Aggressive Deep Driving: Model Predictive Control with a CNN Cost Model

Abstract

We present a framework for vision-based model predictive control (MPC) for the task of aggressive, high-speed autonomous driving. Our approach uses deep convolutional neural networks to predict cost functions from input video which are directly suitable for online trajectory optimization with MPC. We demonstrate the method in a high speed autonomous driving scenario, where we use a single monocular camera and a deep convolutional neural network to predict a cost map of the track in front of the vehicle. Results are demonstrated on a 1:5 scale autonomous vehicle given the task of high speed, aggressive driving.

11 pages, 7 figures

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• End to End Learning for Self-Driving Cars
• DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving

Cited by in corpus (7)

• A Survey of Deep Learning Techniques for Autonomous Driving
• A Survey of End-to-End Driving: Architectures and Training Methods
• A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
• Learning Autonomous Race Driving with Action Mapping Reinforcement Learning
• Agile Autonomous Driving using End-to-End Deep Imitation Learning
• Coupled Longitudinal and Lateral Control of a Vehicle using Deep Learning
• Acting upon Imagination: when to trust imagined trajectories in model based reinforcement learning