Collaborative Planning with Concurrent Synchronization for Operationally Constrained UAV-UGV Teams
Zihao Deng, Qianhuang Li, Peng Gao, Maggie Wigness, John G. Rogers III, Donghyun Kim, Hao Zhang
AI summary
Problem
Existing methods fail to jointly optimize energy-constrained UAV task planning, traversability-constrained UGV path planning, and time-synchronized execution, often causing mission delays or failures.
Approach
CoPCS uses a heterogeneous graph transformer to encode operational constraints and a transformer decoder to generate joint, synchronized action sequences, trained end-to-end via imitation learning.
Key results
- Enables synchronized concurrent co-planning for heterogeneous teams
- Integrates heterogeneous graph transformers with transformer decoders
- Trains a unified policy end-to-end via imitation learning
- Demonstrates substantial performance gains in simulations and physical experiments
Why it matters
Provides a scalable, learning-based solution for reliable multi-robot operations in real-world applications like disaster response and environmental monitoring.
Abstract
Collaborative planning under operational con- straints is an essential capability for heterogeneous robot teams tackling complex large-scale real-world tasks. Unmanned Aerial Vehicles (UAVs) offer rapid environmental coverage, but flight time is often limited by energy constraints, whereas Unmanned Ground Vehicles (UGVs) have greater energy capacity to sup- port long-duration missions, but movement is constrained by traversable terrain. Individually, neither can complete tasks such as environmental monitoring. Effective UAV-UGV collaboration therefore requires energy-constrained multi-UAV task planning, traversability-constrained multi-UGV path planning, and cru- cially, synchronized concurrent co-planning to ensure timely in-mission recharging. To enable these capabilities, we propose Collaborative Planning with Concurrent Synchronization (CoPCS), a learning-based approach that integrates a heterogeneous graph transformer for operationally constrained task encoding with a transformer decoder for joint, synchronized co-planning that enables UAVs and UGVs to act concurrently in a coordinated manner. CoPCS is trained end-to-end under a unified imitation learning paradigm. We conducted extensive experiments to evalu- ate CoPCS in both robotic simulations and physical robot teams. Experimental results demonstrate that our method provides the novel multi-robot capability of synchronized concurrent co- planning and substantially improves team performance. More details of this work are available on the project website: https://hcrlab.gitlab.io/project/CoPCS.