{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T03:24:35Z","timestamp":1790393075393,"version":"4.1.0"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T00:00:00Z","timestamp":1757548800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Automating shiitake mushroom picking is critical for modern agriculture, yet its biological traits hinder automation via target recognition, path planning, and precision challenges. Traditional manual picking is inefficient, labor-heavy, and unsuitable for large-scale production. In human- robot collaboration, computer vision - based human motion prediction enables efficient picking coordination, yet methods like LSTM and static graph networks struggle with robust spatiotemporal correlation capture and long-term stability in complex agricultural settings.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To address this, we propose the Chaos-Optimized Adaptive Spatiotemporal Graph Convolutional Network (CSO-ASTGCN). First, it integrates three core modules: the Adaptive Spatial Feature Graph Convolution Module (ASF-GCN) for dynamic joint correlation modeling (e.g., wrist-finger coupling during grasping). Second, the Dynamic Temporal Feature Graph Convolution Module (DT-GCN) captures multi-scale temporal dependencies. Third, Chaos Search Optimization (CSO) globally optimizes hyper parameters to avoid local optima common in traditional optimization methods. Additionally, a flexible control system fuses CSO-ASTGCN motion prediction with GRCNN grasp pose estimation to optimize grasping paths and operational forces.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Experiments show our model reduces the Mean Per - Joint Position Error (MPJPE) by 15.2% on the CMU dataset and 12.7% on the 3DPW dataset compared to methods like STSGCN and Transformers. The human - robot collaborative system boosts picking efficiency by 31% and cuts mushroom damage by 26% relative to manual operations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>These results validate CSO - ASTGCN\u2019s superiority in spatiotemporal modeling for fine - grained agricultural motions and its practical value in intelligent edible fungi harvesting.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fpls.2025.1665352","type":"journal-article","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T05:26:02Z","timestamp":1757568362000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Research on the method of shiitake mushroom picking robot based on CSO-ASTGCN human action prediction network"],"prefix":"10.3389","volume":"16","author":[{"given":"Daojin","family":"Yao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zichen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanxin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiong","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,11]]},"reference":[{"key":"B1","first-page":"13452","article-title":"End-to-end trainable deep neural network for robotic grasp detection and semantic segmentation from RGB","author":"Ainetter","year":"2021"},{"key":"B2","first-page":"1","article-title":"Attention mechanism for human motion prediction","author":"Al-aqel","year":"2020"},{"key":"B3","doi-asserted-by":"publisher","first-page":"72526","DOI":"10.1109\/ACCESS.2025.3564032","article-title":"A novel LSTM architecture for automatic modulation recognition: Comparative analysis with conventional machine learning and RNN-based approaches","volume":"13","author":"Ansari","year":"2025","journal-title":"IEEE Access"},{"key":"B4","first-page":"226","article-title":"Learning progressive joint propagation for human motion prediction","author":"Cai","year":"2020"},{"key":"B5","volume-title":"Research on pedestrian intention and trajectory prediction methods based on multi-feature fusion","author":"Cao","year":"2025"},{"key":"B6","volume-title":"Human motion trajectory prediction integrating skeletal coupling in human-robot collaboration","author":"Chen","year":"2025"},{"key":"B7","first-page":"6519","article-title":"Learning dynamic relationships for 3D human motion prediction","author":"Cui","year":"2020"},{"key":"B8","first-page":"11467","article-title":"MSR-GCN: Multi-scale residual graph convolution networks for human motion prediction","author":"Dang","year":"2021"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.11975\/j.issn.1002-6819.202503181","article-title":"Recognition and localization method of tomato picking robot based on improved YOLOv8s and RGB-D information fusion","volume":"41","author":"Fan","year":"2025","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"B10","doi-asserted-by":"publisher","first-page":"14273","DOI":"10.1109\/TNNLS.2023.3277476","article-title":"Learning constrained dynamic correlations in spatiotemporal graphs for motion prediction","volume":"35","author":"Fu","year":"2023","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"B11","first-page":"4809","article-title":"Back to mlp: A simple baseline for human motion prediction","author":"Guo","year":"2023"},{"key":"B12","first-page":"2580","article-title":"Human motion prediction via learning local structure representations and temporal dependencies","author":"Guo","year":"2019"},{"key":"B13","first-page":"13713","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"},{"key":"B14","first-page":"1314","article-title":"Efficient nonlinear Markov models for human motion","author":"Lehrmann","year":"2014"},{"key":"B15","first-page":"5226","article-title":"Convolutional sequence-to-sequence model for human dynamics","author":"Li","year":"2018"},{"key":"B16","doi-asserted-by":"publisher","first-page":"182","DOI":"10.11975\/j.issn.1002-6819.202303022","article-title":"Recognizing fruiting body growth period of Lentinus edodes using improved YOLOv5","volume":"40","author":"Lin","year":"2024","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"B17","doi-asserted-by":"publisher","first-page":"14","DOI":"10.19998\/j.cnki.2095-1795.202506303","article-title":"Current situation and trends of agricultural robot technology development","volume":"15","author":"Liu","year":"2025","journal-title":"Agric. Eng."},{"key":"B18","first-page":"2133","article-title":"TrajectoryCNN: A new spatio-temporal feature learning network for human motion prediction","volume-title":"IEEE Transactions on Circuits and Systems for Video Technology","author":"Liu","year":"2020"},{"key":"B19","first-page":"9489","article-title":"Learning trajectory dependencies for human motion prediction","author":"Mao","year":"2019"},{"key":"B20","first-page":"2891","article-title":"On human motion prediction using recurrent neural networks","author":"Martinez","year":"2017"},{"key":"B21","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1177\/0278364919859066","article-title":"Learning robust, real-time, reactive robotic grasping","volume":"39","author":"Morrison","year":"2020","journal-title":"Int. J. Robot. Res."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.3724\/SP.J.1089.2019.17354","article-title":"Human action prediction based on bidirectional GRU and attention mechanism model","volume":"31","author":"Sang","year":"2019","journal-title":"J. Computer-Aided Design Comput. Graphics"},{"key":"B23","first-page":"11209","article-title":"Space-time-separable graph convolutional network for pose forecasting","author":"Sofianos","year":"2021"},{"key":"B24","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1109\/CVPR.2010.5540157","article-title":"Dynamical binary latent variable models for 3D human pose tracking","volume-title":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","author":"Taylor","year":"2010"},{"key":"B25","first-page":"601","article-title":"Recovering accurate 3D human pose in the wild using IMUs and a moving camera","author":"Von Marcard","year":"2018"},{"key":"B26","volume-title":"GGMotion: Group Graph Dynamics-Kinematics Networks for Human Motion Prediction. arXiv preprint arXiv:2507.07515 [Preprint]","author":"Wan","year":"2025"},{"key":"B27","doi-asserted-by":"publisher","first-page":"19","DOI":"10.19998\/j.cnki.2095-1795.2022.09.004","article-title":"Configuration scheme of full-process mechanized equipment for Lentinus edodes production","volume":"12","author":"Wang","year":"2022","journal-title":"J. Agric. Eng."},{"key":"B28","doi-asserted-by":"publisher","first-page":"150","DOI":"10.3969\/j.issn.1000-1212.2025.06.030","article-title":"Design and application of intelligent blueberry picking robot","volume":"56","author":"Wang","year":"2025","journal-title":"Eng. Machinery"},{"key":"B29","doi-asserted-by":"publisher","first-page":"8170","DOI":"10.1109\/LRA.2022.3187261","article-title":"When transformer meets robotic grasping: Exploits context for efficient grasp detection","volume":"7","author":"Wang","year":"2022","journal-title":"IEEE Robot. Automation Lett."},{"key":"B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.12133\/j.smartag.SA202505008","article-title":"Embodied intelligent agricultural robots: Key technologies, application analysis, challenges and prospects","author":"Wei","year":"2025","journal-title":"Smart Agric. (Chinese English)"},{"key":"B31","first-page":"9509","article-title":"Auxiliary tasks benefit 3D skeleton-based human motion prediction","author":"Xu","year":"2023"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1566","DOI":"10.1109\/TRO.2024.3353484","article-title":"Attribute-based robotic grasping with data-efficient adaptation","volume":"40","author":"Yang","year":"2024","journal-title":"IEEE Trans. Robot."},{"key":"B33","doi-asserted-by":"publisher","first-page":"110449","DOI":"10.1016\/j.compag.2025.110449","article-title":"Improved DeepLabV3+ and GR-ConvNet for shiitake mushroom harvest robots\u2019 flexible grasping of mimicry","volume":"236","author":"Yin","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B34","doi-asserted-by":"publisher","first-page":"4768","DOI":"10.1109\/TASE.2023.3301657","article-title":"Lightweight multiscale spatiotemporal locally connected graph convolutional networks for single human motion forecasting","volume":"21","author":"Zhai","year":"2023","journal-title":"IEEE Trans. Automation Sci. Eng."},{"key":"B35","doi-asserted-by":"publisher","first-page":"30","DOI":"10.11896\/j.issn.1002-137X.2019.03.004","article-title":"A review of grey wolf optimization algorithm","volume":"46","author":"Zhang","year":"2019","journal-title":"Comput. Sci."},{"key":"B36","volume-title":"Research on pepper recognition and picking technology based on deep learning","author":"Zhou","year":"2025"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1665352\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T05:26:10Z","timestamp":1757568370000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1665352\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,11]]},"references-count":36,"alternative-id":["10.3389\/fpls.2025.1665352"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2025.1665352","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,11]]},"article-number":"1665352"}}