Inference of Human-derived Specifications of Object Placement via Demonstration

2025-08-26

AI Summary

This work addresses the challenge of enabling robots to interpret implicit human object placement conventions. We propose Position-Augmented Region Connection Calculus (PARCC), a formal logical framework that explicitly models spatial relations humans prioritize—e.g., “teacup placed inside tray and adjacent to coffee pot.” Methodologically, we extend classical RCC logic to PARCC and design a demonstration-driven rule induction algorithm that automatically infers structured spatial constraints from few human placement demonstrations. Experiments show that our approach significantly improves accuracy in reproducing human-preferred layouts compared to handcrafted rules; user studies confirm that generated placement strategies better align with human intuition and habitual practice. Key contributions are: (1) the first formal spatial logic specifically designed for modeling human intent in object arrangement; and (2) an end-to-end learning paradigm that transforms demonstrations into interpretable, logically grounded, and inference-capable placement rules.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

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.

Problem

• Infer human-acceptable object placement specifications via demonstration
• Develop formal logic framework for spatial relationship description
• Learn object arrangement rules through human demonstration algorithm

Innovation

• PARCC framework for spatial relationships
• Inference algorithm learns from demonstrations
• Formal logic based on region connection calculus