bagh2178/GC-VLN
[CoRL 2025] GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigation
This project helps roboticists program robots to navigate complex 3D environments using natural language instructions. It takes human-readable directions, like "go to the kitchen and turn left at the island," and translates them into an optimal navigation path for a robot, even in unseen spaces. This is ideal for researchers or developers creating autonomous systems that need to understand and execute complex verbal commands without prior training in specific environments.
No commits in the last 6 months.
Use this if you need to guide robots through detailed 3D environments using natural language instructions, especially in scenarios where pre-training for every new space isn't feasible.
Not ideal if your robot navigation tasks involve simple, repetitive movements in well-mapped, static environments or if you are not working with sophisticated 3D visual input.
Stars
64
Forks
1
Language
—
License
—
Category
Last pushed
Sep 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/bagh2178/GC-VLN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
KimMeen/Time-LLM
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming...
om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
bytedance/SALMONN
SALMONN family: A suite of advanced multi-modal LLMs
NVlabs/OmniVinci
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
fixie-ai/ultravox
A fast multimodal LLM for real-time voice