CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Sat, 22 Nov 2025 04:15:03 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"692138c7-8034" expires: Tue, 30 Dec 2025 06:45:13 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 6791:318CF6:9AA1CD:ADCAD2:695372A0 accept-ranges: bytes date: Tue, 30 Dec 2025 06:35:13 GMT via: 1.1 varnish age: 0 x-served-by: cache-bom-vanm7210088-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767076513.235679,VS0,VE223 vary: Accept-Encoding x-fastly-request-id: 67925f9b5dfd887db1fe97e30de09d2e860839da content-length: 5853 CMU-VLN: The official webpage for Vision-Language Navigation Project in Zhang Lab in CMU.

Object Navigation

Haokun Zhu¹, Zongtai Li¹, Zihan Liu^1,2, Kevin Guo¹, Yuxin Cai^1,3, Guofei Chen¹, Chen Lv³ Wenshan Wang¹ Jean Oh¹ Ji Zhang¹

¹Carnegie Mellon University, ²New York University, ³Nanyang Technological University

Paper (Coming Soon) Code (Coming Soon)

Contributions

We propose a cross-embodiment system—supporting wheeled robots, quadrupeds, and humanoids—that incrementally builds a multi-layer representation of the environment, including room, viewpoint, and object layers, enabling the VLM to make more informed decisions during the object navigation.
We design an efficient two-stage navigation policy based on this representation, combining high-level planning guided by the VLM's reasoning and low-level exploration with VLM's assistance.
Our system not only supports standard object navigation but also enables conditional object navigation—such as navigation conditioned on object attributes or spatial relations—through its multi-layer representation.
We conduct extensive real-world evaluations, including three long-range tests spanning an entire building floor and 75 unit tests conducted within multi-room environments (51 on wheeled robots, 18 on quadrupeds and 6 on humannoids).