Vision-Based High Speed Driving with a Deep Dynamic Observer
This addresses the problem of vision-based aggressive driving in off-road environments for autonomous vehicle systems, representing a strong specific gain but not a new paradigm.
The paper tackled high-speed autonomous driving on a dirt track using only a monocular camera, IMU, and wheel speed sensors, achieving speeds above 27 mph (12 m/s) on a 32-meter straight with reliable operation at friction limits.
In this paper we present a framework for combining deep learning-based road detection, particle filters, and Model Predictive Control (MPC) to drive aggressively using only a monocular camera, IMU, and wheel speed sensors. This framework uses deep convolutional neural networks combined with LSTMs to learn a local cost map representation of the track in front of the vehicle. A particle filter uses this dynamic observation model to localize in a schematic map, and MPC is used to drive aggressively using this particle filter based state estimate. We show extensive real world testing results, and demonstrate reliable operation of the vehicle at the friction limits on a complex dirt track. We reach speeds above 27 mph (12 m/s) on a dirt track with a 105 foot (32m) long straight using our 1:5 scale test vehicle. A video of these results can be found at https://www.youtube.com/watch?v=5ALIK-z-vUg