Biased-MPPI: Informing Sampling-Based Model Predictive Control by Fusing Ancillary Controllers

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Trevisan, Elia, Alonso-Mora, Javier
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910435845865472
author Trevisan, Elia
Alonso-Mora, Javier
author_facet Trevisan, Elia
Alonso-Mora, Javier
contents Motion planning for autonomous robots in dynamic environments poses numerous challenges due to uncertainties in the robot's dynamics and interaction with other agents. Sampling-based MPC approaches, such as Model Predictive Path Integral (MPPI) control, have shown promise in addressing these complex motion planning problems. However, the performance of MPPI relies heavily on the choice of sampling distribution. Existing literature often uses the previously computed input sequence as the mean of a Gaussian distribution for sampling, leading to potential failures and local minima. In this paper, we propose a novel derivation of MPPI that allows for arbitrary sampling distributions to enhance efficiency, robustness, and convergence while alleviating the problem of local minima. We present an efficient importance sampling scheme that combines classical and learning-based ancillary controllers simultaneously, resulting in more informative sampling and control fusion. Several simulated and real-world demonstrate the validity of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2401_09241
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Biased-MPPI: Informing Sampling-Based Model Predictive Control by Fusing Ancillary Controllers
Trevisan, Elia
Alonso-Mora, Javier
Robotics
Motion planning for autonomous robots in dynamic environments poses numerous challenges due to uncertainties in the robot's dynamics and interaction with other agents. Sampling-based MPC approaches, such as Model Predictive Path Integral (MPPI) control, have shown promise in addressing these complex motion planning problems. However, the performance of MPPI relies heavily on the choice of sampling distribution. Existing literature often uses the previously computed input sequence as the mean of a Gaussian distribution for sampling, leading to potential failures and local minima. In this paper, we propose a novel derivation of MPPI that allows for arbitrary sampling distributions to enhance efficiency, robustness, and convergence while alleviating the problem of local minima. We present an efficient importance sampling scheme that combines classical and learning-based ancillary controllers simultaneously, resulting in more informative sampling and control fusion. Several simulated and real-world demonstrate the validity of our approach.
title Biased-MPPI: Informing Sampling-Based Model Predictive Control by Fusing Ancillary Controllers
topic Robotics
url https://arxiv.org/abs/2401.09241