Go to IEEE ICRA 2025 Workshop RoboLetics homepageTime-Correlated Action Sampling in Model Predictive Path Integral
In this paper, we introduce time-correlated model predictive path integral (TC-MPPI), a novel method designed to mitigate action noise in sampling-based control algorithms. Unlike conventional smoothing techniques that rely on post-processing or additional state variables, TC-MPPI incorporates temporal correlation of actions into stochastic optimal control, effectively enforcing quadratic costs on action derivatives. This reformulation enables us to generate smooth action sequences without requiring further adjustments, using a time-correlated and conditional Gaussian sampling distribution. We demonstrate the effectiveness of our approach through simulations on various robotic platforms, including a pendulum, cart-pole, 2D bicopter, 3D quadcopter, and autonomous vehicle. Simulation videos are available at https://youtu.be/nWfJ2MAV2JI.