Empowering Dynamic Urban Navigation with Stereo and Mid-Level Vision
This work addresses the problem of robust navigation in dynamic urban environments for robotics, offering a more data-efficient approach that is incremental by building on existing foundation models.
The paper tackles the inefficiency of relying solely on monocular vision in robot navigation foundation models by introducing StereoWalker, which integrates stereo inputs and mid-level vision modules like depth estimation and tracking. The result is that StereoWalker achieves comparable performance to state-of-the-art models with only 1.5% of training data and surpasses them with full data, while stereo vision also yields higher navigation performance than monocular input.
The success of foundation models in language and vision motivated research in fully end-to-end robot navigation foundation models (NFMs). NFMs directly map monocular visual input to control actions and ignore mid-level vision modules (tracking, depth estimation, etc) entirely. While the assumption that vision capabilities will emerge implicitly is compelling, it requires large amounts of pixel-to-action supervision that are difficult to obtain. The challenge is especially pronounced in dynamic and unstructured settings, where robust navigation requires precise geometric and dynamic understanding, while the depth-scale ambiguity in monocular views further limits accurate spatial reasoning. In this paper, we show that relying on monocular vision and ignoring mid-level vision priors is inefficient. We present StereoWalker, which augments NFMs with stereo inputs and explicit mid-level vision such as depth estimation and dense pixel tracking. Our intuition is straightforward: stereo inputs resolve the depth-scale ambiguity, and modern mid-level vision models provide reliable geometric and motion structure in dynamic scenes. We also curate a large stereo navigation dataset with automatic action annotation from Internet stereo videos to support training of StereoWalker and to facilitate future research. Through our experiments, we find that mid-level vision enables StereoWalker to achieve a comparable performance as the state-of-the-art using only 1.5% of the training data, and surpasses the state-of-the-art using the full data. We also observe that stereo vision yields higher navigation performance than monocular input.