让农业导航机器人记住走过的路，提升重复任务效率
SUM-AgriVLN: Spatial Understanding Memory for Agricultural Vision-and-Language Navigation
- 用3D重建理解空间，2D图像保存记忆
- 在A2A数据集上成功将导航成功率提至54%
- 适合需要重复巡检的智能农业场景
农业机器人正成为多种农事任务的重要助手，但目前仍严重依赖人工操作或固定轨道移动。A2A基准和AgriVLN方法首次将视觉语言导航（VLN）引入农业领域，使机器人能根据自然语言指令从起点导航至目标位置。然而我们发现：在实际农业场景中用户常给出重复指令，而AgriVLN将每条指令视为独立任务，忽略了利用过往空间记忆辅助当前决策的潜力。为此，我们提出SUM模块，通过3D重建实现空间理解，并以2D表征保存过去的空间记忆，帮助决策系统在当前场景中回忆历史空间特征。我们将该模块集成到AgriVLN主干网络中，构建了SUM-AgriVLN方法。在A2A数据集上的评估显示，其导航成功率（SR）从0.47提升至0.54，仅轻微牺牲路径误差（NE）由2.91米增至2.93米，达到农业视觉语言导航领域的最先进水平。
原文摘要 · Abstract (English)
Agricultural robots are emerging as powerful assistants across a wide range of agricultural tasks, nevertheless, they are still heavily relying on manual operations or fixed railways for movement. The A2A benchmark and the AgriVLN method pioneeringly extended Vision-and-Language Navigation (VLN) to the agricultural domain, successfully navigating agricultural robots from starting points to target positions following natural language instructions, while we observed a limitation: In practical agricultural scenarios, users often give repetitive instructions, but AgriVLN treats every instruction as an independent episode, overlooking the potential to use past spatial memories to assist present episodes. To address this limitation, we propose the SUM module, which executes spatial understanding via 3D reconstructions and saves spatial memories via 2D representations from the past, thereby assisting the decision-maker to recall the spatial characteristics of the scenes in the present. We integrate it into the AgriVLN backbone to build the SUM-AgriVLN method. When evaluated on A2A, it effectively improves SR from 0.47 to 0.54 with only slight sacrifice on NE from 2.91 m to 2.93 m, demonstrating the state-of-the-art performance in the agricultural VLN domain. Code: https://github.com/AlexTraveling/SUM-AgriVLN.
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。