Moving from Data Collection to Data Generation: Addressing the Need for Data in Robotics

Title: Moving from Data Collection to Data Generation: Addressing the Need for Data in Robotics

Abstract: Imitation learning from human demonstrations has emerged as a widely adopted paradigm for teaching robots manipulation skills. However, data collection for imitation learning is costly and resource-intensive, often spanning teams of human operators, fleets of robots, and months of persistent data collection effort. Instead, in this talk, I will advocate for the use of automated data generation methods and simulation platforms as a scalable alternative to fuel this need for data. I will introduce a suite of automated data generation tools that make use of robot planning methods and small sets of human demonstrations, to synthesize new demonstrations automatically. These tools are broadly applicable to a wide range of manipulation problems, including high-precision and long-horizon manipulation, and can be used to produce performant, often near-perfect agents for such tasks. The data generated in simulation can also be used to address real-world robotic manipulation, making synthetic data generation a compelling tool for imitation learning in robotics.

Bio: Ajay Mandlekar is a research scientist at NVIDIA AI. Previously, he obtained his PhD degree from Stanford University, co-advised by Silvio Savarese and Fei-Fei Li. His research focuses on developing systems and algorithms to enable robots to learn useful manipulation tasks.