Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs

Zhuo Xu, Hao-Tien Lewis Chiang, Zipeng Fu, Mithun George Jacob, Tingnan Zhang, Tsang-Wei Edward Lee, Wenhao Yu, Connor Schenck, David Rendleman, Dhruv Shah, Fei Xia, Jasmine Hsu, Jonathan Hoech, Pete Florence, Sean Kirmani, Sumeet Singh, Vikas Sindhwani, Carolina Parada, Chelsea Finn, Peng Xu et al. (2 additional authors not shown)

Keywords: vision-language navigation, multimodal foundation models, long-context reasoning

TL;DR: long context VLM unlocks unprecedented capability for multimodal instruction guided navigation

Abstract: An elusive goal in navigation research is to build an intelligent agent that can understand multimodal instructions including natural language and image, and perform useful navigation. To achieve this, we study a widely useful category of navigation tasks we call Multimodal Instruction Navigation with demonstration Tours (MINT), in which the environment prior is provided through a previously recorded demonstration video. Recent advances in Vision Language Models (VLMs) have shown a promising path in achieving this goal as it demonstrates capabilities in perceiving and reasoning about multimodal inputs. However, VLMs are typically trained to predict textual output and it is an open research question about how to best utilize them in navigation. To solve MINT, we present Mobility VLA, a hierarchical Vision-Language-Action (VLA) navigation policy that combines the environment understanding and common sense reasoning power of long-context VLMs and a robust low-level navigation policy based on topological graphs. The high-level policy consists of a long-context VLM that takes the demonstration tour video and the multimodal user instruction as input to find the goal frame in the tour video. Next, a low-level policy uses the goal frame and an offline constructed topological graph to generate robot actions at every timestep. We evaluated Mobility VLA in a 836$m^2$ real world environment and show that Mobility VLA has a high end-to-end success rates on previously unsolved multimodal instructions such as ``Where should I return this?'' while holding a plastic bin.

Student Paper: yes

Submission Number: 440