Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Xinhao, Li, Jiaqi, Deng, Youming, Chen, Ruxin, Zhang, Yingjia, Ma, Yifei, Guo, Li, Li, Yiming, Zhang, Jing, Feng, Chen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908916643790848
author Liu, Xinhao
Li, Jiaqi
Deng, Youming
Chen, Ruxin
Zhang, Yingjia
Ma, Yifei
Guo, Li
Li, Yiming
Zhang, Jing
Feng, Chen
author_facet Liu, Xinhao
Li, Jiaqi
Deng, Youming
Chen, Ruxin
Zhang, Yingjia
Ma, Yifei
Guo, Li
Li, Yiming
Zhang, Jing
Feng, Chen
contents Reproducible closed-loop evaluation remains a major bottleneck in Embodied AI such as visual navigation. A promising path forward is high-fidelity simulation that combines photorealistic sensor rendering with geometrically grounded interaction in complex, open-world urban environments. Although recent video-3DGS methods ease open-world scene capturing, they are still unsuitable for benchmarking due to large visual and geometric sim-to-real gaps. To address these challenges, we introduce Wanderland, a real-to-sim framework that features multi-sensor capture, reliable reconstruction, accurate geometry, and robust view synthesis. Using this pipeline, we curate a diverse dataset of indoor-outdoor urban scenes and systematically demonstrate how image-only pipelines scale poorly, how geometry quality impacts novel view synthesis, and how all of these adversely affect navigation policy learning and evaluation reliability. Beyond serving as a trusted testbed for embodied navigation, Wanderland's rich raw sensor data further allows benchmarking of 3D reconstruction and novel view synthesis models. Our work establishes a new foundation for reproducible research in open-world embodied AI. Project website is at https://ai4ce.github.io/wanderland/.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20620
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI
Liu, Xinhao
Li, Jiaqi
Deng, Youming
Chen, Ruxin
Zhang, Yingjia
Ma, Yifei
Guo, Li
Li, Yiming
Zhang, Jing
Feng, Chen
Computer Vision and Pattern Recognition
Robotics
Reproducible closed-loop evaluation remains a major bottleneck in Embodied AI such as visual navigation. A promising path forward is high-fidelity simulation that combines photorealistic sensor rendering with geometrically grounded interaction in complex, open-world urban environments. Although recent video-3DGS methods ease open-world scene capturing, they are still unsuitable for benchmarking due to large visual and geometric sim-to-real gaps. To address these challenges, we introduce Wanderland, a real-to-sim framework that features multi-sensor capture, reliable reconstruction, accurate geometry, and robust view synthesis. Using this pipeline, we curate a diverse dataset of indoor-outdoor urban scenes and systematically demonstrate how image-only pipelines scale poorly, how geometry quality impacts novel view synthesis, and how all of these adversely affect navigation policy learning and evaluation reliability. Beyond serving as a trusted testbed for embodied navigation, Wanderland's rich raw sensor data further allows benchmarking of 3D reconstruction and novel view synthesis models. Our work establishes a new foundation for reproducible research in open-world embodied AI. Project website is at https://ai4ce.github.io/wanderland/.
title Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2511.20620