Reflex-Based Open-Vocabulary Navigation without Prior Knowledge Using Omnidirectional Camera and Multiple Vision-Language Models
This approach simplifies robot navigation for applications requiring flexibility without prior setup, though it appears incremental as it builds on existing vision-language models.
The study tackled open-vocabulary robot navigation without prior knowledge by using an omnidirectional camera and multiple pre-trained vision-language models, eliminating the need for map construction or learning, and demonstrated its feasibility with experiments on the Fetch mobile robot.
Various robot navigation methods have been developed, but they are mainly based on Simultaneous Localization and Mapping (SLAM), reinforcement learning, etc., which require prior map construction or learning. In this study, we consider the simplest method that does not require any map construction or learning, and execute open-vocabulary navigation of robots without any prior knowledge to do this. We applied an omnidirectional camera and pre-trained vision-language models to the robot. The omnidirectional camera provides a uniform view of the surroundings, thus eliminating the need for complicated exploratory behaviors including trajectory generation. By applying multiple pre-trained vision-language models to this omnidirectional image and incorporating reflective behaviors, we show that navigation becomes simple and does not require any prior setup. Interesting properties and limitations of our method are discussed based on experiments with the mobile robot Fetch.