A Navigation-Based Evaluation Metric for Probabilistic Occupancy Grids: Pathfinding Cost Mean Squared Error - Archive ouverte HAL
Conference Papers Year : 2023

A Navigation-Based Evaluation Metric for Probabilistic Occupancy Grids: Pathfinding Cost Mean Squared Error

Abstract

While robotics increasingly relies on occupancy grids for environment perception, the lack of specificallydesigned metrics leads existing research to employ Image Quality Assessment (IQA) metrics and topological evaluations, which were primarily designed for binary occupancy grids. While appropriate as a first approximation, not taking into account the particular nature and usage of probabilistic occupancy grids limits the accuracy of their evaluation. In this paper, we propose the PathFinding Cost Mean Squared Error (PFC-MSE), a new probabilistic occupancy grid comparison metric designed to incorporate their main usage and attributes. Emulating gridbased navigation methods, the metric defines the difference between two grids as the measured spread between the navigation behavior their use induces, which emphasizes variations in general topology over local cell-value fluctuations. Experimental results on 10,000 driving scenes exhibit the relevance of the approach in quantifying grid disparities compared to existing approaches.
Fichier principal
Vignette du fichier
IEEE_ITSC_2023_final-4.pdf (484.13 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04211125 , version 1 (19-09-2023)

Licence

Identifiers

  • HAL Id : hal-04211125 , version 1

Cite

Jean-Baptiste Horel, Robin Baruffa, Lukas Rummelhard, Alessandro Renzaglia, Christian Laugier. A Navigation-Based Evaluation Metric for Probabilistic Occupancy Grids: Pathfinding Cost Mean Squared Error. ITSC 2023 - 26th IEEE International Conference on Intelligent Transportation Systems, IEEE, Sep 2023, Bilbao, Spain, Spain. pp.1-6. ⟨hal-04211125⟩
144 View
103 Download

Share

More