Prasad Nethala

Current tomato harvesters rely primarily on external color as the sole indicator of ripeness. However, this approach often results in premature harvesting, leading to insufficient lycopene accumulation and a suboptimal nutritional content for human consumption. Such limitations are especially critical in controlled-environment agriculture (CEA) systems, where maximizing fruit quality and nutrient density is essential for both the yield and consumer health. To address that challenge, this study introduces a novel, multimodal harvest readiness framework tailored to nutrient film technology (NFT)-based smart farms. The proposed approach integrates plant-level stress diagnostics and fruit-level phenotyping using wearable biosensors, AI-assisted computer vision, and non-invasive physiological sensing. Key physiological markers—including the volatile organic compound (VOC) methanol, phytohormones salicylic acid (SA) and indole-3-acetic acid (IAA), and nutrients nitrate and ammonium concentrations—are combined with phenomic traits such as fruit color (a*), size, chlorophyll index (rGb), and water status. The innovation lies in a four-stage decision-making pipeline that filters physiologically stressed plants before selecting ripened fruits based on internal and external quality indicators. Experimental validation across four plant conditions (control, water-stressed, light-stressed, and wounded) demonstrated the efficacy of VOC and hormone sensors in identifying optimal harvest candidates. Additionally, the integration of low-cost electrochemical ion sensors provides scalable nutrient monitoring within NFT systems. This research delivers a robust, sensor-driven framework for autonomous, data-informed harvesting decisions in smart indoor agriculture. By fusing real-time physiological feedback with AI-enhanced phenotyping, the system advances precision harvest timing, improves fruit nutritional quality, and sets the foundation for resilient, feedback-controlled farming platforms suited to meeting global food security and sustainability demands.

This paper presents an extensive review of techniques for plant feature extraction and segmentation, addressing the growing need for efficient plant phenotyping, which is increasingly recognized as a critical application for remote sensing in agriculture. As understanding and quantifying plant structures become essential for advancing precision agriculture and crop management, this survey explores a range of methodologies, both traditional and cutting-edge, for extracting features from plant images and point cloud data, as well as segmenting plant organs. The importance of accurate plant phenotyping in remote sensing is underscored, given its role in improving crop monitoring, yield prediction, and stress detection. The review highlights the challenges posed by complex plant morphologies and data noise, evaluating the performance of various techniques and emphasizing their strengths and limitations. The insights from this survey offer valuable guidance for researchers and practitioners in plant phenotyping, advancing the fields of plant science and agriculture. The experimental section focuses on three key tasks: 3D point cloud generation, 2D image-based feature extraction, and 3D shape classification, feature extraction, and segmentation. Comparative results are presented using collected plant data and several publicly available datasets, along with insightful observations and inspiring directions for future research.

In this paper, a hierarchical reinforcement learning (HRL) architecture, namely a “Hierarchical Deep Deterministic Policy Gradient (HDDPG)” has been proposed and studied. A HDDPG utilizes manager and worker formation similar to other HRL structures. However, unlike others, the HDDPG enables sharing an identical environment and state among workers and managers, while a unique reward system is required for each Deep Deterministic Policy Gradient (DDPG) agent. Therefore, the HDDPG allows easy structural expansion with probabilistic action selection of a worker by the manager. Due to its innate structural advantage, the HDDPG has a merit in building a general AI to deal with a complex time-horizon tasks with various conflicting sub-goals. The experimental results demonstrated its usefulness with a manipulator motion planning problem in a dynamic environment, where path planning and collision avoidance conflict each other. The proposed HDDPG is compared with an HAM and a single DDPG for performance evaluation. The result shows that the HDDPG demonstrated more than 40% of reward gain and more than two times the reward improvement rate. Another important feature of the proposed HDDPG is the biased manager training capability. By adding a preference factor to each worker, the manager can be trained to prefer a certain worker to achieve better success rate for a specific objective if needed.