Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Automated Real-Time Inspection in Indoor and Outdoor 3D Environments with Cooperative Aerial Robots

Andreas Anastasiou, Angelos Zacharia, Savvas Papaioannou, Panayiotis Kolios, Christos G. Panayiotou, Marios M. Polycarpou

TL;DR

This work tackles automated 3D infrastructure inspection in unknown cluttered indoor and outdoor environments using a team of heterogeneous UAVs. It introduces CARI, a two-stage cooperative inspection approach: Stage 1 builds a map of the environment using complementary LiDAR and camera sensing, and Stage 2 computes cooperative, collision-free inspection paths to maximize surface observation quality. The approach combines operational volume determination, real-time occupancy mapping, distributed multi-TSP path planning, and a Dijkstra-Receding Horizon Local Planning controller with ongoing map exchanges to maintain up-to-date plans. Validation is performed with Gazebo-based simulations across three real-world-like scenarios, achieving thorough surface coverage and demonstrated success in the CARIC competition. The framework offers a scalable, practical solution for robust multi-UAV 3D inspection in unknown clutter with real-time coordination and communication constraints.

Abstract

This work introduces a cooperative inspection system designed to efficiently control and coordinate a team of distributed heterogeneous UAV agents for the inspection of 3D structures in cluttered, unknown spaces. Our proposed approach employs a two-stage innovative methodology. Initially, it leverages the complementary sensing capabilities of the robots to cooperatively map the unknown environment. It then generates optimized, collision-free inspection paths, thereby ensuring comprehensive coverage of the structure's surface area. The effectiveness of our system is demonstrated through qualitative and quantitative results from extensive Gazebo-based simulations that closely replicate real-world inspection scenarios, highlighting its ability to thoroughly inspect real-world-like 3D structures.

Automated Real-Time Inspection in Indoor and Outdoor 3D Environments with Cooperative Aerial Robots

TL;DR

This work tackles automated 3D infrastructure inspection in unknown cluttered indoor and outdoor environments using a team of heterogeneous UAVs. It introduces CARI, a two-stage cooperative inspection approach: Stage 1 builds a map of the environment using complementary LiDAR and camera sensing, and Stage 2 computes cooperative, collision-free inspection paths to maximize surface observation quality. The approach combines operational volume determination, real-time occupancy mapping, distributed multi-TSP path planning, and a Dijkstra-Receding Horizon Local Planning controller with ongoing map exchanges to maintain up-to-date plans. Validation is performed with Gazebo-based simulations across three real-world-like scenarios, achieving thorough surface coverage and demonstrated success in the CARIC competition. The framework offers a scalable, practical solution for robust multi-UAV 3D inspection in unknown clutter with real-time coordination and communication constraints.

Abstract

This work introduces a cooperative inspection system designed to efficiently control and coordinate a team of distributed heterogeneous UAV agents for the inspection of 3D structures in cluttered, unknown spaces. Our proposed approach employs a two-stage innovative methodology. Initially, it leverages the complementary sensing capabilities of the robots to cooperatively map the unknown environment. It then generates optimized, collision-free inspection paths, thereby ensuring comprehensive coverage of the structure's surface area. The effectiveness of our system is demonstrated through qualitative and quantitative results from extensive Gazebo-based simulations that closely replicate real-world inspection scenarios, highlighting its ability to thoroughly inspect real-world-like 3D structures.
Paper Structure (16 sections, 6 equations, 4 figures, 2 tables, 2 algorithms)

This paper contains 16 sections, 6 equations, 4 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Preliminaries
  4. Operational Environment
  5. UAV Dynamical Model
  6. Ranging and Visual Sensor Models
  7. Communication Model
  8. Problem Statement
  9. Proposed Approach
  10. Operational Volume Determination
  11. Environmental Mapping
  12. Cooperative Inspection
  13. Evaluation
  14. Simulation Setup
  15. Simulation Results
  16. ...and 1 more sections

Figures (4)

  • Figure 1: Overview of the proposed approach for 3D infrastructure inspection using multi-UAV system.
  • Figure 2: (a) Derivation of the operational volume, (b) Discretization of the operational volume, (c) Mapping path generation and execution, (d) Initial occupancy map generation, (e) Inspection waypoint generation, (f) Inspection path generation.
  • Figure 3: (a)-(c) Illustrative examples of the 3 inspection scenarios conducted for the evaluation of the proposed approach. The bounded boxes indicate the selected area for inspection. (d)-(f) Visualization of inspection intensity achieved by the UAV fleet at each scenario, respectively, by employing the proposed CARI scheme.
  • Figure 4: Average observation quality score $q_{\zeta,k}$ achieved up to time-step $k$ for each scenario for inspection mission durations of $\mathcal{T}_{1} = 300$, $\mathcal{T}_{2} = 500$, and $\mathcal{T}_{3} = 500$, respectively.