Answers are grounded in this paper and cite their sources.
This approach integrates deep learning-based perception and fruit morphometrics to improve harvesting efficiency.
Conventional trajectory planning methods for robotic fruit harvesting mainly rely on static geometric heuristics and often overlook critical sensory and task-specific variables such as fruit morphology and end-effector compatibility. These limitations make traditional approaches less effective in real-world agricultural settings, where conditions are unpredictable and fruits require careful, adaptive handling. Moreover, most existing studies do not incorporate a Convolutional Neural Network (CNN) to detect confidence in the planning process, often treating perception and motion planning as isolated components rather than a unified system. To overcome these challenges, this study proposes a data-driven approach to trajectory optimization that integrates visual perception based on CNN confidence levels, gripper type with different actuation technologies, and fruit orientation, parameters that significantly influence harvesting efficiency. Two multivariate regression models were developed, one specifically for firm fruits such as oranges and the other for soft fruits such as strawberries. The models predict trajectory length using three input variables: CNN detection confidence, actuator type, which includes three-finger and two-finger grippers, and fruit orientation angles ranging from 50ᵒ-130ᵒ. The non-linear influence of orientation is captured through polynomial terms. A total of 46 experimental trials were conducted for each fruit type using a robotic platform under controlled conditions. The regression outputs revealed that CNN confidence strongly influenced trajectory length reduction, while orientation impacted strawberries more severely due to their delicate structure. The optimized A* planner, informed by regression coefficients, reduced trajectory lengths by 14% for oranges and 11% for strawberries compared to baseline trajectories. Positional accuracy also improved by 12% and 15%, respectively. The models achieved high predictive performance (R² = 0.89 and 0.82; RMSE = 3.2 cm and 4.7 cm for oranges and strawberries, respectively). These findings demonstrate that integrating statistical modeling with heuristic planning enhances spatial efficiency and motion reliability in autonomous fruit harvesting.
No takes yet. Share an insight, caveat, or question.
Zeeshan et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: