用深度图和目标点引导，让机器人避障导航更准更快
DevGRU: Depth-guided Visual Navigation using a Collision-aware Recurrent Model
- 结合深度图与目标点，用循环模型预测避障路径
- 在9个场景中显著优于现有方法，错误率更低
- 参数少、推理快，适合部署到资源受限设备
现有视觉导航模型虽具备跨平台泛化能力，但在复杂室内环境中易发生碰撞，尤其在结构化布局和狭窄通道中表现不佳。为此，我们提出一种基于深度图像和目标点条件的导航系统 DevGRU。该系统包含一个动作预测器（AP），可生成具有碰撞感知的未来轨迹，有效避开近处障碍物；同时结合碰撞预测模块，补偿目标位姿估计误差，提前规避潜在偏差。我们在九个不同场景下对方法进行了评估，对比了 ViNT、NoMaD、NavDP 三类先进方法及四种变体。结果表明，DevGRU 在导航性能上大幅超越基准模型；且模型参数量小，推理速度最快，相较 NavDP 模型规模缩小 7 倍，推理速度提升 17 倍。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。