Derivative Action Control: Smooth Model Predictive Path Integral Control without Smoothing

12/18/2021
by   Taekyung Kim, et al.
1

Here, we present a new approach to generate smooth control sequences in Model Predictive Path Integral control (MPPI) tasks without any additional smoothing algorithms. Our method effectively alleviates the chattering in sampling, while the information theoretic derivation of MPPI remains the same. We demonstrated the proposed method in a challenging autonomous driving task with quantitative evaluation of different algorithms. A neural network vehicle model for estimating system dynamics under varying road friction conditions is also presented. Our video can be found at: <https://youtu.be/o3Nmi0UJFqg>.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset