System Design for Maintaining Internal State Consistency in Long-Horizon Robotic Tabletop Games

2026-03-26

AI Summary

This work addresses the challenge of maintaining state consistency in long-horizon, multi-player turn-based tabletop games—such as mahjong—where minor perceptual or execution errors can induce task-state inconsistencies that propagate across decision modules and lead to interaction failures. To mitigate this, the authors propose a system-level architecture that decouples high-level semantic reasoning from real-time perception and control through explicit state partitioning, verifiable action primitives, and a haptic-triggered recovery mechanism. An interaction-layer monitor is further integrated to detect turn violations and inadvertent disclosure of hidden information. This design effectively isolates and contains cross-module error propagation, thereby preserving end-to-end state consistency. Experimental results demonstrate that the proposed approach significantly enhances reliability in long-horizon tasks, whereas conventional monolithic or unverified pipeline architectures exhibit marked performance degradation.

Technology Category

• Multiagent Systems: Mechanism Design
• Reasoning under Uncertainty: Sequential Decision Making
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Long-horizon tabletop games pose a distinct systems challenge for robotics: small perceptual or execution errors can invalidate accumulated task state, propagate across decision-making modules, and ultimately derail interaction. This paper studies how to maintain internal state consistency in turn-based, multi-human robotic tabletop games through deliberate system design rather than isolated component improvement. Using Mahjong as a representative long-horizon setting, we present an integrated architecture that explicitly maintains perceptual, execution, and interaction state, partitions high-level semantic reasoning from time-critical perception and control, and incorporates verified action primitives with tactile-triggered recovery to prevent premature state corruption. We further introduce interaction-level monitoring mechanisms to detect turn violations and hidden-information breaches that threaten execution assumptions. Beyond demonstrating complete-game operation, we provide an empirical characterization of failure modes, recovery effectiveness, cross-module error propagation, and hardware-algorithm trade-offs observed during deployment. Our results show that explicit partitioning, monitored state transitions, and recovery mechanisms are critical for sustaining executable consistency over extended play, whereas monolithic or unverified pipelines lead to measurable degradation in end-to-end reliability. The proposed system serves as an empirical platform for studying system-level design principles in long-horizon, turn-based interaction.

Problem

• state consistency
• long-horizon interaction
• robotic tabletop games
• error propagation
• turn-based games

Innovation

• state consistency
• modular architecture
• verified action primitives
• tactile-triggered recovery
• interaction monitoring