Yondu: Robotic Foundation Models for Intelligent Navigation
Summary
There are already tons of mobile robotics applications that benefit from improved autonomy and human-robot interaction. Theres also lot of untapped footage all over the internet for learning autonomous navigation. Mobile robots are a lot cheaper compared to dextrous ones.We are using a code generation agent to create some annotated training data for our end-to-end models.The founders met while studying at MIT and have been involved in various escapades throughout the years. From hacking hijinks to grueling late night projects, the two have done it all!Michael (left) was studying Robotics at MIT and has worked on building an open source bipedal robot and an autonomous train track cleaner!Tahmid (right) studied Computer Science and AeroAstro at MIT and was a graduate student researching uncertainty quantification for deep learning.P.S. all feedback is appreciated \U0001f600 feel free to email us at founders[at]yonduai[dot]com \U0001f4bc connections to businesses that could use our models for their robots \U0001f6a7 connections to organizations (law enforcement, search-and-rescue, construction, inspection, security, etc) that could use smart robots