Physically Consistent Preferential Bayesian Optimization for Food Arrangement

TL;DR

This paper introduces PCPBO, a novel Bayesian optimization method that generates preferred food arrangements satisfying physical feasibility and domain-specific rules, validated through simulations and human studies.

Contribution

It proposes a bi-level optimization approach combining physical simulation and preference-based Bayesian optimization for feasible food arrangement estimation.

Findings

Successfully generates physically feasible food arrangements

Outperforms baseline methods in preference accuracy

Effective with both simulated and real user data

Abstract

This paper considers the problem of estimating a preferred food arrangement for users from interactive pairwise comparisons using Computer Graphics (CG)-based dish images. As a foodservice industry requirement, we need to utilize domain rules for the geometry of the arrangement (e.g., the food layout of some Japanese dishes is reminiscent of mountains). However, those rules are qualitative and ambiguous; the estimated result might be physically inconsistent (e.g., each food physically interferes, and the arrangement becomes infeasible). To cope with this problem, we propose Physically Consistent Preferential Bayesian Optimization (PCPBO) as a method that obtains physically feasible and preferred arrangements that satisfy domain rules. PCPBO employs a bi-level optimization that combines a physical simulation-based optimization and a Preference-based Bayesian Optimization (PbBO). Our experimental results demonstrated the effectiveness of PCPBO on simulated and actual human users.