2023-2024 Seminar Series
Speaker: Yuval Tassa (Google DeepMind)
Title: MJPC: Asynchronous UI for real-time behavior synthesis
Model-free, learning-based methods are simple and powerful but inherently slow. Model-based predictive control methods can synthesize behavior in real time, but are considered difficult to understand, implement and use.
In this talk I will present MuJoCo MPC (MJPC), a fully open-source interactive application and software framework for predictive control that lets the user easily author and solve complex robotics tasks. MJPC is a rich GUI application, giving the user real-time visual feedback and allowing them to develop intuitions about the underlying algorithm. Importantly, the interactive simulation can be slowed-down asynchronously—effectively speeding up the controller—leading to a democratization of predictive control tooling.
In closing, I will discuss various ways in which model-based and model-free methods can be combined, exploiting the strengths of both approaches.
The talk will include a live demo of multiple locomotion and manipulation tasks solved from scratch, in real-time, on a laptop.
Date: Friday, December 1st 2023
Time: 10:00-11:00 AM EST (GMT -05:00)
Line-Up and Video Links
|Dec. 1, 2023||Yuval Tassa||MJPC: Asynchronous UI for real-time behavior synthesis|