Kento Kawaharazuka / 河原塚 健人 (@KKawaharazuka)
2024-08-22 | ❤️ 92 | 🔁 14
Our new paper “Reflex-Based Open-Vocabulary Navigation without Prior Knowledge Using Omnidirectional Camera and Multiple Vision-Language Models” has been accepted at Advanced Robotics!
website - https://haraduka.github.io/omnidirectional-vlm/ https://x.com/KKawaharazuka/status/1826549893235626175/video/1
미디어
Tags
domain-robotics domain-ai-ml domain-llm domain-vlm domain-web-graphics