学習ベース視覚ダイナミクスによる非線形モデル予測制御
LVD-NMPC: A Learning-based Vision Dynamics Approach to Nonlinear Model Predictive Control for Autonomous Vehicles
深層強化学習で画像シーンのダイナミクスを学習し、非線形モデル予測制御の目標軌道とコスト重みを算出する自動運転手法を提案し、実車両とデータセットで評価した。
著者: Sorin Grigorescu, Cosmin Ginerica, Mihai Zaha, Gigel Macesanu, Bogdan Trasnea
分類: cs.RO, cs.SY, eess.SY
原文アブストラクト
In this paper, we introduce a learning-based vision dynamics approach to nonlinear model predictive control for autonomous vehicles, coined LVD-NMPC. LVD-NMPC uses an a-priori process model and a learned vision dynamics model used to calculate the dynamics of the driving scene, the controlled system's desired state trajectory and the weighting gains of the quadratic cost function optimized by a constrained predictive controller. The vision system is defined as a deep neural network designed to estimate the dynamics of the images scene. The input is based on historic sequences of sensory observations and vehicle states, integrated by an Augmented Memory component. Deep Q-Learning is used to train the deep network, which once trained can be used to also calculate the desired trajectory of the vehicle. We evaluate LVD-NMPC against a baseline Dynamic Window Approach (DWA) path planning executed using standard NMPC, as well as against the PilotNet neural network. Performance is measured in our simulation environment GridSim, on a real-world 1:8 scaled model car, as well as on a real size autonomous test vehicle and the nuScenes computer vision dataset.
