Using Human-Guided Causal Knowledge for More Generalized Robot Task Planning

TL;DR

This paper explores using human-guided causal knowledge via a language interface to improve robot task planning generalization across environments, showing promising initial results.

Contribution

It introduces a novel language interface enabling humans to communicate causal models to robots, enhancing their ability to generalize in task planning.

Findings

Participants successfully used the interface to generate causal models.

Preliminary models achieved near-generalization in tasks.

The approach shows potential for improving robot adaptability.

Abstract

A major challenge in research involving artificial intelligence (AI) is the development of algorithms that can find solutions to problems that can generalize to different environments and tasks. Unlike AI, humans are adept at finding solutions that can transfer. We hypothesize this is because their solutions are informed by causal models. We propose to use human-guided causal knowledge to help robots find solutions that can generalize to a new environment. We develop and test the feasibility of a language interface that na\"ive participants can use to communicate these causal models to a planner. We find preliminary evidence that participants are able to use our interface and generate causal models that achieve near-generalization. We outline an experiment aimed at testing far-generalization using our interface and describe our longer terms goals for these causal models.