Learning specifications for reactive synthesis with safety constraints

2026-01-09

arXiv.org

AI Summary

This work addresses the problem of learning complex task specifications from demonstrations while ensuring safety constraints and generating robust policies that balance user preferences with robotic execution costs in dynamic environments. The approach models implicit tasks as probabilistic deterministic finite automata (PDFAs), uniquely embedding safety constraints throughout the evidence-driven state-merging process. It introduces a computable multi-objective reactive synthesis framework that leverages two-player games and value iteration to produce a Pareto-optimal set of policies. Experimental results demonstrate that the learned PDFAs completely avoid unsafe behaviors, and the synthesized policies reliably accomplish tasks across multiple robotic platforms while effectively trading off user preferences against execution costs.

Technology Category

Intelligent Robots: Learning & Optimization for ROBHumans and AI: Human-Aware Planning and Behavior PredictionPlanning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

Responsible Web: Machine-in-the-loop, human agency and autonomyEconomics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystemsUser Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

This paper presents a novel approach to learning from demonstration that enables robots to autonomously execute complex tasks in dynamic environments. We model latent tasks as probabilistic formal languages and introduce a tailored reactive synthesis framework that balances robot costs with user task preferences. Our methodology focuses on safety-constrained learning and inferring formal task specifications as Probabilistic Deterministic Finite Automata (PDFA). We adapt existing evidence-driven state merging algorithms and incorporate safety requirements throughout the learning process to ensure that the learned PDFA always complies with safety constraints. Furthermore, we introduce a multi-objective reactive synthesis algorithm that generates deterministic strategies that are guaranteed to satisfy the PDFA task while optimizing the trade-offs between user preferences and robot costs, resulting in a Pareto front of optimal solutions. Our approach models the interaction as a two-player game between the robot and the environment, accounting for dynamic changes. We present a computationally-tractable value iteration algorithm to generate the Pareto front and the corresponding deterministic strategies. Comprehensive experimental results demonstrate the effectiveness of our algorithms across various robots and tasks, showing that the learned PDFA never includes unsafe behaviors and that synthesized strategies consistently achieve the task while meeting both the robot cost and user-preference requirements.

Problem

• reactive synthesis
• safety constraints
• learning from demonstration
• task specification
• probabilistic automata

Innovation

• reactive synthesis
• safety-constrained learning
• probabilistic deterministic finite automata
• multi-objective optimization
• learning from demonstration