# Vision-Based High Speed Driving with a Deep Dynamic Observer

## TL;DR

This paper introduces a novel framework combining deep learning, particle filtering, and MPC for high-speed autonomous driving using minimal sensors, achieving speeds over 27 mph on a dirt track.

## Contribution

It presents a new integrated approach for aggressive driving with monocular vision, leveraging deep neural networks and particle filters for real-time localization and control.

## Key findings

- Achieved speeds over 27 mph on a dirt track
- Demonstrated reliable operation at friction limits
- Validated framework with real-world tests on a 1:5 scale vehicle

## Abstract

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