction (HRI)2014
- Language Grounding in Robots2012
- Cognitive Hierarchy: A Limited Thinking Theory in Games2007
- Dynamic Movement Primitives -A Framework for Motor Control in Humans and Humanoid Robotics2006
- Safe planning for human-robot interactionJournal of Robotic Systems, 2005