Learned Visual Navigation for Under-Canopy Agricultural Robots

Abstract

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.

arXiv commentRSS 2021. Project website with data and videos: https://ansivakumar.github.io/learned-visual-navigation/

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• ORB-SLAM: a Versatile and Accurate Monocular SLAM System
• VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator
• End to End Learning for Self-Driving Cars
• Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks
• Driving Policy Transfer via Modularity and Abstraction
• Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
• Deep Steering: Learning End-to-End Driving Model from Spatial and Temporal Visual Cues
• Local Motion Planner for Autonomous Navigation in Vineyards with a RGB-D Camera-Based Algorithm and Deep Learning Synergy
• High Precision Control of Tracked Field Robots in the Presence of Unknown Traction Coefficients
• Combining Optimal Control and Learning for Visual Navigation in Novel Environments
• Multi-Sensor Fusion based Robust Row Following for Compact Agricultural Robots
• Visual Memory for Robust Path Following
• Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis
• Integrating Egocentric Localization for More Realistic Point-Goal Navigation Agents
• Scaling Local Control to Large-Scale Topological Navigation
• Design and Construction of Unmanned Ground Vehicles for Sub-Canopy Plant Phenotyping
• Road Segmentation Using CNN and Distributed LSTM

Cited by in corpus (6)

• WayFAST: Navigation with Predictive Traversability in the Field
• Verifying Controllers with Convolutional Neural Network-based Perception: A Case for Intelligible, Safe, and Precise Abstractions
• Deep Model Predictive Control with Stability Guarantees
• CropNav: a Framework for Autonomous Navigation in Real Farms
• Fed-EC: Bandwidth-Efficient Clustering-Based Federated Learning For Autonomous Visual Robot Navigation
• End-to-End Crop Row Navigation via LiDAR-Based Deep Reinforcement Learning