Aggressive Deep Driving: Model Predictive Control with a CNN Cost Model
This addresses the challenge of vision-based control for aggressive driving in autonomous vehicles, though it appears incremental as it combines existing methods like CNNs and MPC.
The paper tackles the problem of high-speed autonomous driving by using a deep convolutional neural network to predict cost maps from monocular video for model predictive control, achieving aggressive driving on a 1:5 scale vehicle.
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.