Smooth model predictive path integral control without smoothing

HIGHLIGHTS

• who: Without Smoothing and collaborators from the (UNIVERSITY) have published the research work: Smooth Model Predictive Path Integral Control Without Smoothing, in the Journal: (JOURNAL)
• what: The authors propose a method that seamlessly combines MPPI with an input-lifting strategy. The authors propose to model such complex and nonlinear dynamics using a neural_network with state-action history, which enables the network to capture time-varying behavior .
• how: The authors designed the dynamics model with two fully-connected hidden layers each with 32 neurons. The authors collected a human-controlled driving dataset in a . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.