Large-Scale Tunnel Air--Ground Collaboration With FLISP: Fast LiDAR-IMU Synchronized Path Planne

2026-06-24

AI Summary

This study addresses the inefficiency and high risk associated with manual inspection of hydropower station tunnels, as well as the substantial computational overhead and sampling instability of conventional mapping approaches. To overcome these limitations, the authors propose FLISP, a novel framework featuring the first map-free collaborative path planning mechanism that relies solely on a single vehicle-mounted LiDAR-IMU system to simultaneously generate coordinated inspection trajectories for both unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs). FLISP employs a unified perception architecture to enable air-ground collaboration, incorporates platform-specific solvers, and introduces a hierarchical optimization strategy to suppress state estimation drift, thereby eliminating dependence on prior maps. Experimental validation in a 1.2-kilometer operational tunnel demonstrates a 100% mission success rate, with path planning latency of approximately 7 milliseconds—seven times faster than grid-based methods and three orders of magnitude faster than sampling-based approaches.

Abstract

Hydropower tunnel inspection is critical for infrastructure integrity yet remains inefficient and hazardous using manual methods. We propose FLISP (Fast LiDAR-IMU Synchronized Path Planner), a mapless planning framework for cooperative UGV-UAV inspection. Unlike traditional map-based paradigms, FLISP features three core contributions: (1) a unified architecture where a single UGV-mounted LiDAR-IMU suite drives synchronized path generation for both platforms; (2) platform-specific solvers utilizing an enhanced Firefly Algorithm for UGV obstacle avoidance and a dynamic iterative optimizer for UAV flight; and (3) a hierarchical refinement strategy ensuring kinematic feasibility without state estimation drift. Benchmarks in a 1.2 km operational tunnel demonstrate that FLISP circumvents structural bottlenecks of map-based methods, eliminating map rasterization overhead (Fast-LIO2 + A*) and sampling instability (LIO-SAM + RRT*). FLISP achieves a 100% success rate with ~7 ms latency, representing a 7-fold speedup over grid-based and three-order-of-magnitude improvement over sampling-based baselines. Validated in operational hydropower tunnels, this approach offers a scalable solution for robotic inspection in feature-degraded linear infrastructure. A demonstration video is available at https://youtu.be/Y_ezs1PfLJ4, and the code at https://github.com/ArchibaldGuo/FLISP.git.

Problem

• tunnel inspection
• air-ground collaboration
• mapless planning
• LiDAR-IMU synchronization
• linear infrastructure

Innovation

• mapless planning
• LiDAR-IMU synchronization
• UGV-UAV collaboration
• Firefly Algorithm
• hierarchical refinement