# Plan Explicability and Predictability for Robot Task Planning

arXiv: https://arxiv.org/abs/1511.08158 · HTML: https://mlsanity.com/paper/1511.08158/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2015.

## Built on by (most cited first, 26 of 26)

- [Explanations in Autonomous Driving: A Survey](https://mlsanity.com/paper/2103.05154/) (2021)
- [Driving Everywhere with Large Language Model Policy Adaptation](https://mlsanity.com/paper/2402.05932/) (2024)
- [Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recovery](https://mlsanity.com/paper/2101.01625/) (2021)
- [Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?](https://mlsanity.com/paper/2401.05302/) (2024)
- [Contrastive Explanations of Plans Through Model Restrictions](https://mlsanity.com/paper/2103.15575/) (2021)
- [GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment](https://mlsanity.com/paper/2403.11075/) (2024)
- [Human-AI Symbiosis: A Survey of Current Approaches](https://mlsanity.com/paper/2103.09990/) (2021)
- [Logic programming for deliberative robotic task planning](https://mlsanity.com/paper/2301.07550/) (2023)
- [Motion Reasoning for Goal-Based Imitation Learning](https://mlsanity.com/paper/1911.05864/) (2019)
- [Subgoal-Based Explanations for Unreliable Intelligent Decision Support Systems](https://mlsanity.com/paper/2201.04204/) (2022)
- [A Unifying Bayesian Formulation of Measures of Interpretability in Human-AI](https://mlsanity.com/paper/2104.10743/) (2021)
- [A Mental-Model Centric Landscape of Human-AI Symbiosis](https://mlsanity.com/paper/2202.09447/) (2022)
- [Trust-Aware Planning: Modeling Trust Evolution in Iterated Human-Robot Interaction](https://mlsanity.com/paper/2105.01220/) (2021)
- [Policy Regularization for Legible Behavior](https://mlsanity.com/paper/2203.04303/) (2022)
- [Real-time goal recognition using approximations in Euclidean space](https://mlsanity.com/paper/2307.07876/) (2023)
- [Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness](https://mlsanity.com/paper/2403.14641/) (2024)
- [Generating Active Explicable Plans in Human-Robot Teaming](https://mlsanity.com/paper/2109.08834/) (2021)
- [People Attribute Purpose to Autonomous Vehicles When Explaining Their Behavior: Insights from Cognitive Science for Explainable AI](https://mlsanity.com/paper/2403.08828/) (2024)
- [Goal Alignment: A Human-Aware Account of Value Alignment Problem](https://mlsanity.com/paper/2302.00813/) (2023)
- [Safe Explicable Planning](https://mlsanity.com/paper/2304.03773/) (2023)
- [Adaptation and Communication in Human-Robot Teaming to Handle Discrepancies in Agents' Beliefs about Plans](https://mlsanity.com/paper/2307.03362/) (2023)
- [Reducing Human-Robot Goal State Divergence with Environment Design](https://mlsanity.com/paper/2404.15184/) (2024)
- [Safe Explicable Policy Search](https://mlsanity.com/paper/2503.07848/) (2025)
- [Informative Communication of Robot Plans](https://mlsanity.com/paper/2511.13226/) (2025)
- [Safe Task Planning with Long-Term Graph Memory for Embodied Agents](https://mlsanity.com/paper/2609.08444/) (2026)
- [Probabilistic Plan Legibility with Off-the-shelf Planners](https://mlsanity.com/paper/2610.00065/) (2026)

## Abstract (arXiv)

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 unexpectedly. 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 lacks a general solution for high level task planning. To address this issue, we introduce the notions of plan it explicability and it 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 human subjects using physical robots to show the effectiveness of our approach