模型預測控制與強化學習

演講摘要

模型預測控制在自動駕駛應用中越來越受歡迎,以提高車輛的回應能力,同時又保有乘客的舒適度。我們將向您展示一個適用於車道跟隨的模型預測控制範例,該範例結合了縱向和橫向控制。

然後,您將學習如何使用 MathWorks 產品進行強化學習,以及如何設置環境模型、定義策略及其各種超參數,以及如何透過平行運算擴展訓練以提高效能。


Model Predictive Control and Reinforcement Learning

Model predictive control is gaining popularity in automated driving applications to improve vehicle responsiveness while maintaining passenger comfort. We will show you an MPC example for a lane following application, which combines longitudinal and lateral control.

Then you will learn how to do reinforcement learning using MathWorks products as well as how to set up your environment models, define the policy and its various hyperparameters, and scale training through parallel computing to improve performance.