Karl Schmeckpeper
Research Lead at RAI Institute
Cambridge, Massachusetts, United States
Summary
👤
Senior🎓
Top SchoolKarl Schmeckpeper is a research leader with a decade of experience at the intersection of machine learning, robotics, and computer vision, holding a PhD from the University of Pennsylvania under Kostas Daniilidis. He now leads the Foundation Models research team at the RAI Institute after progressing from research scientist roles, bringing deep hands-on expertise in robotic perception, visual foresight, and pose estimation. His work spans building real-world robotic systems—from precise liquid pouring with only RGB sensors to multi-floor navigation stacks—and applying that expertise to large-scale foundation model research. Based in Cambridge, MA, he has a track record of translating academic research into deployed systems, and is comfortable moving between C++, Python, ROS, and deep learning frameworks. An unusual strength is his history of integrating simulation and real-hardware experiments to generate training data and reliable policies for challenging, underconstrained tasks.
10 years of coding experience
7 years of employment as a software developer
Bachelor of Science (B.S.), Computer Science, Bachelor of Science (B.S.), Computer Science at University of Massachusetts AmherstDoctor of Philosophy - PhD, Doctor of Philosophy - PhD at University of Pennsylvania
English
Github Skills (25)
pybullet8
interaction8
robot8
robotics8
deep-reinforcement-learning7
ros6
autonomous-robots6
mujoco6
reinforcement-learning6
arm5
signed5
manipulation5
modularity5
siggraph4
lstm4
Programming languages (4)
Github contributions (5)
kschmeckpeper/rl_with_videos
Nov 2020 - Jun 2021
Reinforcement Learning with Videos: Combining Offline Observations with Interaction
Contributions:15 commits, 2 pushes, 12 comments in 7 months
interactionvideosreinforcement-learningdeep-reinforcement-learningmujoco
kschmeckpeper/keypoint-pose-estimation
Oct 2020 - Apr 2021
Contributions:10 commits, 9 pushes, 1 branch in 6 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.