Towards Reliable Aerial–Ground Vehicle Collaboration Integrated Planning and Autonomy Framework for Field Deployment

Jul 16, 2026

Upload by Quinn

Limited flight endurance restricts unmanned aerial vehicle (UAV) operational range in long-duration missions that must visit multiple spatially distributed Areas of Interest (AOIs). Efficient routing—visit sequencing—governs mission time, energy consumption, and feasibility. UAV–UGV mobile recharging can help, yet creates a tightly coupled cooperative routing challenge across UAV sequencing, UGV road-constrained motion, energy management, and uncertain rendezvous scheduling. A DRL-based integrated planning and autonomy framework is presented, validated outdoors.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

Abstract

Introduction

Problem Formulation and Integrated Framework

Deep Reinforcement Learning Planner

YAML-Based Mission API

Autonomy Stack and System Implementation

Online Replanning with RARP

Outdoor Field Experiments and Validation

Search-and-Rescue Use Case

Towards Reliable Aerial–Ground Vehicle Collaboration: An Integrated Planning and Autonomy Framework for Field Deployment Md Safwan Mondal , Luca Russo , James D. Humann , James M. Dotterweich, and Pranav Bhounsule arXiv :2607 .07350v 1 [ cs .RO] 7 Jul 2026 Abstract—Limited flight endurance significantly restricts the operational range of unmanned aerial vehicles (UAVs) in longduration missions such as surveillance and inspection, where multiple spatially distributed Areas of Interest (AOIs) must be visited. These tasks require efficient routing—determining the sequence of visits—which directly impacts mission time, energy consumption, and overall feasibility. Pairing UAVs with unmanned ground vehicles (UGVs) for mobile recharging offers a promising solution, but introduces a tightly coupled cooperative routing problem involving UAV route planning, UGV roadconstrained movement, energy management, and rendezvous scheduling under uncertainty. In this work, we present an integrated planning and autonomy framework for reliable field deployment. We formulate the problem as an energy-constrained cooperative routing task and solve it using a Deep Reinforcement Learning (DRL)-based planner that jointly optimizes the UAV visitation sequence and rendezvous locations with the UGV, outperforming baseline heuristics in minimizing total mission time. To bridge the gap between planning and execution, we introduce a standardized two-layer YAML-based mission API that captures environment states and structures lightweight, synchronized action sequences. This framework is supported by a complete autonomy stack using PX4/MAVSDK for UAV control and ROS 2/Nav2 for UGV navigation. Furthermore, we propose a lightweight Rendezvous-Aware Replanner (RARP) that operates online to handle environmental uncertainties, reducing energy margin violations from 83.33% to 20.00% . The full system is validated through outdoor field experiments, demonstrating robust cooperative navigation and adaptability in dynamic tasks, including a search-and-rescue scenario with vision-language model (VLM)-based hazard detection. Index Terms—UAV–UGV collaboration, cooperative routing, deep reinforcement learning, autonomous systems, field deployment. I. INTRODUCTION THe collaboration between Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) has been widely explored across domains that benefit from the complementary strengths of aerial mobility and ground-level endurance and payload capacity. UAVs provide rapid coverage and high-resolution sensing but are severely constrained by limited flight endurance. UGVs, in contrast, offer long- 1Md Safwan Mondal (corresponding author), Luca Russo and Pranav A. Bhounsule are with the Department of Mechanical and Industrial Engineering, University of Illinois Chicago, IL, 60607 USA. [mmonda4@uic.edu](mmonda4@uic.edu), [lrusso5@uic.edu](lrusso5@uic.edu) , [pranav@uic.edu](pranav@uic.edu)[ ](pranav@uic.edu)[2](2 James D. Humann is with DEVCOM Army Research Laboratory)[ James D. Humann is with DEVCOM Army Research Laboratory](2 James D. Humann is with DEVCOM Army Research Laboratory), Minneapolis, Minnesota, [USA.](USA. james.d.humann.civ@army.mil)[ james.d.humann.civ@army.mil](USA. james.d.humann.civ@army.mil)[ ](USA. james.d.humann.civ@army.mil)[3](3 James M. Dotterweich)[ James M. Dotterweich](3 James M. Dotterweich), [is with DEVCOM Army Research](is with DEVCOM Army Research)[ ](is with DEVCOM Army Research)Laboratory, Aberdeen Proving Grounds, Aberdeen, MD 21005 USA. [james.m.dotterweich.civ@army.mil](james.m.dotterweich.civ@army.mil) *This work was supported by ARO contract number W911NF-24-2-0018 . duration operation, higher payload capability, and reliable navigation along road networks. When integrated, a UGV can act as a mobile recharging or support platform, allowing the UAV to operate for longer durations by periodically recharging from the UGV. This cross-domain synergy has motivated a growi

FAQs

Why does UAV endurance limit long-duration ISR missions with multiple AOIs?

Limited flight endurance constrains how far a UAV can operate while visiting multiple spatially distributed AOIs, impacting overall mission feasibility.

How does pairing UAVs with UGVs help address endurance limits?

UGVs provide mobile recharging at designated rendezvous points, enabling the UAV to extend mission duration through periodic battery replenishment.

What is the core contribution of the proposed framework?

An integrated energy-constrained cooperative routing framework combines a DRL-based planner for UAV visit sequencing and rendezvous decisions, a standardized YAML mission API, and an online Rendezvous-Aware Replanner for robust execution under uncertainty.

Jul 16, 2026

Upload by Quinn