# Autonomous Cars: Vision based Steering Wheel Angle Estimation

## TL;DR

This paper proposes a vision-based system for estimating steering wheel angles in autonomous cars by matching road images with onboard camera images of the steering wheel, reducing dependency on vehicle-specific sensors and training data.

## Contribution

It introduces a novel approach that eliminates the need for vehicle-specific sensors and extensive training data by matching road and steering wheel images directly.

## Key findings

- Reduces reliance on vehicle-specific sensors.
- Avoids the need for extensive training data.
- Uses image matching for steering angle estimation.

## Abstract

Machine learning models, which are frequently used in self-driving cars, are trained by matching the captured images of the road and the measured angle of the steering wheel. The angle of the steering wheel is generally fetched from steering angle sensor, which is tightly-coupled to the physical aspects of the vehicle at hand. Therefore, a model-agnostic autonomous car-kit is very difficult to be developed and autonomous vehicles need more training data. The proposed vision based steering angle estimation system argues a new approach which basically matches the images of the road captured by an outdoor camera and the images of the steering wheel from an onboard camera, avoiding the burden of collecting model-dependent training data and the use of any other electromechanical hardware.