Problem
Research questions and friction points this paper is trying to address.
visual locomotion controllers
complex visual environments
evaluation gap
hyper-photo-realistic
closed-loop evaluation
The Neverwhere Visual Parkour Benchmark Suite
🤖 AI Summary
为解决视觉运动控制器在复杂环境下的评估难题，通过构建包含60多个3D高斯点云重建场景的Neverwhere基准套件，提供了一种超逼真的闭环评估环境。
📝 Abstract
State-of-the-art visual locomotion controllers are increasingly capable at handling complex visual environments, making evaluating their real-world performance before deployment increasingly difficult. This work intends to narrow this train/evaluation gap by developing a collection of hyper-photo-realistic, closed-loop evaluation environments - The Neverwhere Benchmark Suite - comprised of over sixty 3D Gaussian Splatting reconstructions of urban indoor and outdoor scenes. Our goal is to encourage large-scale and reproducible robot evaluation by making it easier to create and integrate Gaussian splats-based reconstructions into simulated continuous testing setups. We also underscore the potential pitfalls of relying exclusively on 3D Gaussian-generated data for training, by providing policy checkpoints trained over multiple Neverwhere scenes and their performance when evaluated in novel scenes. Our analysis illustrates the necessity of sourcing diverse data to ensure performance. Code and data are available on the project page: https://ziyc.github.io/neverwhere-bench/.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Gaussian Splatting
Benchmark Suite
Photo-Realistic Environments
Robot Evaluation
🔎 Similar Papers
No similar papers found.
