Student name: João Faria

RUN-EU institution: Polytechnic Institute of Cávado and Ave, Portugal

Abstract

The integration of Autonomous Mobile Robots (AMRs) has significantly advanced across various sectors, including industry, agriculture, and healthcare, enhancing automation and human-robot collaboration [1][2]. However, ensuring safe and adaptive robot behavior in dynamic and unstructured environments remains a challenge [3][4]. A fundamental requirement for effective robot adaptation is the ability to perceive and respond to environmental conditions, such as surface characteristics (e.g., dry, wet, smooth, rough), which directly impact mobility and stability [5]. This research focuses on improving AMRs’ real-time adaptability by leveraging Artificial Intelligence (AI) techniques to recognize and respond to different surface topologies. The primary objective is to enhance safety and efficiency in human-centered environments by enabling robots to dynamically adjust navigation parameters such as speed and trajectory based on detected terrain conditions. Such adaptability is essential for applications where AMRs operate alongside humans, ensuring reliable performance in diverse settings [6][7]. The expected outcome of this study is the development of an AI-driven algorithm capable of detecting and classifying various surface conditions in real time. By integrating this capability into AMRs, the system will optimize movement strategies across multiple sectors, improving operational reliability and safety. This contribution is crucial for the digital transformation of autonomous navigation, enabling robots to function more efficiently in complex and unpredictable environments.

References

[1] A. Markis, M. Papa, D. Kaselautzke, M. Rathmair, V. Sattinger, and M. Brandstötter, “Safety of Mobile Robot Systems in Industrial Applications,” ARW OAGM Work. 2019, pp. 26–31, 2019, doi: 10.3217/978-3-85125-663-5-04.

[2] World Robotics 2022, “Market presentation World Robotics 2022”.

[3] Robotnik, “The Rise of Machine Learning Robots: Explore Machine Learning in Robotics | Robotnik ®.”, 2023,  https://robotnik.eu/the-rise-of-machine-learning-robots-explore-machine-learning-in-robotics/ (accessed Apr. 14, 2024).

[4] Robotnik, “What is adaptive robotics? | Robotnik ®.” 2023, https://robotnik.eu/what-is-adaptive-robotics/ (accessed Apr. 14, 2024).

[5] F. Rubio, F. Valero, and C. Llopis-Albert, “A review of mobile robots: Concepts, methods, theoretical framework, and applications,” International Journal of Advanced Robotic Systems, vol. 16, no. 2, Apr. 2019, doi: 10.1177/1729881419839596.

[6] F. Xue, L. Hu, C. Yao, Z. Liu, Z. Zhu, and Z. Jia, “Sound-Based Terrain Classification for Multi-modal Wheel-Leg Robots,” ICARM 2022 – 2022 7th IEEE Int. Conf. Adv. Robot. Mechatronics, pp. 174–179, 2022, doi:10.1109/ICARM54641.2022.9959511.

[7] M. Yang and E. Yang, “Two-stage multi-sensor fusion positioning system with seamless switching for cooperative mobile robot and manipulator system,” Int. J. Intell. Robot. Appl., vol. 7, no. 2, pp. 275–290, Jun. 2023, https://doi.org/10.1007/s41315-023-00276-0.