Heterogeneous Vehicles Routing for Water Canal Damage Assessment

TL;DR

This paper presents a path planning framework for heterogeneous UAV and ground vehicle teams to efficiently inspect large water canal networks, ensuring safety, regulatory compliance, and rapid replanning capabilities.

Contribution

It introduces a novel MIQP-based optimization approach for joint path planning of UAVs and ground vehicles with constraints, tailored for large-scale water canal inspection.

Findings

Successfully generates optimal inspection paths covering all canal segments.

Enables quick replanning when conditions change.

Validated through simulation results.

Abstract

In Japan, inspection of irrigation water canals has been mostly conducted manually. However, the huge demand for more regular inspections as infrastructure ages, coupled with the limited time window available for inspection, has rendered manual inspection increasingly insufficient. With shortened inspection time and reduced labor cost, automated inspection using a combination of unmanned aerial vehicles (UAVs) and ground vehicles (cars) has emerged as an attractive alternative to manual inspection. In this paper, we propose a path planning framework that generates optimal plans for UAVs and cars to inspect water canals in a large agricultural area (tens of square kilometers). In addition to optimality, the paths need to satisfy several constraints, in order to guarantee UAV navigation safety and to abide by local traffic regulations. In the proposed framework, the canal and road networks are first modeled as two graphs, which are then partitioned into smaller subgraphs that can be covered by a given fleet of UAVs within one battery charge. The problem of finding optimal paths for both UAVs and cars on the graphs, subject to the constraints, is formulated as a mixed-integer quadratic program (MIQP). The proposed framework can also quickly generate new plans when a current plan is interrupted. The effectiveness of the proposed framework is validated by simulation results showing the successful generation of plans covering all given canal segments, and the ability to quickly revise the plan when conditions change.