Dynamic UGV-UAV Cooperative Path Planning in Uncertain Environments

Researchers Ninh Nguyen and Srinivas Akella from UNC Charlotte have introduced a Dynamic UGV-UAV Cooperative Path Planning (DUCPP) framework, accepted at IEEE ICRA 2026. The system enables an unmanned ground vehicle (UGV), assisted by one or more unmanned aerial vehicles (UAVs), to navigate uncertain road networks where edges may be impassable due to damage or debris. The UAVs dynamically inspect road segments, identify blocked routes, and prune them from the UGV's path, ensuring safe and efficient travel to a destination.

The team evaluated multiple strategies, including a bidirectional approach, on 100 urban road networks. The bidirectional method consistently outperformed others, and using multiple UAVs further reduced UGV travel time at the cost of increased computation. This work is particularly relevant for disaster response, emergency supply transport, and rescue operations, where road conditions are partially unknown. The framework provides a robust solution for cooperative path planning in challenging, uncertain environments.