Ken Oslund

Google (United States), Stanford University

Papers

4

Total Citations

42

H-Index

4

About

Ken Oslund is a robotics researcher pushing the boundaries of high-speed, agile, and interactive robotic systems. His work spans three key areas: real-time perception and control for dynamic manipulation, animal-inspired locomotion for quadruped robots, and efficient scaling of large transformer models for robotics. Oslund’s most notable contribution is the development of a robotic table tennis system capable of sustained rallies with humans and precise ball placement, a landmark case study in high-speed learning (17 citations). He also led the creation of Barkour, a benchmark for quadruped agility that quantifies animal-level locomotion skills like sprinting and leaping (13 citations). In 2024, he introduced SARA-RT, a novel up-training method that makes large robotics transformers deployable on physical robots, addressing a critical bottleneck in scaling AI for real-world use (7 citations). Earlier, his JediBot project explored human-robot sword-fighting, demonstrating his long-standing interest in interactive, dynamic tasks. With over 40 combined citations across his top papers, Oslund’s work is shaping how robots learn and act at high speeds, bridging simulation and reality for next-generation embodied intelligence.

Research Focus

Key Achievements

4
H-Index
4
Papers
42
Total Citations
11
Avg Citations/Paper
🏆 Most Cited Paper
Robotic Table Tennis: A Case Study into a High Speed Learning System
17 citations · 2023
📈 Most Prolific Year: 2023 (2 Papers)
🤝 Key Collaborators: 85
🏛 Institutions: Google (United States), Stanford University

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago