MICP-L: Mesh-based ICP for Robot Localization using Hardware-Accelerated Ray Casting

Abstract-- Triangle mesh maps have proven to be a versatile 3D environment representation for robots to navigate in challenging indoor and outdoor environments exhibiting tunnels, hills and varying slopes. To make use of these mesh maps, methods are needed that allow robots to accurately localize themselves to perform typical tasks like path planning and navigation. We accelerate the computation of ray casting correspondences (RCC) between range sensors and mesh maps by supporting different parallel computing devices like multicore CPUs, GPUs and the latest NVIDIA RTX hardware. By additionally transforming the covariance computation into a reduction operation, we can optimize the initial guessed poses in parallel on CPUs or GPUs, making our implementation applicable in real-time on a variety Figure 1: The Lero agricultural monitoring robot uses MICP-L for of target architectures. We demonstrate the robustness of our localization during mesh-based navigation between beds in a market localization approach with datasets from agriculture, drones, garden micro-farming environment. It is designed to be Localization is the task of estimating the state of a applicable to robots with varying computational capabilities.