Machine learning has made tremendous strides in the field of robotics, particularly in enhancing perception, adaptability, and decision-making. This technological revolution has enabled robots to navigate complex scenarios that were previously beyond their capabilities using traditional approaches. However, as robots continue to shrink in size to the micro- and nanoscales, new challenges have emerged.
At these minuscule dimensions, traditional modelling methods struggle to address the complexities involved in actuation and locomotion. Additionally, control and navigation are hindered by environmental disruptions, while tracking encounters in vivo faces significant noise interference. To overcome these challenges, researchers have turned to machine learning as a viable solution.
Recent advancements in machine learning have significantly contributed to the development of micro- and nanorobots. Machine learning has played a vital role in various aspects of robotics, including design, actuation, locomotion, planning, tracking, and navigation. These advancements are poised to benefit a wide range of applications in fields such as micromanipulation, targeted drug delivery, bio-sensing, and medical diagnosis.
This comprehensive review aims to shed light on the latest achievements in machine learning for micro- and nanorobots. By exploring the potential of machine learning in overcoming fundamental challenges, this research seeks to broaden the application horizons of micro- and nanorobotics in biomedicine. By fostering interdisciplinary collaborations across robotics, computer science, material science, and related disciplines, researchers hope to unlock new possibilities in this burgeoning field.
