Cognitive Robotics in Intelligent Manufacturing

AUTOR(I) / AUTHOR(S): Zoran Miljković , Aleksandar Jokić

Download Full Pdf  

DOI: https://doi.org/10.46793/TIE26.003M

SAŽETAK /ABSTRACT:

In the interest of developing an intelligent manufacturing environment with an agile, efficient, and optimally utilized transportation system, cognitive mobile robots need to achieve a certain level of autonomy. In this keynote paper, we explain a novel stereo visual servoing method for efficient nonholonomic mobile robot control based on semantic segmentation. Semantic segmentation offers rich contextual information necessary for informed decision-making in clustered, dynamic, and continuously evolving manufacturing environments. The new algorithm is deployed on our own-developed wheeled differential-drive mobile robot, named RAICO (Robot with Artificial Intelligence based COgnition). The experimental results show that the accuracy of the proposed approach is improved compared to state-of-the-art approaches, while remaining robust to partial scene occlusions and illumination changes. Also, in this invited paper, a novel Bio-Inspired Learning Control Approach (BILCA) for the autonomous mobile robot Khepera II, based on Learning from Demonstration (LfD), the Firefly Algorithm (FA), and homography between the current and target camera views, is presented. BILCA comprises two stages: (i) a learning stage, during which actuator commands are derived using FA and demonstrations of the desired behavior, and (ii) an evaluation stage, in which the resulting wheel commands are validated in real-world experiments. Two separate problems are addressed in this study: trajectory reproduction and the synthesis of visual control commands for robot orientation correction. The results indicate that larger firefly swarms achieve higher accuracy in the final pose of the mobile robot, while the desired trajectory is reproduced with minimal error in the final control iteration. An experiment conducted on the cognitive mobile robot Khepera II, in an indoor environment unifies two considered problems within a single transportation task.

KLJUČNE REČI / KEYWORDS: 

cognitive mobile robots; intelligent manufacturing environment; visual servoing; semantic segmentation; learning from demonstration; metaheuristic firefly algorithm

 PROJEKAT / ACKNOWLEDGEMENT:

This research is supported by the Science Fund of the Republic of Serbia, grant No. 17801, Cybersecurity of Motion Control Systems in Industry 4.0 – MCSecurity, as well as by the Ministry of Science, Technological Development and Innovations of the Serbian Government under the contract No. 451-03-34/2026-03/200105.

LITERATURA / REFERENCES:

• Javaid, M., Haleem, A., Singh, R. P., & Suman, R. (2022). Enabling flexible manufacturing system (FMS) through the applications of industry 4.0 technologies. Internet of Things and Cyber-Physical Systems, 2, 49–62.
• El Kalach, F., Yousif, I., Wuest, T., Sheth, A., & Harik, R. (2025). Cognitive manufacturing: definition and current trends. Journal of Intelligent Manufacturing, 36(6), 3695–3715.
• Pakkala, D., Känsäkoski, N., Heikkilä, T., Backman, J., & Pääkkönen, P. (2025). On design of cognitive situation-adaptive autonomous mobile robotic applications. Computers in Industry, 167, 104263.
• Karabegovic, I. (2024). AI-Enhanced Mobile and Collaborative Robotics for Autonomous Inspection and Predictive Maintenance in Smart Manufacturing. Smart Wearable Technology.
• Sünderhauf, N., Brock, O., Scheirer, W., Hadsell, R., Fox, D., Leitner, J., Upcroft, B., Abbeel, P., Burgard, W., Milford, M., & Corke, P. (2018). The limits and potentials of deep learning for robotics. International Journal of Robotics Research, 37(4–5), 405–420.
• Mitić, M., & Miljković, Z. (2015). Bio-inspired approach to learning robot motion trajectories and visual control commands. Expert Systems with Applications, 42(5), 2624–2637.
• Jokić, A., Petrović, M., & Miljković, Z. (2022). Semantic segmentation based stereo visual servoing of nonholonomic mobile robot in intelligent manufacturing environment. Expert Systems with Applications, 190, 116203.
• Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008). Speeded-Up Robust Features (SURF). Computer Vision and Image Understanding, 110(3), 346–359.