Probabilistic Plan Legibility with Off-the-shelf Planners

Summary

Legible planning is the creation of plans that best disambiguate their goals from a set of other candidates from an observer's perspective.

Abstract Summary

Legible planning is the creation of plans that best disambiguate their goals from a set of other candidates from an observer's perspective. In this paper we propose a method for legible planning for arbitrary PDDL domains, by extending previous research on legibility to classical planning without requiring to construct ad-hoc planners. We also discuss how the observer perspective may be estimated through a second order theory of mind that connects the planner's and the observer's task spaces. Our solution can for example be deployed in human-robot teaming scenarios, where an autonomous robot in a team can implicitly communicate its goal by producing legible plans. We present benchmark results on several PDDL planning domains. Our results generally show that plan legibility is a trade-off with plan efficiency, however, not all planning domains allows to increase legibility in the same way and a regularizing factor to balance legibility and efficiency was proved necessary.

Key Points

Legible planning is the creation of plans that best disambiguate their goals from a set of other candidates from an observer's perspective.
In this paper we propose a method for legible planning for arbitrary PDDL domains, by extending previous research on legibility to classical planning without requiring to construct ad-hoc planners.
We also discuss how the observer perspective may be estimated through a second order theory of mind that connects the planner's and the observer's task spaces.
Our solution can for example be deployed in human-robot teaming scenarios, where an autonomous robot in a team can implicitly communicate its goal by producing legible plans.
We present benchmark results on several PDDL planning domains

llustrative Example

To illustrate the production of legible plans we propose the following example in the Human-Robot teaming scenario shown in Figure 2 . It is a rescue scenario where an autonomous scout robot is moving in a dangerous environment (e.g. a laboratory filled with toxic gases) searching for people, while a commander supervisions the operations on its computer interface from outside of the building.

Both have access to a map of the environment in the form of a grid-world on which the robot’s position is being tracked.

llustrative Example — Probabilistic Plan Legibility with Off-the-shelf Planners — Figure 2: Legible planning in the rescue scenario. Left side: world grid that the commander believes the robot is planning for. This plan instance is estimated internally by the robot through a theory of mind, and doesn’t have any obstacles. Right side: real world grid computed by the robot, which has the real goal and contains detected obstacles.

Sources and Demonstrations

Figures are reproduced from Persiani et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.