AdaCropFollow: Self-Supervised Online Adaptation for Visual Under-Canopy Navigation
Under-canopy agricultural robots can enable various applications like precise monitoring, spraying, weeding, and plant manipulation tasks throughout the growing season. Autonomous navigation under the canopy is challenging due to the degradation in accuracy of RTK-GPS and the large variability in the visual appearance of the scene over time. In prior work, we developed a supervised learning-based perception system with semantic keypoint representation and deployed this in various field conditions. A large number of failures of this system can be attributed to the inability of the perception model to adapt to the domain shift encountered during deployment. In this paper, we propose a self-supervised online adaptation method for adapting the semantic keypoint representation using a visual foundational model, geometric prior, and pseudo labeling. Our preliminary experiments show that with minimal data and fine-tuning of parameters, the keypoint prediction model trained with labels on the source domain can be adapted in a self-supervised manner to various challenging target domains onboard the robot computer using our method. This can enable fully autonomous row-following capability in under-canopy robots across fields and crops without requiring human intervention.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous NavigationSimilar Papers 제목 키워드 기반
Generalizing to the Open World: Deep Visual Odometry with Online Adaptation
Despite learning-based visual odometry (VO) has shown impressive results in recent years, the pretrained networks may easily collapse in unseen environments. The large domain gap between training and testing data makes t…
Bayesian InferenceDepth EstimationOptical Flow EstimationPose Estimation+1An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World
Recently, learning-based robotic navigation systems have gained extensive research attention and made significant progress. However, the diversity of open-world scenarios poses a major challenge for the generalization of…
Depth EstimationMonocular Depth EstimationMonocular Visual OdometryPose Estimation+3Self-Supervised Deep Visual Odometry with Online Adaptation
Self-supervised VO methods have shown great success in jointly estimating camera pose and depth from videos. However, like most data-driven methods, existing VO networks suffer from a notable decrease in performance when…
Meta-LearningVisual OdometryORB-SfMLearner: ORB-Guided Self-supervised Visual Odometry with Selective Online Adaptation
Deep visual odometry, despite extensive research, still faces limitations in accuracy and generalizability that prevent its broader application. To address these challenges, we propose an Oriented FAST and Rotated BRIEF …
Motion EstimationVisual OdometryOnline Adaptation via Dual-Stage Alignment and Self-Supervision for Fast-Calibration Brain-Computer Interfaces
Individual differences in brain activity hinder the online application of electroencephalogram (EEG)-based brain computer interface (BCI) systems. To overcome this limitation, this study proposes an online adaptation alg…