Distributed Virtual Model Control for Scalable Human-Robot Collaboration in Shared Workspace

2026-02-19

AI Summary

This work addresses deadlock and safety issues arising from trajectory planning conflicts in shared workspaces involving multiple robots and humans. The authors propose a decentralized, agent-agnostic virtual model control (VMC) framework that eliminates the need for explicit trajectory planning. By modeling both humans and robots as virtual components interacting through spring-damper dynamics, the framework generates motion implicitly and incorporates a force-based deadlock detection mechanism coupled with decentralized negotiation. The approach scales seamlessly to arbitrary numbers of agents and enables intuitive parameter tuning to shape safe behaviors. Experiments demonstrate a reduction in deadlock occurrence from 61.2% to zero in a block-placement task, successful real-world collaboration between two humans and two robots, and simulation-based extension to four robots, with inter-agent distances consistently maintained around 20 cm.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Intelligent Robots: Motion and Path Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We present a decentralized, agent agnostic, and safety-aware control framework for human-robot collaboration based on Virtual Model Control (VMC). In our approach, both humans and robots are embedded in the same virtual-component-shaped workspace, where motion is the result of the interaction with virtual springs and dampers rather than explicit trajectory planning. A decentralized, force-based stall detector identifies deadlocks, which are resolved through negotiation. This reduces the probability of robots getting stuck in the block placement task from up to 61.2% to zero in our experiments. The framework scales without structural changes thanks to the distributed implementation: in experiments we demonstrate safe collaboration with up to two robots and two humans, and in simulation up to four robots, maintaining inter-agent separation at around 20 cm. Results show that the method shapes robot behavior intuitively by adjusting control parameters and achieves deadlock-free operation across team sizes in all tested scenarios.

Problem

• human-robot collaboration
• deadlock
• shared workspace
• scalability
• safety

Innovation

• Virtual Model Control
• Decentralized Control
• Deadlock Resolution
• Human-Robot Collaboration
• Scalable Multi-Agent System