Sado, Fatai and Loo, Chu Kiong and Liew, Wei Shiung and Kerzel, Matthias and Wermter, Stefan (2023) Explainable goal-driven agents and robots - a comprehensive review. ACM Computing Surveys, 55 (10). ISSN 0360-0300, DOI https://doi.org/10.1145/3564240.
Full text not available from this repository.Abstract
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.
| Item Type: | Article |
|---|---|
| Funders: | Impact Oriented Interdisciplinary Research Grant (IIRG) from University of Malaya IIRG002C-19HWB, German Research Foundation (DFG) TRR 169, BMWK under project VeriKAS, Georg Forster Research Fellowship for Experienced Researchers from Alexander von Humboldt-Stiftung/Foundation |
| Uncontrolled Keywords: | Accountability; Continual learning; Deep neural network; Explainability; Explainable AI; Goal-driven agents; Transparency |
| Subjects: | Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Faculty of Computer Science & Information Technology > Department of Artificial Intelligence |
| Depositing User: | Ms Zaharah Ramly |
| Date Deposited: | 07 May 2024 04:04 |
| Last Modified: | 07 May 2024 04:04 |
| URI: | http://eprints.um.edu.my/id/eprint/38241 |
Actions (login required)
 |
View Item |
