Distributed Virtual Model Control for Scalable Human-Robot Collaboration in Shared Workspace
Yi Zhang, Omar Faris, Chapa Sirithunge, Kai-Fung Chu, Fumiya Iida, Fulvio Forni
AI summary
Problem
Current human-robot collaboration methods often rely on heavy computation, agent-specific rules, or centralized planning, limiting scalability and safety in dynamic shared workspaces.
Approach
The authors embed both humans and robots in a shared workspace governed by virtual mechanical components, where motion emerges from spring-damper interactions rather than explicit planning, supplemented by a force-based stall detector for conflict resolution.
Key results
- Agent-agnostic control treating humans and robots identically via virtual mechanics
- Elimination of robot blockages in pick-and-place tasks, reducing failure rates from 61.2% to zero
- Scalable decentralized architecture supporting up to two humans and two robots experimentally, and four robots in simulation
- Maintenance of safe inter-agent separation (~20 cm) through tunable virtual spring and damper parameters
Why it matters
Offers a lightweight, scalable, and safety-guaranteed control paradigm for dynamic shared workspaces, enabling seamless human-robot teamwork without heavy computation or agent-specific rules.
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 ne- gotiation. 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.