Virga enables safer coordination between drones and ground robots
VIRGA: Virtual-Agent-Intermediated Riemannian Geometry for Active-Sensing Air-Ground Coordination
Robotics
Summary
Keeping a flying drone visible to a ground robot with a rotating sensor is tricky when they both move and avoid obstacles. The paper presents VIRGA, a system that lets the two robots share information through a virtual helper that guides their movements based on special math fields. This approach helps them move safely together, keeps the drone visible to the sensor, and works well even in tight and complex spaces. The authors tested VIRGA against other methods and found it better at balancing speed, safety, and good views.
What this means in practice
- •For warehouse automation teams: Coordinate drones and ground robots in warehouses to improve safe scanning and inspection around obstacles without losing sensor visibility.
- •For robotic cave explorers: Enable autonomous drone and ground robot teams to safely navigate confined and irregular underground spaces while keeping mutual observation.
Authors
Fenghe Guo, Runjie Shen, Chenyang Sun, Junrui Zhang
Abstract
Air-ground autonomy becomes harder when the unmanned aerial vehicle (UAV) must remain observable by a gimbal light detection and ranging (LiDAR) mounted on the unmanned ground vehicle (UGV). The platforms must avoid dynamic obstacles while coordinating heterogeneous motion, limited sensing, and changing task initiative within one closed loop. This paper presents VIRGA, a neural geometric coordination framework that turns dual-LiDAR observations into bounded source-specific Riemannian fields and couples them through a virtual agent with reciprocal elastic feedback. Platform-aware execution maps convert the shared coordination reference into feasible UAV, UGV, and gimbal commands while enforcing active-observation safeguards. Evaluation against three complementary baselines reveals distinct limitations. An adapted Ray-RMP controller provides the fastest Riemannian response but produces insufficient clearance in the coupled air-ground task. A dense analytical Riemannian field improves geometric avoidance, yet its high evaluation cost prevents stable field-of-view maintenance. An adapted ColAG controller achieves the lowest latency but still incurs safety and observability violations. VIRGA completes all paired warehouse conditions safely, while a long-range cave stress test without retraining demonstrates sustained coordination in irregular and confined geometry. Ablations confirm contributions from online geometric evaluation, virtual-agent mediation, and reciprocal feedback.