arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.13133cs.RO
收藏

DecoVLN:解耦观察、推理与修正以实现视觉-语言导航

DecoVLN: Decoupling Observation, Reasoning, and Correction for Vision-and-Language Navigation

Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Shandong University(山东大学)

Zihao Xin, Wentong Li, Yixuan Jiang, Bin Wang, Runmin Cong, Jie Qin, Shengjun Huang

AI总结:

DecoVLN通过优化长期记忆构建和修正策略,提升长周期导航的鲁棒性与稳定性,实验证明其在真实环境中的有效性。

摘要:

视觉-语言导航(VLN)要求智能体执行长周期指令并导航复杂3D环境。然而,现有方法面临两大挑战:构建有效长期记忆库和克服误差累积问题。为解决这些问题,我们提出DecoVLN框架,旨在实现稳健的流式感知和闭环控制。首先,我们将长期记忆构建表述为优化问题,并引入自适应细化机制,通过迭代优化统一评分函数选择历史候选池中的帧。该函数联合平衡三个关键标准:指令的语义相关性、所选记忆的视觉多样性以及历史轨迹的时间覆盖范围。其次,为缓解误差累积,我们引入状态-动作对级别的修正微调策略。通过利用状态之间的测地距离精确量化与专家轨迹的偏差,智能体在可信区域收集高质量的状态-动作对,同时过滤出相关性低的污染数据。这提高了误差修正的效率和稳定性。大量实验验证了DecoVLN的有效性,并已在真实环境中部署。

英文摘要:

Vision-and-Language Navigation (VLN) requires agents to follow long-horizon instructions and navigate complex 3D environments. However, existing approaches face two major challenges: constructing an effective long-term memory bank and overcoming the compounding errors problem. To address these issues, we propose DecoVLN, an effective framework designed for robust streaming perception and closed-loop control in long-horizon navigation. First, we formulate long-term memory construction as an optimization problem and introduce adaptive refinement mechanism that selects frames from a historical candidate pool by iteratively optimizing a unified scoring function. This function jointly balances three key criteria: semantic relevance to the instruction, visual diversity from the selected memory, and temporal coverage of the historical trajectory. Second, to alleviate compounding errors, we introduce a state-action pair-level corrective finetuning strategy. By leveraging geodesic distance between states to precisely quantify deviation from the expert trajectory, the agent collects high-quality state-action pairs in the trusted region while filtering out the polluted data with low relevance. This improves both the efficiency and stability of error correction. Extensive experiments demonstrate the effectiveness of DecoVLN, and we have deployed it in real-world environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑