Visual Perception and Autonomous Navigation Control for Orchard Robots: From Scene Understanding to Closed-Loop Motion Execution.
- 1School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China.
- 2Key Laboratory of Plant Protection Engineering, Ministry of Agriculture and Rural Affairs, Jiangsu University, Zhenjiang 212013, China.
Abstract
Autonomous navigation is essential for orchard robots performing spraying, weeding, inspection, harvesting, and transport, yet semi-structured orchards combine repeatable tree-row geometry with canopy occlusion, uneven illumination, weak road boundaries, terrain variation, and intermittent global positioning. This review examines orchard visual navigation through a control-oriented chain of scene information, perception and localization, navigation-reference construction, motion execution, and closed-loop evaluation. Particular emphasis is placed on orchard-specific interfaces: repeated row geometry can stabilize reference extraction but can also create perceptual ambiguity; canopy occlusion can simultaneously degrade visual features and GNSS availability; and headland turning requires explicit switching among row following, turning, relocalization, and task resumption. Passable areas, tree-row/canopy structure, and obstacle/end-of-row semantics are compared according to the control variables they generate, including drivable corridors, lateral and heading errors, curvature, safety clearance, event states, and tracking targets. Traditional vision, deep-learning detection and segmentation, depth vision, visual SLAM, multi-sensor fusion, and path-tracking control are synthesized in terms of operating conditions, failure modes, and downstream control effects. The review further analyzes perception-to-control error propagation, end-to-end latency, cross-season generalization, and the mismatch between image metrics and field navigation performance. A unified perception-representation-localization-planning-control-evaluation framework and full-chain benchmark protocol are presented.
Related
- Robotic Fruit Harvesting Systems: Integration of Perception, Manipulation, and Detachment for Autonomous Harvesting
- Control of leaf shape through non-cell autonomous TCP4 regulation
- Distinct Roles of Working Memory and Inhibitory Control in Speech-in-Noise Perception
- Edge-deployable greenhouse tomato cluster harvesting robot integrating YOLOv8n-BiFPN-WIoU and ROS-based autonomous control
- QuImputer: an LD-informed QUBO/Ising formulation of genotype imputation with quantum-hardware execution
BibTeX
@article{wang2026visual,
title = {{Visual Perception and Autonomous Navigation Control for Orchard Robots: From Scene Understanding to Closed-Loop Motion Execution.}},
author = {Yunfei Wang and Xiang Dong and Zhenlei Zhang and Zhihao Zhang and Weidong Jia},
journal = {Sensors (Basel, Switzerland)},
year = {2026},
month = oct,
doi = {10.3390/s26206402},
url = {https://europepmc.org/article/MED/42944266},
note = {CC BY},
}
RIS
TY - JOUR
TI - Visual Perception and Autonomous Navigation Control for Orchard Robots: From Scene Understanding to Closed-Loop Motion Execution.
AU - Yunfei Wang
AU - Xiang Dong
AU - Zhenlei Zhang
AU - Zhihao Zhang
AU - Weidong Jia
PY - 2026
DA - 2026/10/10
JO - Sensors (Basel, Switzerland)
DO - 10.3390/s26206402
UR - https://europepmc.org/article/MED/42944266
AB - Autonomous navigation is essential for orchard robots performing spraying, weeding, inspection, harvesting, and transport, yet semi-structured orchards combine repeatable tree-row geometry with canopy occlusion, uneven illumination, weak road boundaries, terrain variation, and intermittent global positioning. This review examines orchard visual navigation through a control-oriented chain of scene information, perception and localization, navigation-reference construction, motion execution, and closed-loop evaluation. Particular emphasis is placed on orchard-specific interfaces: repeated row geometry can stabilize reference extraction but can also create perceptual ambiguity; canopy occlusion can simultaneously degrade visual features and GNSS availability; and headland turning requires explicit switching among row following, turning, relocalization, and task resumption. Passable areas, tree-row/canopy structure, and obstacle/end-of-row semantics are compared according to the control variables they generate, including drivable corridors, lateral and heading errors, curvature, safety clearance, event states, and tracking targets. Traditional vision, deep-learning detection and segmentation, depth vision, visual SLAM, multi-sensor fusion, and path-tracking control are synthesized in terms of operating conditions, failure modes, and downstream control effects. The review further analyzes perception-to-control error propagation, end-to-end latency, cross-season generalization, and the mismatch between image metrics and field navigation performance. A unified perception-representation-localization-planning-control-evaluation framework and full-chain benchmark protocol are presented.
SN - 1424-8220
ER -