Research paper
Safety constraints around legged vision-language navigation
The authors place state estimation, spatial perception and a barrier-constrained motion planner below a vision-language action planner. They report humanoid and quadruped experiments to examine collision avoidance under the method's assumptions.
Reviewed 2026-11-05 · Source and bibliography checked
- Original title
- Caging Vision-Language Navigation for Legged Robots via Barrier-Certified Safety Architecture
- Publisher
- arXiv
- Authors
- Kulkarni, Abhijeet M., Katragadda, Saimouli, Du, Yuze, Sha, Zijun, Huang, Guoquan
- First archive posting
- 2026-11-03
- Source language
- en
- Source country
- US
- Edition
- arXiv:2611.04972v1
- Access
- Open archive metadata and manuscript
- Publication status
- Preprint
Related resources and engineering notes
Source overview
The authors place state estimation, spatial perception and a barrier-constrained motion planner below a vision-language action planner. They report humanoid and quadruped experiments to examine collision avoidance under the method's assumptions.
Use and review
Source check covers the archive abstract and metadata. Reported results depend on the stated models and tests; application-specific safety validation remains required. The date is the first archive posting.
Sources & editions
Caging Vision-Language Navigation for Legged Robots via Barrier-Certified Safety Architecture ↗
arXiv · arXiv:2611.04972v1
arXiv abstract, citation metadata and v1 submission history. First archive posting: 2026-11-03.