DevGRU: Depth-guided Visual Navigation using a Collision-aware Recurrent Model

2026-08-18

AI Summary

为解决视觉导航模型在复杂室内环境中的碰撞问题，提出DevGRU系统，利用深度图像和目标点生成避碰轨迹，显著提升导航性能。

Abstract

Existing visual navigation models often aim to develop foundation models that can generalize robot navigation across diverse platforms. However, many of these models are prone to collisions when deployed in complex indoor environments, particularly in structured layouts and narrow passages. To address this problem, we propose a depth image- and point-goal-conditioned navigation system, DevGRU. The proposed system employs an action predictor (AP) that generates collision-aware future trajectories, enabling effective avoidance of immediate obstacles. In conjunction with a collision predictor, the AP further compensates for errors accumulated in the goal pose estimation and proactively mitigates future deviations. To evaluate our method, we conducted experiments across nine different scenes and three state-of-the-art approaches - ViNT, NoMaD, and NavDP - as well as four additional variants of ViNT and NoMaD. In terms of navigation performance, DevGRU significantly outperforms ViNT and NoMaD by a large margin. In addition, the proposed model has a relatively small number of trainable parameters, resulting in the fastest inference time among the baselines, particularly outperforming NavDP by 7x in model size and 17x in inference time.

Problem

• visual navigation
• collision
• indoor environments
• structured layouts
• narrow passages

Innovation

• Depth-guided
• Collision-aware
• Action Predictor (AP)
• Navigation Performance
• Inference Time