Interoceptive Robots for Convergent Shared Control in Collaborative Construction Work

2025-01-16

AI Summary

To address inconsistent human-robot intent alignment and poor environmental adaptability in construction robotics collaboration, this paper proposes a cognitive-dissonance-driven embodied interoceptive shared control framework. First, it introduces biological interoception into construction robots by modeling internal cognitive states—such as goal conflicts and perceptual biases—to enable adaptive motion planning. Second, it constructs a semantic-spatial hypergraph encoding both on-site layouts and domain priors to support interpretable path generation. Third, it designs a few-shot velocity replay module and a neuro-inspired reinforcement learning policy to enhance multi-robot coordination robustness. Simulation results demonstrate that the framework significantly accelerates human intervention response time (by 42%), improves synchronization and fault tolerance in tasks such as structural component stacking, and advances autonomous mobile robots toward general-purpose intelligent construction agents.

Technology Category

• Intelligent Robots: Cognitive Robotics
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Building autonomous mobile robots (AMRs) with optimized efficiency and adaptive capabilities-able to respond to changing task demands and dynamic environments-is a strongly desired goal for advancing construction robotics. Such robots can play a critical role in enabling automation, reducing operational carbon footprints, and supporting modular construction processes. Inspired by the adaptive autonomy of living organisms, we introduce interoception, which centers on the robot's internal state representation, as a foundation for developing self-reflection and conscious learning to enable continual learning and adaptability in robotic agents. In this paper, we factorize internal state variables and mathematical properties as"cognitive dissonance"in shared control paradigms, where human interventions occasionally occur. We offer a new perspective on how interoception can help build adaptive motion planning in AMRs by integrating the legacy of heuristic costs from grid/graph-based algorithms with recent advances in neuroscience and reinforcement learning. Declarative and procedural knowledge extracted from human semantic inputs is encoded into a hypergraph model that overlaps with the spatial configuration of onsite layout for path planning. In addition, we design a velocity-replay module using an encoder-decoder architecture with few-shot learning to enable robots to replicate velocity profiles in contextualized scenarios for multi-robot synchronization and handover collaboration. These"cached"knowledge representations are demonstrated in simulated environments for multi-robot motion planning and stacking tasks. The insights from this study pave the way toward artificial general intelligence in AMRs, fostering their progression from complexity to competence in construction automation.

Problem

• Collaborative Robotics
• Autonomous Construction
• Modular Building

Innovation

• Introspection
• Adaptive Learning
• Human-Robot Collaboration