Waymo Driverless Car Data Analysis and Driving Modeling using CNN and LSTM

TL;DR

This paper explores predicting autonomous vehicle acceleration using Waymo's dataset by applying CNNs to mimic human actions and LSTMs to handle the temporal sequence of driving data, advancing self-driving car decision models.

Contribution

It introduces a novel combination of CNN and LSTM models specifically for acceleration prediction in autonomous driving using real-world data.

Findings

CNN effectively mimics human driving actions

LSTM captures temporal dependencies in driving data

Model achieves promising accuracy in acceleration prediction

Abstract

Self driving cars has been the biggest innovation in the automotive industry, but to achieve human level accuracy or near human level accuracy is the biggest challenge that research scientists are facing today. Unlike humans autonomous vehicles do not work on instincts rather they make a decision based on the training data that has been fed to them using machine learning models using which they can make decisions in different conditions they face in the real world. With the advancements in machine learning especially deep learning the self driving car research skyrocketed. In this project we have presented multiple ways to predict acceleration of the autonomous vehicle using Waymo's open dataset. Our main approach was to using CNN to mimic human action and LSTM to treat this as a time series problem.