Integrating Human-Provided Information Into Belief State Representation Using Dynamic Factorization

TL;DR

This paper introduces a dynamic belief state representation that efficiently integrates human-provided information with sensory data, improving inference and planning in complex, partially observed open domains.

Contribution

It proposes a novel dynamic factorization method for belief states that adapts based on correlations, enhancing inference efficiency in open environments.

Findings

Significant reduction in inference time compared to static factorization.

Effective in both 2D gridworld and 3D cooking tasks.

Improved planning performance in partially observed scenarios.

Abstract

In partially observed environments, it can be useful for a human to provide the robot with declarative information that represents probabilistic relational constraints on properties of objects in the world, augmenting the robot's sensory observations. For instance, a robot tasked with a search-and-rescue mission may be informed by the human that two victims are probably in the same room. An important question arises: how should we represent the robot's internal knowledge so that this information is correctly processed and combined with raw sensory information? In this paper, we provide an efficient belief state representation that dynamically selects an appropriate factoring, combining aspects of the belief when they are correlated through information and separating them when they are not. This strategy works in open domains, in which the set of possible objects is not known in advance, and provides significant improvements in inference time over a static factoring, leading to more efficient planning for complex partially observed tasks. We validate our approach experimentally in two open-domain planning problems: a 2D discrete gridworld task and a 3D continuous cooking task. A supplementary video can be found at http://tinyurl.com/chitnis-iros-18.