Coloring Between the Lines: Personalization in the Null Space of Planning Constraints

2025-05-21

AI Summary

Addressing the challenge of jointly ensuring safety, functional capability, and user preference in long-term personalization for general-purpose robots, this paper proposes an incremental behavior customization method grounded in the nullspace of Constraint Satisfaction Problems (CSPs). The core contribution is the first application of CSP nullspace optimization to online robot personalization: it enables parameterized constraint learning and uncertainty-aware, reset-free adaptation while strictly satisfying hard safety and task constraints. By leveraging online human-robot interaction to drive nullspace refinement, the approach supports sample-efficient, composable integration of new constraints. Evaluations across three simulated environments, a web-based user study, and a real-world assistive dining robot demonstrate that our method achieves higher personalized satisfaction with significantly fewer interactions than state-of-the-art baselines.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Humans and AI: Learning Human Values and Preferences
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Generalist robots must personalize in-the-wild to meet the diverse needs and preferences of long-term users. How can we enable flexible personalization without sacrificing safety or competency? This paper proposes Coloring Between the Lines (CBTL), a method for personalization that exploits the null space of constraint satisfaction problems (CSPs) used in robot planning. CBTL begins with a CSP generator that ensures safe and competent behavior, then incrementally personalizes behavior by learning parameterized constraints from online interaction. By quantifying uncertainty and leveraging the compositionality of planning constraints, CBTL achieves sample-efficient adaptation without environment resets. We evaluate CBTL in (1) three diverse simulation environments; (2) a web-based user study; and (3) a real-robot assisted feeding system, finding that CBTL consistently achieves more effective personalization with fewer interactions than baselines. Our results demonstrate that CBTL provides a unified and practical approach for continual, flexible, active, and safe robot personalization. Website: https://emprise.cs.cornell.edu/cbtl/

Problem

• Enable flexible robot personalization without compromising safety
• Learn parameterized constraints from online interaction efficiently
• Achieve continual adaptation in diverse environments without resets

Innovation

• Exploits null space of constraint satisfaction problems
• Learns parameterized constraints from online interaction
• Achieves sample-efficient adaptation without resets