I'm Kyle Vedder

In 20 years I want there to be robots that can effectively automate the mechanical aspects of high-quality elder care (e.g. fetching objects, changing sheets, cleaning the room). The US is on the verge of a large retirement of baby boomers and China faces a deeply troubling demographic cliff in 20 years, motivating the need for new, more scalable and cost-effective methods of providing high-quality elder care that does not compromise on outcomes for patients.

Background

I am a CS PhD candidate at Penn under Eric Eaton in the Lifelong Machine Learning group of GRASP Lab. Motivated by my goal of developing elder care robots, my research interests lie in the intersection of:

• Mobile robotics
• Vision-based object detection
• Self-supervised/unsupervised continual learning

During my undergrad in CS at UMass Amherst I did research under Joydeep Biswas in the Autonomous Mobile Robotics Lab. My research was in:

• Single-Agent Path Finding (SAPF) for sampling based planners
• Anytime Multi-Agent Path Finding (MAPF) for efficient first solution generation
• Core infrastructure and low level safety system of our RoboCup Small Size League team

I have also done a number of industry internships; I have interned twice at Unidesk (a startup since aquired by Citrix), twice at Google, and once at Amazon's R&D lab, Lab126 (where I worked on their home robot Astro). This summer I am joining Argo AI as a Research Intern under James Hays.

More Information

• Email: kvedder (at) seas.upenn.edu
• Resume: /resume
• Publications: /publications
• GitHub: kylevedder

Updates