{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T14:16:16Z","timestamp":1776694576682,"version":"3.51.2"},"reference-count":41,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T00:00:00Z","timestamp":1762473600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Special Project of the Department of Education of Shaanxi Province","award":["24JK0551"],"award-info":[{"award-number":["24JK0551"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Underground coal mine conveying systems operate in unstructured environments. Influenced by geological and operational factors, coal conveyors are frequently contaminated by foreign objects such as coal gangue and anchor bolts. These contaminants disrupt conveying stability and pose challenges to safe mining operations, making their effective removal critical. Given the significant heterogeneity and unpredictability of these objects in shape, size, and orientation, precise manipulation requires dual-arm cooperative control. Traditional control algorithms rely on precise dynamic models and fixed parameters, lacking robustness in such unstructured environments. To address these challenges, this paper proposes a cooperative grasping method tailored for heterogeneous objects in unstructured environments. The MATD3 algorithm is employed to cooperatively perform dual-arm trajectory planning and grasping tasks. A multi-factor reward function is designed to accelerate convergence in continuous action spaces, optimize real-time grasping trajectories for foreign objects, and ensure stable robotic arm positioning. Furthermore, priority experience replay (PER) is integrated into the MATD3 framework to enhance experience utilization and accelerate convergence toward optimal policies. For slender objects, a sequential cooperative optimization strategy is developed to improve the stability and reliability of grasping and placement. Experimental results demonstrate that the P-MATD3 algorithm significantly improves grasping success rates and efficiency in unstructured environments. In single-arm tasks, compared to MATD3 and MADDPG, P-MATD3 increases grasping success rates by 7.1% and 9.94%, respectively, while reducing the number of steps required to reach the pre-grasping point by 11.44% and 12.77%. In dual-arm tasks, success rates increased by 5.58% and 9.84%, respectively, while step counts decreased by 11.6% and 18.92%. Robustness testing under Gaussian noise demonstrated that P-MATD3 maintains high stability even with varying noise intensities. Finally, ablation and comparative experiments comprehensively validated the proposed method\u2019s effectiveness in simulated environments.<\/jats:p>","DOI":"10.3390\/s25226824","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T14:55:15Z","timestamp":1762527315000},"page":"6824","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Research on a Cooperative Grasping Method for Heterogeneous Objects in Unstructured Scenarios of Mine Conveyor Belts Based on an Improved MATD3"],"prefix":"10.3390","volume":"25","author":[{"given":"Rui","family":"Gao","sequence":"first","affiliation":[{"name":"College of Electrical and Control Engineering, Xi\u2019an University of Science and Technology, Xi\u2019an 710054, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengcong","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electrical and Control Engineering, Xi\u2019an University of Science and Technology, Xi\u2019an 710054, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyi","family":"Du","sequence":"additional","affiliation":[{"name":"College of Electrical and Control Engineering, Xi\u2019an University of Science and Technology, Xi\u2019an 710054, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Bao","sequence":"additional","affiliation":[{"name":"College of Electrical and Control Engineering, Xi\u2019an University of Science and Technology, Xi\u2019an 710054, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xudong","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Mechanical Engineering, Xi\u2019an University of Science and Technology, Xi\u2019an 710054, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahui","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Mechanical Engineering, Xi\u2019an University of Science and Technology, Xi\u2019an 710054, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,7]]},"reference":[{"key":"ref_1","unstructured":"Feng, Z., Xue, R., Yuan, L., Yu, Y., Ding, N., Liu, M., Gao, B., Sun, J., Zheng, X., and Wang, G. (2025). Multi-agent Embodied AI: Advances and Future Directions. arXiv."},{"key":"ref_2","first-page":"291","article-title":"On the Academic Ideology of \u201cSorting the Gangue is Sorting the Images\u201d","volume":"53","author":"Ma","year":"2025","journal-title":"Coal Sci. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.isatra.2022.09.007","article-title":"A Novel Model Predictive Artificial Potential Field Based Ship Motion Planning Method Considering COLREGs for Complex Encounter Scenarios","volume":"134","author":"He","year":"2022","journal-title":"ISA Trans."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1017\/S0263574723001546","article-title":"Obstacle Avoidance Path Planning of 6-DOF Robotic Arm Based on Improved A* Algorithm and Artificial Potential Field Method","volume":"42","author":"Tang","year":"2024","journal-title":"Robotica"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2461","DOI":"10.1109\/LRA.2021.3067310","article-title":"An Overall Configuration Planning Method of Continuum Hyper-Redundant Manipulators Based on Improved Artificial Potential Field Method","volume":"6","author":"Tian","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Xia, X., Li, T., Sang, S., Cheng, Y., Ma, H., Zhang, Q., and Yang, K. (2023). Path Planning for Obstacle Avoidance of Robot Arm Based on Improved Potential Field Method. Sensors, 23.","DOI":"10.3390\/s23073754"},{"key":"ref_7","first-page":"109210","article-title":"Robot Path Planning Based on Three-Dimensional Artificial Potential Field","volume":"135","author":"Lin","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_8","unstructured":"Fujimoto, S., van Hoof, H., and Meger, D. (2018, January 10\u201315). Addressing Function Approximation Error in Actor-Critic Methods. Proceedings of the 35th International Conference on Machine Learning, Stockholmsm\u00e4ssan, Stockholm, Sweden."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"V\u00f6lz, A., and Graichen, K. (2018, January 1\u20135). An Optimization-Based Approach to Dual-Arm Motion Planning with Closed Kinematics. Proceedings of the 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems, Madrid, Spain.","DOI":"10.1109\/IROS.2018.8593927"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hao, L., Zhu, X., Li, T., Sang, S., Cheng, Y., Ma, H., Zhang, Q., and Yang, K. (2022). An Improved Path Planning Algorithm Based on Artificial Potential Field and Primal-Dual Neural Network for Surgical Robot. Comput. Methods Programs Biomed., 226.","DOI":"10.1016\/j.cmpb.2022.107202"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.tra.2019.01.010","article-title":"Driving Aggressiveness Management Policy to Enhance the Performance of Mixed Traffic Conditions in Automated Driving Environments","volume":"121","author":"Lee","year":"2019","journal-title":"Transp. Res. Part A Policy Pract."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1729881418799562","DOI":"10.1177\/1729881418799562","article-title":"An Improved Artificial Potential Field Method of Trajectory Planning and Obstacle Avoidance for Redundant Manipulators","volume":"15","author":"Wang","year":"2018","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lu, X., Welleck, S., West, P., Jiang, L., Kasai, J., Khashabi, D., Le Bras, R., Qin, L., Yu, Y., and Zellers, R. (2022, January 10\u201315). NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Seattle, WA, USA.","DOI":"10.18653\/v1\/2022.naacl-main.57"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1109\/TEVC.2018.2878221","article-title":"ACO-A*: Ant Colony Optimization Plus A* for 3-D Traveling in Environments With Dense Obstacles","volume":"23","author":"Yu","year":"2019","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"147827","DOI":"10.1109\/ACCESS.2020.3015976","article-title":"Surface Optimal Path Planning Using an Extended Dijkstra Algorithm","volume":"8","author":"Luo","year":"2020","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.eswa.2018.08.008","article-title":"Multi-objective Multi-robot Path Planning in Continuous Environment Using an Enhanced Genetic Algorithm","volume":"115","author":"Nazarahari","year":"2018","journal-title":"Expert Syst. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2776","DOI":"10.3934\/mbe.2023130","article-title":"Robotic Arm Trajectory Optimization Based on Multiverse Algorithm","volume":"20","author":"Liu","year":"2022","journal-title":"Math. Biosci. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"106099","DOI":"10.1016\/j.engappai.2023.106099","article-title":"Trajectory Planning for a 6-Axis Robotic Arm with Particle Swarm Optimization Algorithm","volume":"122","author":"Ekrem","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ma, H., Wei, X., Wang, P., Zhang, Y., Cao, X., and Zhou, W. (2022). Multi-Arm Global Cooperative Coal Gangue Sorting Method Based on Improved Hungarian Algorithm. Sensors, 22.","DOI":"10.3390\/s22207987"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1109\/TASE.2020.2976560","article-title":"Neural RRT*: Learning-Based Optimal Path Planning","volume":"17","author":"Wang","year":"2020","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_21","first-page":"e27235","article-title":"BI-RRT*: An Improved Path Planning Algorithm for Secure and Trustworthy Mobile Robots Systems","volume":"10","author":"Fan","year":"2024","journal-title":"Heliyon"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.eswa.2019.01.032","article-title":"Quick-RRT*: Triangular Inequality-Based Implementation of RRT* with Improved Initial Solution and Convergence Rate","volume":"123","author":"Jeong","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"7244","DOI":"10.1109\/TIE.2020.2998740","article-title":"MOD-RRT*: A Sampling-Based Algorithm for Robot Path Planning in Dynamic Environment","volume":"68","author":"Qi","year":"2021","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"115457","DOI":"10.1016\/j.eswa.2021.115457","article-title":"F-RRT*: An Improved Path Planning Algorithm with Improved Initial Solution and Convergence Rate","volume":"184","author":"Liao","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"108362","DOI":"10.1016\/j.engappai.2024.108362","article-title":"HB-RRT: A Path Planning Algorithm for Mobile Robots Using Halton Sequence-Based Rapidly-Exploring Random Tree","volume":"133","author":"Zhong","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"10970","DOI":"10.1109\/JSEN.2022.3232088","article-title":"Dynamic Parallel Mapping and Trajectory Planning of Robot Arm in Unknown Environment","volume":"23","author":"Wang","year":"2023","journal-title":"IEEE Sens. J."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Su, C., and Xu, J. (2022). A Sampling-Based Unfixed Orientation Search Method for Dual Manipulator Cooperative Manufacturing. Sensors, 22.","DOI":"10.3390\/s22072502"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"3299","DOI":"10.1007\/s00170-022-08809-w","article-title":"A Novel Non-Collision Path Planning Strategy for Multi-Manipulator Cooperative Manufacturing Systems","volume":"120","author":"Su","year":"2022","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/j.neunet.2022.03.037","article-title":"Deep Learning, Reinforcement Learning, and World Models","volume":"152","author":"Matsuo","year":"2022","journal-title":"Neural Netw."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3215","DOI":"10.1007\/s10462-020-09938-y","article-title":"A Survey on Multi-Agent Deep Reinforcement Learning: From the Perspective of Challenges and Applications","volume":"54","author":"Du","year":"2021","journal-title":"Artif. Intell. Rev."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"15051","DOI":"10.1109\/TNNLS.2023.3283523","article-title":"Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive Review of Algorithms and Applications","volume":"35","author":"Munikoti","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1109\/TASE.2024.3352584","article-title":"A Task-Adaptive Deep Reinforcement Learning Framework for Dual-Arm Robot Manipulation","volume":"22","author":"Cui","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.neucom.2020.04.028","article-title":"MRCDRL: Multi-Robot Coordination with Deep Reinforcement Learning","volume":"406","author":"Wang","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_34","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., and Levine, S. (2018, January 10\u201315). Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Prianto, E., Kim, M., Park, J.-H., Bae, J.-H., and Kim, J.-S. (2020). Path Planning for Multi-Arm Manipulators Using Deep Reinforcement Learning: Soft Actor\u2013Critic with Hindsight Experience Replay. Sensors, 20.","DOI":"10.3390\/s20205911"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Tang, W., Cheng, C., Ai, H., and Chen, L. (2022). Dual-Arm Robot Trajectory Planning Based on Deep Reinforcement Learning under Complex Environment. Micromachines, 13.","DOI":"10.3390\/mi13040564"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"04021087","DOI":"10.1061\/(ASCE)AS.1943-5525.0001335","article-title":"Coordinated Control Based on Reinforcement Learning for Dual-Arm Continuum Manipulators in Space Capture Missions","volume":"34","author":"Jiang","year":"2021","journal-title":"J. Aerosp. Eng."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"102644","DOI":"10.1016\/j.rcim.2023.102644","article-title":"A Novel Robotic Grasping Method for Moving Objects Based on Multi-Agent Deep Reinforcement Learning","volume":"86","author":"Huang","year":"2024","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1174","DOI":"10.1109\/LRA.2021.3138545","article-title":"Multifingered Grasping Based on Multimodal Reinforcement Learning","volume":"7","author":"Liang","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"12098","DOI":"10.1109\/TPAMI.2023.3283537","article-title":"MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making with Deep Reinforcement Learning","volume":"45","author":"Hu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"eaao4900","DOI":"10.1126\/scirobotics.aao4900","article-title":"Vision-based Grasp Learning of an Anthropomorphic Hand-arm System in a Synergy-based Control Framework","volume":"4","author":"Ficuciello","year":"2019","journal-title":"Sci. Robot."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/6824\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T05:20:12Z","timestamp":1762838412000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/6824"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,7]]},"references-count":41,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["s25226824"],"URL":"https:\/\/doi.org\/10.3390\/s25226824","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,7]]}}}