Explainable Goal-driven Agents and Robots - A Comprehensive Review

Recent applications of autonomous agents and robots have brought attention to crucial trust-related challenges associated with the current generation of artificial intelligence (AI) systems. AI systems based on the connectionist deep learning neural network approach lack capabilities of explaining t...

Full description

Saved in:
Bibliographic Details
Published in:ACM computing surveys 2023-10, Vol.55 (10), p.1-41, Article 211
Main Authors: Sado, Fatai, Loo, Chu Kiong, Liew, Wei Shiung, Kerzel, Matthias, Wermter, Stefan
Format: Article
Language:English
Subjects:
Agents (artificial intelligence)
Artificial intelligence
Communication
Computer science
Computing methodologies
Deep learning
Explainable artificial intelligence
Intelligent agents
Knowledge representation and reasoning
Machine learning
Neural networks
Robots
Safety critical
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent applications of autonomous agents and robots have brought attention to crucial trust-related challenges associated with the current generation of artificial intelligence (AI) systems. AI systems based on the connectionist deep learning neural network approach lack capabilities of explaining their decisions and actions to others, despite their great successes. Without symbolic interpretation capabilities, they are ‘black boxes’, which renders their choices or actions opaque, making it difficult to trust them in safety-critical applications. The recent stance on the explainability of AI systems has witnessed several approaches to eXplainable Artificial Intelligence (XAI); however, most of the studies have focused on data-driven XAI systems applied in computational sciences. Studies addressing the increasingly pervasive goal-driven agents and robots are sparse at this point in time. This paper reviews approaches on explainable goal-driven intelligent agents and robots, focusing on techniques for explaining and communicating agents’ perceptual functions (e.g., senses, vision) and cognitive reasoning (e.g., beliefs, desires, intentions, plans, and goals) with humans in the loop. The review highlights key strategies that emphasize transparency, understandability, and continual learning for explainability. Finally, the paper presents requirements for explainability and suggests a road map for the possible realization of effective goal-driven explainable agents and robots.
ISSN:0360-0300
1557-7341
DOI:10.1145/3564240