Inference of Human-derived Specifications of Object Placement via Demonstration

TL;DR

This paper introduces PARCC, a formal logic framework based on RCC, for inferring human-like object placement specifications from demonstrations, enhancing robotic understanding of spatial arrangements.

Contribution

The paper presents PARCC, a novel logic-based framework, and an inference algorithm to learn object placement rules from human demonstrations, improving robot-human spatial understanding.

Findings

PARCC effectively captures human object placement specifications.

Learning from demonstrations outperforms manual specifications.

Human study validates the framework's ability to infer human intentions.

Abstract

As robots' manipulation capabilities improve for pick-and-place tasks (e.g., object packing, sorting, and kitting), methods focused on understanding human-acceptable object configurations remain limited expressively with regard to capturing spatial relationships important to humans. To advance robotic understanding of human rules for object arrangement, we introduce positionally-augmented RCC (PARCC), a formal logic framework based on region connection calculus (RCC) for describing the relative position of objects in space. Additionally, we introduce an inference algorithm for learning PARCC specifications via demonstrations. Finally, we present the results from a human study, which demonstrate our framework's ability to capture a human's intended specification and the benefits of learning from demonstration approaches over human-provided specifications.