Physical AI Working Group Meeting

Don’t Disintegrate Your Robots, Some Observations From My Years In The Trenches Abstract: The difficulties of fielding robot products are often fed by a long history of weak, ineffective and downright counterproductive software architecture and engineering practices. Building a complete robot product is incredibly difficult, but picking the wrong approach to robot software can make that process even more difficult. This talk will share some of the ways that bad assumptions about robot software can make your development path harder and offers a few suggestions on how things might get better. About the speaker: Todd Pack is a longtime roboticist with experiences at iRobot, Jibo, Amazon Robotics, and Neo Cybernetica.

About the MassRobotics AI working group: The physical AI working group brings together stakeholders from industry, academia, and government to explore the intersection of artificial intelligence and robotics. Our mission is to advance the development and deployment of AI systems that interact with and understand the physical world — from perception and reasoning to manipulation and motion. The group focuses on real-world applications and innovation in areas such as machine learning for robotics, embodied intelligence, AI-enhanced autonomy, and human-robot collaboration.  Through open dialogue, shared research, and collaboration, we aim to identify technical challenges, help with data acquisition, and accelerate progress in physical AI. Our vision is to make Massachusetts a global hub for robotics-focused AI innovation.