Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Explaining Why Things Go Where They Go: Interpretable Constructs of Human Organizational Preferences

Emmanuel Fashae, Michael Burke, Leimin Tian, Lingheng Meng, Pamela Carreno-Medrano

TL;DR

The paper tackles the lack of interpretability in human-guided domestic object rearrangement. It introduces four explicit constructs—Spatial practicality, Habitual convenience, Semantic coherence, and Commonsense appropriateness—and validates them via a 63-participant online study across kitchen and living-room contexts. The constructs are formalized as four normalized scores and integrated into a Monte Carlo Tree Search planner to generate arrangements that align with user preferences. Empirical results show psychometric validity, construct-level predictive power for satisfaction, and that participant-weighted planning can reproduce human-like organization, enabling transparent, personalized robotic assistance. This work provides a compact, interpretable foundation for robot planning in household environments.

Abstract

Robotic systems for household object rearrangement often rely on latent preference models inferred from human demonstrations. While effective at prediction, these models offer limited insight into the interpretable factors that guide human decisions. We introduce an explicit formulation of object arrangement preferences along four interpretable constructs: spatial practicality (putting items where they naturally fit best in the space), habitual convenience (making frequently used items easy to reach), semantic coherence (placing items together if they are used for the same task or are contextually related), and commonsense appropriateness (putting things where people would usually expect to find them). To capture these constructs, we designed and validated a self-report questionnaire through a 63-participant online study. Results confirm the psychological distinctiveness of these constructs and their explanatory power across two scenarios (kitchen and living room). We demonstrate the utility of these constructs by integrating them into a Monte Carlo Tree Search (MCTS) planner and show that when guided by participant-derived preferences, our planner can generate reasonable arrangements that closely align with those generated by participants. This work contributes a compact, interpretable formulation of object arrangement preferences and a demonstration of how it can be operationalized for robot planning.

Explaining Why Things Go Where They Go: Interpretable Constructs of Human Organizational Preferences

TL;DR

The paper tackles the lack of interpretability in human-guided domestic object rearrangement. It introduces four explicit constructs—Spatial practicality, Habitual convenience, Semantic coherence, and Commonsense appropriateness—and validates them via a 63-participant online study across kitchen and living-room contexts. The constructs are formalized as four normalized scores and integrated into a Monte Carlo Tree Search planner to generate arrangements that align with user preferences. Empirical results show psychometric validity, construct-level predictive power for satisfaction, and that participant-weighted planning can reproduce human-like organization, enabling transparent, personalized robotic assistance. This work provides a compact, interpretable foundation for robot planning in household environments.

Abstract

Robotic systems for household object rearrangement often rely on latent preference models inferred from human demonstrations. While effective at prediction, these models offer limited insight into the interpretable factors that guide human decisions. We introduce an explicit formulation of object arrangement preferences along four interpretable constructs: spatial practicality (putting items where they naturally fit best in the space), habitual convenience (making frequently used items easy to reach), semantic coherence (placing items together if they are used for the same task or are contextually related), and commonsense appropriateness (putting things where people would usually expect to find them). To capture these constructs, we designed and validated a self-report questionnaire through a 63-participant online study. Results confirm the psychological distinctiveness of these constructs and their explanatory power across two scenarios (kitchen and living room). We demonstrate the utility of these constructs by integrating them into a Monte Carlo Tree Search (MCTS) planner and show that when guided by participant-derived preferences, our planner can generate reasonable arrangements that closely align with those generated by participants. This work contributes a compact, interpretable formulation of object arrangement preferences and a demonstration of how it can be operationalized for robot planning.
Paper Structure (13 sections, 12 equations, 2 figures, 4 tables)

This paper contains 13 sections, 12 equations, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Theoretical Motivation
  5. User Study
  6. Computational Generation of Human-Aligned Arrangements
  7. Results and Discussion
  8. Psychometric Validation of Questionnaire
  9. Empirical Validation of Proposed Constructs
  10. Shared Dimensions as a Basis for Assessing Arrangements
  11. Behavioral Heterogeneity in Organization
  12. Preference-Aligned Trajectory Generation
  13. Conclusions and Future Work

Figures (2)

  • Figure 1: Survey interface showing an example organization task in the kitchen. Participants arranged objects by dragging them into available receptacle zones. More details about the interface are provided in the appendix.
  • Figure 2: Importance ratings by construct (boxplots with jitter). Brackets indicate post-hoc comparisons and stars denote $p$ levels (*** $<.001$, ** $<.01$, * $<.05$, n.s. $\ge .05$).