Abstract:
We typically have a clear idea about the final design and functionality of a robot before we start building it. We apply this top-down design approach to a wide range of robotic systems and it allows our robots to be more optimized, autonomous, and programmable. However, if we want to design and actuate multiple robots in miniature scales or robots made of soft and deforming materials, this approach sometimes fails to meet our needs. In such cases, we adopt nature’s design strategy that creates complex and emergent morphologies, and adaptive functions out of the collective motion of many neighboring, soft, smaller, and simpler elements. In this talk, I will describe how we can use this bottom-up design approach to build and control soft robots and their self-assemblies in multiple length scales. I will talk about how we can benefit from engineering tools, fundamental laws of physics, and emerging machine learning methods to explore the vast design and function search space of soft robots. I will give examples from my works on embodied intelligence where the physical properties of the robots enable further increments to computational intelligence while multiplying the effects of adaptivity, durability, and autonomy. Our findings can enable novel robotic systems in medicine, agriculture, and human-robot interaction, and establish stronger connections with biology,  physics, and material science.

Bio:
Utku Culha has received his bachelor’s and master’s degrees from Bilkent University, Turkey from the Computer Engineering Department. He started his Ph.D. on Mechanical Engineering in ETH-Zurich, Switzerland with Prof. Fumiya Iida and then moved to the University of Cambridge, UK to help establish the Bio-Inspired Robotics Laboratory. During his Ph.D., Utku has worked on deforming thermoplastic materials to build robots with adaptive sensing, locomotion, and manipulation skills. After completing his Ph.D., Utku joined the Physical Intelligence Department at the Max-Planck Institute (MPI) for Intelligent Systems in Stuttgart, Germany, and has been working as a Humboldt Postdoctoral researcher with Prof. Metin Sitti since 2016. Utku is interested in creating self-assembling soft robots that can physically adapt to their environment by deforming their body morphologies. He is also working on using data-efficient machine-learning methods to explore novel robot functions, designs, and controllers.

***Want to attend this lecture? Subscribe to our mailing list here or by sending an empty email to scioi-info-join@lists.tu-berlin.de
The Zoom Link will be sent the day before the lecture. (Contact communication@scioi.de for specific questions)

(Image copyright Utku Culha)