SidewalkBench: Benchmarking Visual Navigation on Urban Sidewalks

arXiv:2606.16953 · cs.RO · Submitted 2026-06-15 · Read on arXiv

cs.RO

Submitted: 2026-06-15

Updated: 2026-10-13

Code: https://github.com/isaac-sim/IsaacSim

Project page: https://vail-ucla.github.io/SidewalkBench

Terminology

• Benchmark — 2× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• ViNT: A Foundation Model for Visual Navigation
• From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
• Narrate2Nav: Real-Time Visual Navigation with Implicit Language Reasoning in Human-Centric Environments
• TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments
• A Protocol for Validating Social Navigation Policies
• Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation
• StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling
• NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance
• Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI
• AirSim360: A Panoramic Simulation Platform within Drone View
• HuNavSim 2.0: An Enhanced Human Navigation Simulator for Human-Aware Robot Navigation
• Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
• GaussGym: An open-source real-to-sim framework for learning locomotion from pixels
• SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Image
• On Evaluation of Embodied Navigation Agents
• Decoupled Weight Decay Regularization

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies