Rolling horizon coverage control with collaborative autonomous agents.

2025-01-30

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences

AI Summary

This work addresses the problem of distributed multi-UAV cooperative coverage of key points on 3D object surfaces. To tackle challenges posed by nonlinear visibility modeling and multi-agent coordination constraints, we propose a non-myopic, low-redundancy receding-horizon planning method. We first formulate ray-tracing-based visibility conditions as logical expressions and embed them into a mixed-integer nonlinear programming (MINLP) framework. Coupled with distributed model predictive control, the approach jointly optimizes UAV trajectories and camera poses. The method ensures real-time execution while significantly improving coverage quality: simulation and physical experiments in building inspection scenarios demonstrate enhanced coverage completeness and a reduction of redundant observation areas by over 35%, validating its effectiveness and engineering applicability in complex geometric environments.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This work proposes a coverage controller that enables an aerial team of distributed autonomous agents to collaboratively generate non-myopic coverage plans over a rolling finite horizon, aiming to cover specific points on the surface area of a three-dimensional object of interest. The collaborative coverage problem, formulated as a distributed model predictive control problem, optimizes the agents' motion and camera control inputs, while considering inter-agent constraints aiming at reducing work redundancy. The proposed coverage controller integrates constraints based on light-path propagation techniques to predict the parts of the object's surface that are visible with regard to the agents' future anticipated states. This work also demonstrates how complex, non-linear visibility assessment constraints can be converted into logical expressions that are embedded as binary constraints into a mixed-integer optimization framework. The proposed approach has been demonstrated through simulations and practical applications for inspecting buildings with unmanned aerial vehicles (UAVs).This article is part of the theme issue 'The road forward with swarm systems'.

Problem

• Enable aerial agents to collaboratively cover 3D objects
• Optimize agent motion and camera inputs to reduce redundancy
• Convert visibility constraints into binary mixed-integer optimization

Innovation

• Rolling horizon coverage control for aerial agents
• Distributed model predictive control optimization
• Mixed-integer framework with visibility constraints