Given the problems of cell surface reflection, unstable incoming material position, damage susceptibility during contact, difficulty in achieving closed-loop fastening and welding quality control, and low efficiency of multi-model mixed-flow switching in new energy vehicle battery module assembly, this paper proposes an intelligent robot application framework that integrates 3D visual positioning, visual-force state fusion, Cartesian impedance control, and digital twin scheduling. Based on publicly available statistical data from the International Energy Agency and the International Federation of Robotics, this study analyzes the industry demand and incorporates research on robot assembly and battery automation over the past three years to build a closed-loop system of "perception-planning-execution-detection-traceability". It also offers models for pose estimation, compliant control, process capability evaluation and multi-objective scheduling, and sets engineering design goals and verification schemes for twelve-cell square modules. Based on the scenario calculation, assuming a theoretical cycle time of 45 seconds and the conditions of set equipment availability, performance rate and quality rate, the system can produce about 69 qualified modules per hour. The proposed framework provides an engineering basis for robot selection, control parameter setting, quality gating and digital operation-and-maintenance of a flexible automated battery module production line. Verification is divided into offline simulation, single-station test and full-line continuous-cycle validation, and the acceptance criteria include pose accuracy, contact-force limits, process capability, cycle time, traceability and recipe changeover. The staged scheme supports pilot-line acceptance and factory validation without substituting scenario calculations with actual enterprise production data.

Boyu Cao. Application Research of Intelligent Robots in the Assembly of Battery Modules for New Energy Vehicles. International Journal of Engineering Technology and Construction (2026), Vol. 7, Issue 1: 18-28. https://doi.org/10.38007/IJETC.2026.070103.

[1] International Energy Agency. Global EV Outlook 2026: Moving towards increased affordability. Paris: IEA, 2026. Available at: https://doi.org/10.1787/a9e65774-en.

[2] International Federation of Robotics. World Robotics 2024: Industrial Robots. Frankfurt am Main: IFR, 2024. Available at: https://ifr.org/ifr-press-releases/news/record-4-million-robots-work-in-factories-around-the-globe.

[3] Kaarlela T, Villagrossi E, Rastegarpanah A, et al. Robotized disassembly of electric vehicle batteries: A systematic literature review. Journal of Manufacturing Systems, 2024, 74: 901-921. DOI: 10.1016/j.jmsy.2024.05.013.

[4] Zang Y, Qu M, Pham DT, et al. Robotic disassembly of electric vehicle batteries: Technologies and opportunities. Computers & Industrial Engineering, 2024, 198: 110727. DOI: 10.1016/j.cie.2024.110727.

[5] Liang C, Parnada A, Gbadebo A, et al. An experimental robotic cell for the disassembly of electric vehicle battery modules. Journal of Remanufacturing, 2025, 15: 381-410. DOI: 10.1007/s13243-025-00156-9.

[6] Wang B, Zhang J, Wu D. Force-vision fusion fuzzy control for robotic batch precision assembly of flexibly absorbed pegs. Robotics and Computer-Integrated Manufacturing, 2025, 92: 102861. DOI: 10.1016/j.rcim.2024.102861.

[7] Ota K, Jha DK, Jain S, et al. Autonomous robotic assembly: From part singulation to precise assembly. In: 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems. Abu Dhabi: IEEE, 2024: 13525-13532. DOI: 10.1109/IROS58592.2024.10802423.

[8] Touhid MTB, Zhu E, Ehteshamfar MV, et al. Synchronization evaluation of digital twin for a robotic assembly system using computer vision. Manufacturing Letters, 2024, 41: 1257-1263. DOI: 10.1016/j.mfglet.2024.09.152.

[9] Li X, He B, Wang Z, et al. A digital twin system for task-replanning and human-robot control of robot manipulation. Advanced Engineering Informatics, 2024, 62: 102570. DOI: 10.1016/j.aei.2024.102570.

[10] Li Y, Jin Z, Liu J, et al. Visuo-tactile feedback policies for terminal assembly facilitated by reinforcement learning. Frontiers in Robotics and AI, 2025, 12: 1660244. DOI: 10.3389/frobt.2025.1660244.