mlsanityData to 7 Oct 2026

Learned Visual Navigation for Under-Canopy Agricultural Robots

arXiv 2107.02792 ↗First posted 6 Jul 2021cs.RO cs.AI cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

We describe a system for visually guided autonomous navigation of under-canopy farm robots. Low-cost under-canopy robots can drive between crop rows under the plant canopy and accomplish tasks that are infeasible for over-the-canopy drones or larger agricultural equipment. However, autonomously navigating them under the canopy presents a number of challenges: unreliable GPS and LiDAR, high cost of sensing, challenging farm terrain, clutter due to leaves and weeds, and large variability in appearance over the season and across crop types. We address these challenges by building a modular system that leverages machine learning for robust and generalizable perception from monocular RGB images from low-cost cameras, and model predictive control for accurate control in challenging terrain. Our system, CropFollow, is able to autonomously drive 485 meters per intervention on average, outperforming a state-of-the-art LiDAR based system (286 meters per intervention) in extensive field testing spanning over 25 km.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 28 of its 75 references that are in the map. First posted on arXiv 6 Jul 2021.

Builds on

28 of 75 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016End to End Learning for Self-Driving Carscited by 1,000
  4. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  5. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  6. 2017VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimatorcited by 418
  7. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 352
  8. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
  9. 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 229
  10. 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 227
  11. 2017Cognitive Mapping and Planning for Visual Navigationcited by 209
  12. 2018Towards End-to-End Lane Detection: an Instance Segmentation Approachcited by 129
16 more
  1. 2020BADGR: An Autonomous Self-Supervised Learning-Based Navigation Systemcited by 97
  2. 2018Driving Policy Transfer via Modularity and Abstractioncited by 91
  3. 2020Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysiscited by 61
  4. 2019Combining Optimal Control and Learning for Visual Navigation in Novel Environmentscited by 50
  5. 2019Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networkscited by 41
  6. 2019Scaling Local Control to Large-Scale Topological Navigationcited by 37
  7. 2017Learning to Fly by Crashingcited by 33
  8. 2020Integrating Egocentric Localization for More Realistic Point-Goal Navigation Agentscited by 27
  9. 2018Visual Memory for Robust Path Followingcited by 16
  10. 2020Learning to Move with Affordance Mapscited by 15
  11. 2018The Rosario Dataset: Multisensor Data for Localization and Mapping in Agricultural Environmentscited by 10
  12. 2017Deep Steering: Learning End-to-End Driving Model from Spatial and Temporal Visual Cuescited by 9
  13. 2020Local Motion Planner for Autonomous Navigation in Vineyards with a RGB-D Camera-Based Algorithm and Deep Learning Synergycited by 8
  14. 2021Multi-Sensor Fusion based Robust Row Following for Compact Agricultural Robotscited by 6
  15. 2021High Precision Control of Tracked Field Robots in the Presence of Unknown Traction Coefficientscited by 2
  16. 2019Design and Construction of Unmanned Ground Vehicles for Sub-Canopy Plant Phenotypingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 3; 2023: 2; 2024: 5; 2025: 3; 2026: 3.

18 papers.

Sort:

By area:

  1. 2022WayFAST: Navigation with Predictive Traversability in the Fieldcited by 30
  2. 2022Proactive Anomaly Detection for Robot Navigation with Multi-Sensor Fusioncited by 15
  3. 2021Towards agricultural autonomy: crop row detection under varying field conditions using deep learningcited by 4
  4. 2023Vision-based Vineyard Navigation Solution with Automatic Annotationcited by 4
  5. 2024Fed-EC: Bandwidth-Efficient Clustering-Based Federated Learning For Autonomous Visual Robot Navigationcited by 4
  6. 2022Towards Infield Navigation: leveraging simulated data for crop row detectioncited by 3
  7. 2024Lessons from Deploying CropFollow++: Under-Canopy Agricultural Navigation with Keypointscited by 3
  8. 2021A Deep Learning Driven Algorithmic Pipeline for Autonomous Navigation in Row-Based Cropscited by 2
  9. 2023Push Past Green: Learning to Look Behind Plant Foliage by Moving Itcited by 2
  10. 2025ZeST: an VLM-based Zero-Shot Traversability Navigation for Unknown Environmentscited by 2
  11. 2024RowDetr: End-to-End Crop Row Detection Using Polynomialscited by 1
  12. 2025End-to-End Crop Row Navigation via LiDAR-Based Deep Reinforcement Learningcited by 1
6 more
  1. 2024Spannotation: Enhancing Semantic Segmentation for Autonomous Navigation with Efficient Image Annotationcited by 0
  2. 2024Towards Real-Time Generation of Delay-Compensated Video Feeds for Outdoor Mobile Robot Teleoperationcited by 0
  3. 2025CA-Cut: Crop-Aligned Cutout for Data Augmentation to Learn More Robust Under-Canopy Navigationcited by 0
  4. 2026LeCropFollow: Latent Space Planning for Navigation in Unstructured Crop Fieldscited by 0
  5. 2026Autonomous Agricultural Tractor: Integrated Weed Detection and LiDAR Navigation for Precision Paddy Farmingcited by 0
  6. 2026ObstaDiff: Generalizable Diffusion Policy Learning via Obstacle-aware Representationscited by 0