Embodied artificial intelligence refers to the field of AI in which agents, such as robots, learn to solve challenging tasks requiring interaction with a physical environment. AIpowered robots will benefit society in manufacturing, healthcare, and more. To achieve this, low latency and data efficiency are key. This is why ondevice AI is crucial for embodied AI. This webinar will walk through Qualcomm AI Research’s stateoftheart results in the area of embodied AI called robot motion planning, with an emphasis on understanding 3D images and videos with equivariant networks and geometric deep learning.

From this webinar, you will learn about:

The need for and benefits of embodied AI
Representing the physical world with geometric algebra
Two key concepts: equivariance & transformers
Robot motion planning simulation (demo)
Future directions of embodied AI

Speaker: Taco Cohen
Principal Engineer, Qualcomm AI Research
Taco Cohen is a machine learning researcher at Qualcomm AI Research in Amsterdam. He received a BSc in theoretical computer science from Utrecht University, and a MSc in artificial intelligence and PhD in machine learning (with prof. Max Welling) from the University of Amsterdam. He was a cofounder of Scyfer, a company focussed on deep active learning, acquired by Qualcomm in 2017. His research is focused on equivariant networks and geometric deep learning, causality and interactive learning. During his studies he has interned at Google Deepmind (working with Geoff Hinton) and OpenAI. He received the 2014 University of Amsterdam MSc thesis prize, a Google PhD Fellowship, ICLR 2018 best paper award for “Spherical CNNs”, was named one of 35 innovators under 35 by MIT Tech Review, and won the 2022 ELLIS PhD Award and 2022 Kees Schouhamer Immink prize for his PhD research.

Webinar moderated by Armina Stepan