Lukas Biewald
Papers
1
Total Citations
24
H-Index
1
About
Lukas Biewald is a leading figure in applied machine learning, with a focus on bridging the gap between simulation and real-world robotics. His most-cited work, "Domain Randomization and Generative Models for Robotic Grasping" (2018, 24 citations), tackles a critical challenge in robotic manipulation: generalization. Biewald pioneered the use of domain randomization—varying simulated environments so aggressively that models learn to ignore irrelevant visual details—combined with generative models to create vast, diverse training data. This approach enabled robots to grasp novel objects without expensive real-world data collection, a breakthrough that has influenced subsequent work in sim-to-real transfer. Beyond his research, Biewald is best known as the founder of Figure Eight (formerly CrowdFlower), a platform that revolutionized human-in-the-loop machine learning by enabling scalable data annotation. His entrepreneurial and technical contributions have made him a key voice in practical AI deployment, emphasizing robust, data-efficient systems that work outside the lab.
Research Focus
Key Achievements
Top Papers
- 1Domain Randomization and Generative Models for Robotic Grasping24 citations · 2018