Active Robotic Perception for Disease Detection and Mapping in Apple Trees

2026-03-24

AI Summary

This study addresses the challenges of delayed manual monitoring and low spatial resolution in detecting apple tree diseases—such as fire blight—in large-scale orchards. To overcome these limitations, the authors propose an autonomous mobile robot system that leverages active perception and multi-view planning to accurately localize disease symptoms and construct a 3D semantic map during the dormant season. The core innovations include a voxel-level 3D semantic mapping framework incorporating semantic confidence and an active viewpoint planning strategy guided by semantic uncertainty, which jointly optimizes geometric baselines, maximizes volumetric reduction of unknown space, and prioritizes low-confidence diseased regions. Experimental results demonstrate that in simulation, the semantic planner achieves an F1 score of 0.6106 after 30 viewpoints, with the voxel-based planner covering 85.82% of the region of interest; in laboratory conditions, the system attains an F1 score of 0.9058, significantly outperforming baseline methods.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Machine Learning: Active Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Large-scale orchard production requires timely and precise disease monitoring, yet routine manual scouting is labor-intensive and financially impractical at the scale of modern operations. As a result, disease outbreaks are often detected late and tracked at coarse spatial resolutions, typically at the orchard-block level. We present an autonomous mobile active perception system for targeted disease detection and mapping in dormant apple trees, demonstrated on one of the most devastating diseases affecting apple today -- fire blight. The system integrates flash-illuminated stereo RGB sensing, real-time depth estimation, instance-level segmentation, and confidence-aware semantic 3D mapping to achieve precise localization of disease symptoms. Semantic predictions are fused into the volumetric occupancy map representation enabling the tracking of both occupancy and per-voxel semantic confidence, building actionable spatial maps for growers. To actively refine observations within complex canopies, we evaluate three viewpoint planning strategies within a unified perception-action loop: a deterministic geometric baseline, a volumetric next-best-view planner that maximizes unknown-space reduction, and a semantic next-best-view planner that prioritizes low-confidence symptomatic regions. Experiments on a fabricated lab tree and five simulated symptomatic trees demonstrate reliable symptom localization and mapping as a precursor to a field evaluation. In simulation, the semantic planner achieves the highest F1 score (0.6106) after 30 viewpoints, while the volumetric planner achieves the highest ROI coverage (85.82\%). In the lab setting, the semantic planner attains the highest final F1 (0.9058), with both next-best-view planners substantially improving coverage over the baseline.

Problem

• disease detection
• apple trees
• fire blight
• spatial mapping
• orchard monitoring

Innovation

• active perception
• semantic 3D mapping
• next-best-view planning
• instance-level segmentation
• autonomous disease detection