SYDCROSep 3, 2015

Model Predictive Path Integral Control using Covariance Variable Importance Sampling

arXiv:1509.01149v3215 citations
Originality Synthesis-oriented
AI Analysis

This work addresses control optimization for robotics or autonomous systems, but it appears incremental as it builds on existing MPPI methods with a modified sampling approach.

The paper tackles the problem of improving Model Predictive Path Integral (MPPI) control by introducing a generalized importance sampling scheme that modifies drift and diffusion terms, and implements it on a GPU for parallel optimization. The result is a performance comparison in simulation with a model predictive control version of differential dynamic programming, though no concrete numbers are provided.

In this paper we develop a Model Predictive Path Integral (MPPI) control algorithm based on a generalized importance sampling scheme and perform parallel optimization via sampling using a Graphics Processing Unit (GPU). The proposed generalized importance sampling scheme allows for changes in the drift and diffusion terms of stochastic diffusion processes and plays a significant role in the performance of the model predictive control algorithm. We compare the proposed algorithm in simulation with a model predictive control version of differential dynamic programming.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes