Jonas Mayer is a Principal Consultant at TNG Technology Consulting. As Head of Innovation Hacking, his main focus lies on creating innovative showcases and prototypes in soft- and hardware. Since 2018 he's been working on numerous projects ranging from market-leading Realtime Deepfakes, an LLM Shitposting AI, all the way to autonomous drone racing. As a keynote speaker, he has been talking about the Innovation Hacking projects at over a hundred conferences all across IT and Tech. Prior to joining TNG, Jonas studied Informatics: Games Engineering at TU Munich. More information can be found at innovation-hacking.com.
Robotics is transitioning from factory floors to our everyday lives, particularly through humanoid robots. This session features a live demonstration of our Unitree G1 android, exploring how advances in AI, increasing data availability, and edge computing hardware are transforming science fiction into reality.
The session begins with an overview of robotics and its market potential. Next, robot training is examined, demonstrating how integrated hardware and software bridge the gap between simulation and real-world deployment. Finally, Vision-Language-Action (VLA) models are explored for enabling meaningful human-robot interaction and future applications.
We introduce an innovative application of computer vision and artificial intelligence to analyze training videos of canoe athletes preparing for the Olympic Games. Our method employs foreground-background separation for canoe detection and waterline derivation. Through pose detection, we identify the paddle and have trained a neural network to recognize essential paddle positions for routine training analysis. Additionally, we incorporate biomechanical insights in a post-processing step to refine AI results and enhance analysis accuracy. Traditionally, biomechanics engineers manually screen training videos frame by frame to locate specific paddle positions and measure the paddle's angle relative to the waterline; a process taking about 20 minutes per athlete. Our approach significantly streamlines this process, reducing the workload by an order of magnitude.
Searching for speaker images...