arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.07563cs.MScs.DCcs.ROcs.SYeess.SY
收藏

MPPI-Generic:一种用于随机轨迹优化的CUDA库

MPPI-Generic: A CUDA Library for Stochastic Trajectory Optimization

Autonomous Control and Decision Systems Lab, Georgia Institute of Technology(自主控制与决策系统实验室,佐治亚理工学院)

Bogdan Vlahov, Jason Gibson, Manan Gandhi, Evangelos A. Theodorou

AI总结:

MPPI-Generic是一种用于随机轨迹优化的CUDA库,提供多种模型预测控制算法,并支持自定义动态模型和成本函数,展示了其在GPU上的高效计算能力。

摘要:

本文介绍了一种名为MPPI-Generic的新C++/CUDA库,用于加速随机优化的GPU计算。该库提供了模型预测路径积分控制、管状模型预测路径积分控制以及鲁棒模型预测路径积分控制的实现,并允许这些算法在多种已有的动态模型和成本函数上使用。此外,研究人员可以根据我们的API定义创建自己的动态模型或成本函数,而无需修改实际的模型预测路径积分控制代码。最后,我们通过各种GPU对模型预测路径积分控制的其他流行实现进行计算性能比较,以展示该库能够提供的实时能力。库代码可在:https://acdslab.github.io/mppi-generic-website/ 上找到。

英文摘要:

This paper introduces a new C++/CUDA library for GPU-accelerated stochastic optimization called MPPI-Generic. It provides implementations of Model Predictive Path Integral control, Tube-Model Predictive Path Integral Control, and Robust Model Predictive Path Integral Control, and allows for these algorithms to be used across many pre-existing dynamics models and cost functions. Furthermore, researchers can create their own dynamics models or cost functions following our API definitions without needing to change the actual Model Predictive Path Integral Control code. Finally, we compare computational performance to other popular implementations of Model Predictive Path Integral Control over a variety of GPUs to show the real-time capabilities our library can allow for. Library code can be found at: https://acdslab.github.io/mppi-generic-website/ .

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑