{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:56:47Z","timestamp":1774540607791,"version":"3.50.1"},"reference-count":26,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T00:00:00Z","timestamp":1774483200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2024YFB4709105"],"award-info":[{"award-number":["2024YFB4709105"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Aiming at the problems of difficult hard-constraint enforcement and weak environmental generalization ability in the safe trajectory planning of manipulators in complex environments, a Policy-Guided Model Predictive Path Integral (PG-MPPI) planning framework is proposed. This framework integrates the advantages of reinforcement learning and model predictive control to construct a global prior guidance, local real-time optimization and hard-constraint safety assurance: a Constraint-Discounted Soft Actor\u2013Critic (CD-SAC) offline learning policy is designed, which incorporates the configuration-space distance field as a safety guidance term to realize the learning of obstacle avoidance behavior; the offline policy is used to guide the online sampling and optimization of MPPI, improving sampling efficiency and planning quality; and a Control Barrier Function (CBF) safety filter is introduced to revise control commands in real time, ensuring the strict satisfaction of constraints. Taking the SIASUN T12B manipulator as the research object, simulation comparison experiments are carried out in multi-obstacle scenarios. The results show that the PG-MPPI algorithm outperforms the comparison algorithms in the success rate of collision-free target reaching, ensures the smoothness and feasibility of the trajectory, and has a good adaptive capacity to complex environments with unknown obstacle configurations, thus providing an efficient solution for the autonomous and safe operation of manipulators.<\/jats:p>","DOI":"10.3390\/s26072074","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:10:24Z","timestamp":1774537824000},"page":"2074","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Policy-Guided Model Predictive Path Integral for Safe Manipulator Trajectory Planning"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1793-2229","authenticated-orcid":false,"given":"Liang","family":"Liang","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang 110819, China"},{"name":"SIASUN Robot & Automation Co., Ltd., Shenyang 110168, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9906-5493","authenticated-orcid":false,"given":"Chengdong","family":"Wu","sequence":"additional","affiliation":[{"name":"Faculty of Robot Science and Engineering, Northeastern University, Shenyang 110169, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4566-4532","authenticated-orcid":false,"given":"Xiaofeng","family":"Wang","sequence":"additional","affiliation":[{"name":"SIASUN Robot & Automation Co., Ltd., Shenyang 110168, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"5969512","DOI":"10.1155\/2024\/5969512","article-title":"Review on motion planning of robotic manipulator in dynamic environments","volume":"1","author":"Liu","year":"2024","journal-title":"J. Sens."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2049","DOI":"10.1177\/02783649241246557","article-title":"Reactive collision-free motion generation in joint space via dynamical systems and sampling-based MPC","volume":"43","author":"Koptev","year":"2024","journal-title":"Int. J. Robot. Res."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Luo, S., Zhang, M., Zhuang, Y., Ma, C., and Li, Q. (2023). A survey of path planning of industrial robots based on rapidly exploring random trees. Front. Neurorobot., 17.","DOI":"10.3389\/fnbot.2023.1268447"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Schulman, J., Ho, J., Lee, A.X., Awwal, I., Bradlow, H., and Abbeel, P. (2013, January 24). Finding locally optimal, collision-free trajectories with sequential convex optimization. Proceedings of the Robotics: Science and Systems 2013, Berlin, Germany.","DOI":"10.15607\/RSS.2013.IX.031"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2967","DOI":"10.1016\/j.automatica.2014.10.128","article-title":"Model predictive control: Recent developments and future promise","volume":"50","author":"Mayne","year":"2014","journal-title":"Automatica"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1603","DOI":"10.1109\/TRO.2018.2865891","article-title":"Information-theoretic model predictive control: Theory and applications to autonomous driving","volume":"34","author":"Williams","year":"2018","journal-title":"IEEE Trans. Robot."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LRA.2025.3630871","article-title":"Feedback-MPPI: Fast sampling-based MPC via rollout differentiation\u2013adios low-level controllers","volume":"11","author":"Belvedere","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3605","DOI":"10.1109\/TIV.2023.3348134","article-title":"RL-driven MPPI: Accelerating online control laws calculation with offline policy","volume":"9","author":"Qu","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ezeji, O., Ziegltrum, M., Turrisi, G., Belvedere, T., and Modugno, V. (2025, January 25). BC-MPPI: A Probabilistic Constraint Layer for Safe Model-Predictive Path-Integral Control. Proceedings of the Agents and Robots for Reliable Engineered Autonomy 2025, Bologna, Italy.","DOI":"10.1007\/978-3-032-08049-3_8"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1007\/s41315-023-00274-2","article-title":"A review of recent trend in motion planning of industrial robots","volume":"7","author":"Tamizi","year":"2023","journal-title":"Int. J. Intell. Robot. Appl."},{"key":"ref_11","first-page":"135","article-title":"Reinforcement learning for assembly robots: A review","volume":"15","author":"Stan","year":"2020","journal-title":"Proc. Manuf. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1109\/TRO.2025.3644945","article-title":"Actor\u2013Critic Model Predictive Control: Differentiable Optimization Meets Reinforcement Learning for Agile Flight","volume":"42","author":"Romero","year":"2025","journal-title":"IEEE Trans. Robot."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Baltussen, T.M.J.T., Orrico, C.A., Katriniok, A., Heemels, W.P.M.H., and Krishnamoorthy, D. (2025, January 10). Value Function Approximation for Nonlinear MPC: Learning a Terminal Cost Function with a Descent Property. Proceedings of the 2025 IEEE 64th Conference on Decision and Control, Rio De Janeiro, Brazil.","DOI":"10.1109\/CDC57313.2025.11312195"},{"key":"ref_14","unstructured":"Hansen, N., Wang, X., and Su, H. (2022). Temporal difference learning for model predictive control. arXiv."},{"key":"ref_15","unstructured":"Wang, P., Li, C., Weaver, C., Kawamoto, K., Tomizuka, M., Tang, C., and Zhan, W. (2024). Residual-mppi: Online policy customization for continuous control. arXiv."},{"key":"ref_16","unstructured":"Dergachev, S., Pshenitsyn, A., Panov, A., Skrynnik, A., and Yakovlev, K. (2025). CoRL-MPPI: Enhancing MPPI with Learnable Behaviours for Efficient and Provably-Safe Multi-Robot Collision Avoidance. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"102305","DOI":"10.1016\/j.cagd.2024.102305","article-title":"Real-time collision detection between general SDFs","volume":"111","author":"Liu","year":"2024","journal-title":"Comput. Aided Geom. Des."},{"key":"ref_18","unstructured":"Li, Y., Miyazaki, T., and Kawashima, K. (2025). One-Step Model Predictive Path Integral for Manipulator Motion Planning Using Configuration Space Distance Fields. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, Y., Chi, X., Razmjoo, A., and Calinon, S. (2024). Configuration space distance fields for manipulation planning. arXiv.","DOI":"10.15607\/RSS.2024.XX.131"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ames, A.D., Coogan, S., Egerstedt, M., Notomista, G., Sreenath, K., and Tabuada, P. (2019, January 15). Control barrier functions: Theory and applications. Proceedings of the 2019 18th European Control Conference, Naples, Italy.","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1109\/LCSYS.2021.3093255","article-title":"Safety embedded control of nonlinear systems via barrier states","volume":"6","author":"Almubarak","year":"2021","journal-title":"IEEE Control Syst. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1109\/LRA.2025.3632612","article-title":"TD-CD-MPPI: Temporal-Difference Constraint-Discounted Model Predictive Path Integral Control","volume":"11","author":"Crestaz","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chane-Sane, E., Leziart, P.A., Flayols, T., Stasse, O., Sou\u00e8res, P., and Mansard, N. (2024, January 14). Cat: Constraints as terminations for legged locomotion reinforcement learning. Proceedings of the International Conference on Intelligent Robots and Systems (IROS), Abu Dhabi, United Arab Emirates.","DOI":"10.1109\/IROS58592.2024.10802334"},{"key":"ref_24","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., and Levine, S. (2018, January 10). 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_25","doi-asserted-by":"crossref","first-page":"3861","DOI":"10.1109\/TAC.2016.2638961","article-title":"Control barrier function based quadratic programs for safety critical systems","volume":"62","author":"Ames","year":"2016","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Todorov, E. (2014, January 31). Convex and analytically-invertible dynamics with contacts and constraints: Theory and implementation in MuJoCo. Proceedings of the 2014 IEEE International Conference on Robotics and Automation, Hong Kong, China.","DOI":"10.1109\/ICRA.2014.6907751"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/7\/2074\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:13:38Z","timestamp":1774538018000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/7\/2074"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,26]]},"references-count":26,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["s26072074"],"URL":"https:\/\/doi.org\/10.3390\/s26072074","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,26]]}}}