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.
翻译:在本文中,我们对自主车辆的非线性模型预测控制采用了基于学习的视觉动态方法,即LVD-NMPC。 LVD-NMPC使用一个优先过程模型和一个学习的视觉动态模型,用来计算驾驶场的动态、受控系统的预期状态轨迹以及受限预测控制器优化的二次成本函数的加权收益。视觉系统被定义为一个深神经网络,旨在估计图像场景的动态。输入基于感官观测和车辆状态的历史序列,由增强的内存部分整合。深Q学习用于培训深网络,一旦经过培训,就可以用来计算车辆的预期轨迹。我们用标准NMPC执行的基线动态窗口法(DWA)和实验网络神经网络的路径规划对LVD-NPPC进行了评估。在模拟环境中测量了GridSim的性能,在真实世界1:8缩放的模型汽车上,以及在实际大小自动测试飞行器和计算机影像数据集上。