Receding-Horizon Next-Best-View Planner for Autonomous Leaf Surface Reconstruction

2026-07-30

AI Summary

This work addresses the challenge of high-fidelity reconstruction of plant leaf surfaces in resource-constrained field environments by proposing a receding-horizon next-best-view (NBV) planning approach. The method introduces a centroid-based information gain function to quantify view utility and integrates multi-step lookahead reasoning to optimize the robot’s observation trajectory, effectively balancing computational efficiency with reconstruction quality while mitigating inter-leaf occlusions. Experimental results on strawberry plants across multiple growth stages demonstrate that the proposed approach significantly reduces surface reconstruction error and enhances geometric fidelity, achieving up to a 10% improvement in reconstruction accuracy over baseline methods.

Abstract

Accurate plant leaf modeling is fundamental to downstream tasks such as plant growth monitoring, and phenotyping for yield estimation. Autonomous robotic reconstruction for large-scale field deployment must address limitations on robot planning budget and computation resources while optimizing viewpoint utility for leaf surface reconstruction. Existing approaches either focus on rigid objects, point-cloud coverage or plant reconstruction without fully addressing the system limitations or exploiting task-driven point cloud utility. In this work, we study next-best-view (NBV) planning for leaf surface reconstruction under travel constraints. We develop a novel Centroid-based Information Gain (CIG) function that measures the spatial distribution of observed points relative to the centroid of the existing point cloud to compute viewpoint utility. We also develop a receding-horizon variant that reasons over future viewpoints. To benchmark our work, we use the LAST-STRAW [1] public dataset that includes point clouds of strawberry plants over different growth stages and compare our method with attention-driven NBV [2] that uses a visibility-based information gain approach. The proposed receding-horizon approach consistently reduces surface reconstruction error and improves geometric fidelity across multiple growth stages, especially under increased inter-leaf occlusion. Results demonstrate that our approach is able to visit viewpoints that reduce surface reconstruction error and improves reconstruc-tion accuracy as compared to the baseline by upto 10%.

Problem

• next-best-view planning
• leaf surface reconstruction
• autonomous robotic reconstruction
• viewpoint utility
• travel constraints

Innovation

• Next-Best-View planning
• Centroid-based Information Gain
• receding-horizon planning
• leaf surface reconstruction
• autonomous robotic perception