Abstract

Temporal Intent Reconstruction framework integrated with a Masked Cognitive Predictor to improve predictive control under changing goals and dynamic conditions. Using real multimodal data from HARMONIC, RoboMind, RoboNet, and Open X-Embodiment, the model reconstructs past intent trajectories and embeds misalignment signals into the control objective for long-horizon adaptation. Experiments showed stable reconstruction across embodiment and modality variations, reduced goal divergence by 31.4%, and improved tracking behaviour by 78% during transitions. The framework improved accuracy, RMSE reduction, and tracking behaviour compared with baseline MPC, inverse learning, and reinforcement-based controllers. These results indicate that temporal intent reconstruction enhances consistency and long-range predictive capability in systems operating under varied sensing, morphology, and task settings.

References

• Jose Manuel Alcayaga, Oswaldo Anibal Men´endez, Miguel Attilio Torres-Torriti, Juan Pablo V´asconez, Tito Ar´evalo-Ramirez, and Alvaro Javier Prado Romo. Lstm enhanced deep reinforcement learning for robust trajectory tracking control of skid-steer mobile robots under terramechanical constraints. Robotics, 14(6):74, 2025.
• Abdelhakim Amer, Mohit Mehndiratta, Yury Brodskiy, and Erdal Kayacan. Empowering autonomous underwater vehicles using learning-based model predictive control with dynamic forgetting gaussian processes. IEEE Transactions on Control Systems Technology, 2025.
• Luka Antonyshyn and Sidney Givigi. Deep model-based reinforcement learning for predictive control of robotic systems with dense and sparse rewards. Journal of Intelligent & Robotic Systems, 110(3):100, 2024.
• Muhammad Asif, Talha Ahmed Khan, andWang-Cheol Song. Leveraging cognitive machine reasoning and nlp for automated intent-based networking and e2e service orchestration. IEEE Access, 2025.
• Janet M Baker and Peter Cariani. Time-domain brain: Temporal mechanisms for brain functions using time-delay nets, holographic processes, radio communications, and emergent oscillatory sequences. Frontiers in Computational Neuroscience, 19:1540532, 2025.
• Farnaz Boudaghi, Danial Waleed, and Luis A Duffaut Espinosa. Data reconstruction using smart sensor placement. Sensors, 24(18):6008, 2024.
• Open X-Embodiment Collaboration, Abby O’Neill, .........., and Zipeng Lin. Open X-Embodiment: Robotic learning datasets and RT-X models. https://arxiv.org/abs/ 2310.08864, 2023.
• Bangwu Dai, Fuli Wang, Yuqing Chang, Fei Chu, and Shengjun Song. Process model-assisted optimization control method based on model predictive control and deep reinforcement learning for coordinated control system in coal-fired power unit. IEEE Transactions on Automation Science and Engineering, 2024.
• Sudeep Dasari, Frederik Ebert, Stephen Tian, Suraj Nair, Bernadette Bucher, Karl Schmeckpeper, Siddharth Singh, Sergey Levine, and Chelsea Finn. Robonet: Large-scale multi-robot learning. In CoRL 2019: Volume 100 Proceedings of Machine Learning Research, 2019.
• Anirban Dutta. Neurocomputational mechanisms of sense of agency: Literature review for integrating predictive coding and adaptive control in human–machine interfaces. Brain Sciences, 15(4):396, 2025.
• Haitham El-Hussieny. Real-time deep learning-based model predictive control of a 3-dof biped robot leg. Scientific Reports, 14(1):16243, 2024.
• Sorin M Grigorescu and Mihai V Zaha. Inverse rl scene dynamics learning for nonlinear predictive control in autonomous vehicles. IEEE Transactions on Neural Networks and Learning Systems, 2025.
• T Gu, T Zhi, X Bao, L Chang, D Weyns, SM Hezavehi, P Avgeriou, R Calinescu, R Mirandola, D Perez-Palacin, et al. Autonomous and adaptive systems. ACM Transactions on, 20(1), 2025.
• Jing Huang, Ziheng Zhang, and Xiaogang Ruan. An improved dyna-q algorithm inspired by the forward prediction mechanism in the rat brain for mobile robot path planning. Biomimetics, 9(6):315, 2024.
• Rahul Kumar, Manish Bhanu, Jo˜ao Mendes-Moreira, and Joydeep Chandra. Spatio-temporal predictive modeling techniques for different domains: a survey. ACM Computing Surveys, 57(2):1–42, 2024.
• Javier Laplaza, Francesc Moreno, and Alberto Sanfeliu. Enhancing robotic collaborative tasks through contextual human motion prediction and intention inference. International Journal of Social Robotics, pages 1–20, 2024.
• Gedi Liu. Uncertainty theory. AI & SOCIETY, pages 1–12, 2025.
• Tania Lombrozo. Learning by thinking in natural and artificial minds. Trends in Cognitive Sciences, 2024.
• Anji Ma, Guoyi Chi, Serena Ivaldi, and Lipeng Chen. Learning high-level robotic manipulation actions with visual predictive model. Complex & Intelligent Systems, 10(1):811– 823, 2024.
• Michael Maiworm, Daniel Limon, and Rolf Findeisen. Online learning-based model predictive control with gaussian process models and stability guarantees. International Journal of Robust and Nonlinear Control, 31(18):8785–8812, 2021.
• Amoh Mensah Akwasi, Haoyong Chen, Junfeng Liu, and Otuo-Acheampong Duku. Hybrid adaptive learning-based control for grid-forming inverters: Real-time adaptive voltage regulation, multi-level disturbance rejection, and lyapunovbased stability. Energies, 18(16):4296, 2025.
• Alireza Mirzabagheri, Majid Ahmadi, Ning Zhang, Reza Alirezaee, Saeed Mozaffari, and Shahpour Alirezaee. Navigating uncertainty: Advanced techniques in pedestrian intention prediction for autonomous vehicles—a comprehensive review. Vehicles, 7(2):57, 2025.
• Ahmed Wajeh Mushtaha, Wesam Salah Alaloul, Abdullah O Baarimah, Muhammad Ali Musarat, Khalid Mhmoud Alzubi, and Abdul Mateen Khan. A decision-making framework for prioritizing reconstruction projects in post-disaster recovery. Results in Engineering, 25:103693, 2025.
• Benjamin A. Newman, Reuben M. Aronson, Siddhartha S. Srinivasa, Kris Kitani, and Henny Admoni. Harmonic: A multimodal dataset of assistive human–robot collaboration. The International Journal of Robotics Research, Dec 2021.
• Krupa Prag, Matthew Woolway, and Turgay Celik. Datadriven model predictive control of dc-to-dc buck-boost converter. IEEE Access, 9:101902–101915, 2021.
• Krupa Prag, Matthew Woolway, and Turgay Celik. Toward data-driven optimal control: A systematic review of the landscape. IEEE Access, 10:32190–32212, 2022.
• R Kelly Rainer Jr, Robert Glenn Richey Jr, and Soumyadeb Chowdhury. How robotics is shaping digital logistics and supply chain management: An ongoing call for research. Journal of Business Logistics, 46(1):e70005, 2025.
• Rohan Mandar Salvi and Pronob Kumar Barman. Evolving architectures and long-horizon planning in multi-agent conversational ai: A decade in review. Emerging Frontiers Library for The American Journal of Interdisciplinary Innovations and Research, 7(07):106–122, 2025.
• Aishwarya Selvamurugan, Aromal Vinod Kumar, Hrishikesh R Palan, Arockiaraj Simiyon, and Thirunavukkarasu Indiran. Reinforcement learning-based nonlinear model predictive controller for a jacketed reactor: A machine learning concept validation using jetson orin. ACS omega, 10(28):30864–30878, 2025.
• Caroline Specht, Abhiraj Bishnoi, and Roberto Lampariello. Autonomous spacecraft rendezvous using tube-based model predictive control: design and application. Journal of Guidance, Control, and Dynamics, 46(7):1243–1261, 2023.
• Dingshan Sun, Anahita Jamshidnejad, and Bart De Schutter. A novel framework combining mpc and deep reinforcement learning with application to freeway traffic control. IEEE Transactions on Intelligent Transportation Systems, 25(7):6756–6769, 2024.
• Yicheng Sun, Qi Zhang, Jinsong Bao, Yuqian Lu, and Shimin Liu. Empowering digital twins with large language models for global temporal feature learning. Journal of Manufacturing Systems, 74:83–99, 2024.
• Getaneh Berie Tarekegn, Rong-Terng Juang, Belayneh Abebe Tesfaw, Hsin-Piao Lin, Huan-Chia Hsu, Robel Berie Tarekegn, and Li-Chia Tai. A centralized multi-agent drlbased trajectory control strategy for unmanned aerial vehicleenabled wireless communications. IEEE Open Journal of Vehicular Technology, 2024.
• Sydney Thompson, Alexander Lew, Yifan Li, Elizabeth Stanish, Alex Huang, Rohan Phanse, and Marynel V´azquez. Predicting human intent to interact with a public robot: The people approaching robots database (par-d). In Proceedings of the 26th International Conference on Multimodal Interaction, pages 536–545, 2024.
• Hua-Ping Wan and Yi-Qing Ni. Bayesian multi-task learning methodology for reconstruction of structural health monitoring data. Structural Health Monitoring, 18(4):1282–1309, 2019.
• Bo Wang, Fusheng Bai, and Ke Zhang. Actor-critic objective penalty function method: an adaptive strategy for trajectory tracking in autonomous driving. Complex & Intelligent Systems, 10(2):1715–1732, 2024.
• Yuru Wang and Jiaxin Zhou. Rejecting unfairness enhances the implicit sense of agency in the human brain. Scientific Reports, 14(1):22822, 2024.
• Kun Wu, Chengkai Hou, Jiaming Liu, Zhengping Che, Xiaozhu Ju, Zhuqin Yang, Meng Li, Yinuo Zhao, Zhiyuan Xu, Guang Yang, et al. Robomind: Benchmark on multiembodiment intelligence normative data for robot manipulation. In Robotics: Science and Systems (RSS) 2025. Robotics: Science and Systems Foundation, 2025.
• Zhe Wu, Panagiotis D Christofides, Wanlu Wu, Yujia Wang, Fahim Abdullah, Aisha Alnajdi, and Yash Kadakia. A tutorial review of machine learning-based model predictive control methods. Reviews in Chemical Engineering, 41(4):359–400, 2025.
• Suchuan Xing and Yihan Wang. Proactive data placement in heterogeneous storage systems via predictive multi-objective reinforcement learning. IEEE Access, 2025.
• Xin Xu, Hong Chen, Chuanqiang Lian, and Dazi Li. Learning-based predictive control for discrete-time nonlinear systems with stochastic disturbances. IEEE transactions on neural networks and learning systems, 29(12):6202–6213, 2018.
• Xingyu Yang, Zhengxue Zhou, Leihui Li, and Xuping Zhang. Collaborative robot dynamics with physical human–robot interaction and parameter identification with pinn. Mechanism and Machine Theory, 189:105439, 2023.
• Chao Yu, Zhiyuan Zhou, and Junbo Gao. Rural network resilience: A new tool for exploring the mechanisms and pathways of rural sustainable development. Sustainability (2071- 1050), 16(14), 2024.
• Leila Ghorban Zadeh, Ali Shahbaz Haider, and Ted KA Brekken. Bayesian actor-critic wave energy converter control with modeling errors. IEEE Transactions on Sustainable Energy, 14(1):3–11, 2022.
• Gholamreza Zare and P Malekpour Alamdari. Diffusionbased latent intent evolution for anticipatory and goaltransition- aware recommendation, 2025.
• Fawang Zhang, Jingliang Duan, Haoyuan Xu, Hao Chen, Hui Liu, Shida Nie, and Shengbo Eben Li. Inverse model predictive control: Learning optimal control cost functions for mpc. IEEE Transactions on Industrial Informatics, 2024.
• Lu Zhang, Junyao Xie, Charles Robert Koch, and Stevan Dubljevic. Model predictive control of jacket tubular reactors with a reversible exothermic reaction. Industrial & Engineering Chemistry Research, 59(42):18921–18936, 2020.
• Yu Zhang, Long Wen, Zhenshan Bing, Xiangtong Yao, Linghuan Kong, Wei He, and Alois Knoll. Adaptive safetycritical control for high-order systems: A real-time gaussian process approach. IEEE Transactions on Automation Science and Engineering, 2025.
• Xiangwei Zhu, Huiqin Wang, Yi Han, Donghui Zhang, Senhao Liu, Zhijie Zhang, and Yansheng Liu. Reconstructing the voc–ozone research framework through a systematic review of observation and modeling. Sustainability, 17(16):7512, 2025.