Plan explicability and predictability for robot task planning

By Yu Zhang, Sarath Sreedharan, Anagha Kulkarni, Tathagata Chakraborti, Hankui Zhuo, Subbarao Kambhampati. 2015

184 citations recorded by the source corpus.

Intelligent robots and machines are becoming pervasive in human populated environments. A desirable capability of these agents is to respond to goal-oriented commands by autonomously constructing task plans. However, such autonomy can add significant cognitive load and potentially introduce safety risks to humans when agents behave in unexpected ways. Hence, for such agents to be helpful, one important requirement is for them to synthesize plans that can be easily understood by humans. While there exists previous work that studied socially acceptable robots that interact with humans in “natural ways”, and work that investigated legible motion planning, there is no general solution for high level task planning. To address this issue, we introduce the notions of plan explicability and predictability. To compute these measures, first, we postulate that humans understand agent plans by associating abstract tasks with agent actions, which can be considered as a labeling process. We learn the labeling scheme of humans for agent plans from training examples using conditional random fields (CRFs). Then, we use the learned model to label a new plan to compute its explicability and predictability. These measures can be used by agents to proactively choose or directly synthesize plans that are more explicable and predictable to humans. We provide evaluations on a synthetic domain and with a physical robot to demonstrate the effectiveness of our approach.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Control and Systems Engineering, AI Ethics, Fairness & Society, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In AI Ethics, Fairness & Society

In Robotics & Control

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “Informativeness [5, 44, 21, 25, 26, 45, 30, 32, 34, 35, 37, 38, 41, 46, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 63, 64, 65, 66, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 86, 87, 88, 89, 59, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 1”
Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “…or as preliminary or synthesized discussion (Byrne, 1991; Felton, 2017; Kass and Leake, 1987; Kulesza et al., 2015; Rosenthal et al., 2016; Sørmo, Cassens, and Aamodt, 2005; Swartout and Moore, 1983; Van Der Linden, 2002; Wallis and Shortliffe, 1981; Wick and Thompson, 1992; Zhang et al., 2016).”
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, background): “Other introductory works include [171] and [172], in addition of a dozen papers that was discussed very recently in a dedicated session of the ICAPS Workshop [11].”
Explainable Planning (2017, background): “Plan Explicability [Zhang et al., 2017] focuses on human’s interpretation of plans.”
Explanations in Autonomous Driving: A Survey (2021, background): “[136], and plan explanation for model reconciliation [90], [137].”
RADAR - A Proactive Decision Support System for Human-in-the-Loop Planning (2017, background): “Further, the system should be, if possible, act in a fashion that is easily understandable to the human in the loop (Zhang et al. 2017), or be able to explain the rationale behind its suggestions if required (Kambhampati 1990; Sohrabi, Baier, and McIlraith 2011) in a fashion easily understood by the”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “Explicability The degree of association between the expected behaviour of a robot to achieve assigned tasks or goals and its actual observed actions [74] Explicitness The capacity of a method for explainability to provide immediate and understandable explanations [75]”