用元学习实现小样本自适应，让机器人在不同农田间快速导航
MetaCropFollow: Few-Shot Adaptation with Meta-Learning for Under-Canopy Navigation
- 基于关键点的视觉导航+元学习，快速适应新农田环境
- 仅需少量数据即可完成域适应，提升低数据场景下导航鲁棒性
- 适合农业机器人在复杂多变田间环境部署使用
自主农田内导航相比地表以上环境面临更多挑战，如作物行间距狭窄、GPS定位精度下降及环境杂乱等。基于关键点的视觉导航在该场景中表现良好，但不同农业环境在光照、季节、土壤和作物类型上的差异可能导致显著域偏移。本文探索利用元学习，在极少量数据条件下克服这种域偏移。通过训练一个基础学习器，使其能够快速适应新环境，从而在低数据条件下实现更稳健的导航性能。
原文摘要 · Abstract (English)
Autonomous under-canopy navigation faces additional challenges compared to over-canopy settings - for example the tight spacing between the crop rows, degraded GPS accuracy and excessive clutter. Keypoint-based visual navigation has been shown to perform well in these conditions, however the differences between agricultural environments in terms of lighting, season, soil and crop type mean that a domain shift will likely be encountered at some point of the robot deployment. In this paper, we explore the use of Meta-Learning to overcome this domain shift using a minimal amount of data. We train a base-learner that can quickly adapt to new conditions, enabling more robust navigation in low-data regimes.
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。