BenchNav: Simulation Platform for Benchmarking Off-road Navigation Algorithms with Probabilistic Traversability

TL;DR

BenchNav is an open-source simulation platform that benchmarks off-road navigation algorithms with probabilistic traversability, aiding in the design and comparison of diverse planning methods in complex environments.

Contribution

It introduces a versatile, PyTorch-based simulation platform with synthetic environment generation, ML-based traversability prediction, and standardized planning execution for off-road navigation.

Findings

Demonstrates BenchNav's effectiveness with three different planning algorithms.

Provides a comprehensive pipeline for synthetic environment creation and traversability modeling.

Facilitates algorithm benchmarking in complex off-road scenarios.

Abstract

As robotic navigation techniques in perception and planning advance, mobile robots increasingly venture into off-road environments involving complex traversability. However, selecting suitable planning methods remains a challenge due to their algorithmic diversity, as each offers unique benefits. To aid in algorithm design, we introduce BenchNav, an open-source PyTorch-based simulation platform for benchmarking off-road navigation with uncertain traversability. Built upon Gymnasium, BenchNav provides three key features: 1) a data generation pipeline for preparing synthetic natural environments, 2) built-in machine learning models for traversability prediction, and 3) consistent execution of path and motion planning across different algorithms. We show BenchNav's versatility through simulation examples in off-road environments, employing three representative planning algorithms from different domains. https://github.com/masafumiendo/benchnav