Explainable robotic systems: understanding goal-driven actions in a reinforcement learning scenario

• Published in: Neural computing & applications Vol. 35; no. 25; pp. 18113 - 18130
• Main Authors: Cruz, Francisco, Dazeley, Richard, Vamplew, Peter, Moreira, Ithan
• Format: Journal Article
• Language: English
• Published: London Springer London 01.09.2023; Springer Nature B.V
• Subjects: Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Decision making; Deep learning; Image Processing and Computer Vision; Navigation; Probability and Statistics in Computer Science; Robotics; Robots; S.I. : LatinX in AI Research; Special Issue on LatinX in AI Research; Success; Visual tasks; Explainable robotic systems; Goal-driven explanations; Explainable reinforcement learning
• DOI: 10.1007/s00521-021-06425-5
• ISSN: 0941-0643

Robotic systems are more present in our society everyday. In human–robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To increase action understanding, users demand more explainability about the decisions by the robot in particular situations. Recently, explainable robotic systems have emerged as an alternative focused not only on completing a task satisfactorily, but also on justifying, in a human-like manner, the reasons that lead to making a decision. In reinforcement learning scenarios, a great effort has been focused on providing explanations using data-driven approaches, particularly from the visual input modality in deep learning-based systems. In this work, we focus rather on the decision-making process of reinforcement learning agents performing a task in a robotic scenario. Experimental results are obtained using 3 different set-ups, namely, a deterministic navigation task, a stochastic navigation task, and a continuous visual-based sorting object task. As a way to explain the goal-driven robot’s actions, we use the probability of success computed by three different proposed approaches: memory-based, learning-based, and introspection-based. The difference between these approaches is the amount of memory required to compute or estimate the probability of success as well as the kind of reinforcement learning representation where they could be used. In this regard, we use the memory-based approach as a baseline since it is obtained directly from the agent’s observations. When comparing the learning-based and the introspection-based approaches to this baseline, both are found to be suitable alternatives to compute the probability of success, obtaining high levels of similarity when compared using both the Pearson’s correlation and the mean squared error.