Hybrid dynamical system models for human–robot interaction
Tanveer Ahmad Wanitanveer.ahmad@niu.edu.inDepartment of PhysicsNoida International UniversityGreater Noida, Uttar Pradesh, 201312, IndiaView full profile → , *Nitish BhardwajCorresponding authormathuranitish.bhardwaj@gla.ac.inDepartment of Computer Engineering & ApplicationsGLA UniversityMathura, Uttar Pradesh, 281406, IndiaView full profile → , Smita Tolanismitatolani@gmail.comFaculties Engineering, Sciences and HumanitiesSt. Vincent Pallotti College of Engineering & TechnologyNagpur, Maharashtra, 441108, IndiaView full profile → , Sanjay Olisanjay-maths@dayanandasagar.eduDepartment of MathematicsDayananda Sagar College of EngineeringBangalore, Karnataka, 560111, IndiaView full profile → , Praveen Priyaranjan Nayakpraveennayak@soa.ac.inDepartment of Electronics and Communication EngineeringInstitute of Technical Education and ResearchSiksha ‘O’ Anusandhan (Deemed to be University)Bhubaneswar, Odisha, 751030, IndiaView full profile → , Loganathanloganathan.avmts022@avit.ac.inDepartment of Humanities and SciencesAarupadai Veedu Institute of TechnologyVinayaka Mission’s Research Foundation (Deemed to be University)Paiyanur, Tamil Nadu, 603104, IndiaView full profile → , S. R. Likhithlikhith.sr@presidencyuniversity.inPresidency School of Computer Science and EngineeringPresidency UniversityBangalore, Karnataka, 560119, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Apr 2026
- Published Online:
- 27 Oct 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIM-2817
- Pages:
- 3033–3046
Abstract
With the increasing popularity of human–robot interaction (HRI), control systems are becoming more and more interesting and complicated because they need to coordinate continuous human movements and discrete robot decision-making in dynamic environments. The current strategies tend to be less flexible when working collaboratively, take longer to react and become less stable in interaction. This study presents a hybrid nonlinear state-space model, hybrid automata, Model Predictive Control (MPC), Extended Kalman Filter (EKF) and Adaptive Hybrid Interaction Algorithm (AHIA) based Hybrid Dynamical Human–Robot Interaction (HD-HRI) framework for real-time human intent estimation and robot motion planning. The framework is assessed based on the accuracy of interaction, prediction of intent, trajectory tracking error, response latency, collision avoidance rate and task completion success. Experimental results confirm that 95.8% of the interactions are accurate, 94.9% of intents are correctly predicted, 21.6% of trajectory tracking errors is reduced, 18.4% of response latency is reduced, 97.3% of collisions are avoided, and 95.6% of the tasks are completed. The results prove that the proposed hybrid dynamical framework can be effectively implemented in practical applications, which can be reliable, stable, and efficient for human–robot collaboration.
Keywords
Subject Classifications
References
[1] Y. Liu, K. Luo, Q. Tian, and H. Hu, “An efficient data-driven framework of hybrid dynamics for real-time modeling and control of continuum robots,” Mechanism and Machine Theory, vol. 220, Art. no. 106361 (2026), doi: 10.1016/j.mechmachtheory.2026.106361.
[2] C. Wang, “High precision mechanical hybrid control industrial robots driven by multimodal perception fusion,” Journal of Engineering and Applied Science, vol. 73, Art. no. 175 (2026), doi: 10.1186/s44147-026-01026-2.
[3] H. Fazlollahtabar, “Human-robot interaction using retrieval-augmented generation and fine-tuning with transformer neural networks in Industry 5.0,” Scientific Reports, vol. 15, Art. no. 29233 (2025), doi: 10.1038/s41598-025-12742-9.
[4] J. Zhang and W. Zhan, “Research into collaborative evolution in hybrid human-robot rescue teams,” in Proc. 4th Int. Conf. Image, Video and Signal Processing (IVSP), New York, USA: ACM, pp. 184–191 (2022), doi: 10.1145/3531232.3531259.
[5] N. Dehgardi, M. Azari, and Y. Shang, “Relationship between the inverse sum indeg index of graph operations and their factors,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 29, no. 3, pp. 1181–1199 (2026), doi: 10.47974/JDMSC-2193.
[6] A. Zehfroosh and H. G. Tanner, “A hybrid PAC reinforcement learning algorithm for human-robot interaction,” Frontiers in Robotics and AI, vol. 9, Art. no. 797213 (2022), doi: 10.3389/frobt.2022.797213.
[7] A. A. Khan and K. Thurow, “Human-robot interaction in indoor mobile robotics: Current state, interaction modalities, applications, and future challenges,” Sensors, vol. 26, no. 6, Art. no. 1840 (2026), doi: 10.3390/s26061840.
[8] W. M. P. Steijn, C. Van Gulijk, D. Van der Beek, and T. Sluijs, “A system-dynamic model for human-robot interaction: Solving the puzzle of complex interactions,” Safety, vol. 9, no. 1, Art. no. 1 (2023), doi: 10.3390/safety9010001.
[9] G. Lettera, D. Costa, and M. Callegari, “A hybrid architecture for safe human-robot industrial tasks,” Applied Sciences, vol. 15, no. 3, Art. no. 1158 (2025), doi: 10.3390/app15031158.
[10] T. K. Evans, V. Popescu, and S. Ahmed, “A systematic review of hybrid dynamical system models for human-robot interaction: Methods, architectures, and future research directions,” International Journal of Electrical, Electronics and Computer Systems, vol. 14, no. 2, pp. 151–161 (2025), doi: 10.65521/ijeecs.v14i2.2111.
[11] F. Schirmer, P. Kranz, C. G. Rose, J. Schmitt, and T. Kaupp, “Towards dynamic human-robot collaboration: A holistic framework for assembly planning,” Electronics, vol. 14, no. 1, Art. no. 190 (2025), doi: 10.3390/electronics14010190.
[12] C. Urrea, “Hybrid deep learning-reinforcement learning for adaptive human-robot task allocation in Industry 5.0,” Systems, vol. 13, no. 8, Art. no. 631 (2025), doi: 10.3390/systems13080631.
[13] S. Ajani and S. Y. Amdani, “Obstacle collision prediction model for path planning using obstacle trajectory clustering,” in Data, Engineering and Applications, Lecture Notes in Electrical Engineering, vol. 907. Singapore: Springer pp. 99–111 (2022), doi: 10.1007/978-981-19-4687-5_8.
