Saved in:
Bibliographic Details
Main Authors: Moraes, Pablo, Peters, Christopher, Sodre, Hiago, Moraes, William, Barcelona, Sebastian, Deniz, Juan, Castelli, Victor, Guterres, Bruna, Grando, Ricardo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.07209
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914969075843072
author Moraes, Pablo
Peters, Christopher
Sodre, Hiago
Moraes, William
Barcelona, Sebastian
Deniz, Juan
Castelli, Victor
Guterres, Bruna
Grando, Ricardo
author_facet Moraes, Pablo
Peters, Christopher
Sodre, Hiago
Moraes, William
Barcelona, Sebastian
Deniz, Juan
Castelli, Victor
Guterres, Bruna
Grando, Ricardo
contents This article presents the implementation and evaluation of a behavior cloning approach for route following with autonomous cars. Behavior cloning is a machine-learning technique in which a neural network is trained to mimic the driving behavior of a human operator. Using camera data that captures the environment and the vehicle's movement, the neural network learns to predict the control actions necessary to follow a predetermined route. Mini-autonomous cars, which provide a good benchmark for use, are employed as a testing platform. This approach simplifies the control system by directly mapping the driver's movements to the control outputs, avoiding the need for complex algorithms. We performed an evaluation in a 13-meter sizer route, where our vehicle was evaluated. The results show that behavior cloning allows for a smooth and precise route, allowing it to be a full-sized vehicle and enabling an effective transition from small-scale experiments to real-world implementations.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07209
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Behavior Cloning for Mini Autonomous Car Path Following
Moraes, Pablo
Peters, Christopher
Sodre, Hiago
Moraes, William
Barcelona, Sebastian
Deniz, Juan
Castelli, Victor
Guterres, Bruna
Grando, Ricardo
Robotics
This article presents the implementation and evaluation of a behavior cloning approach for route following with autonomous cars. Behavior cloning is a machine-learning technique in which a neural network is trained to mimic the driving behavior of a human operator. Using camera data that captures the environment and the vehicle's movement, the neural network learns to predict the control actions necessary to follow a predetermined route. Mini-autonomous cars, which provide a good benchmark for use, are employed as a testing platform. This approach simplifies the control system by directly mapping the driver's movements to the control outputs, avoiding the need for complex algorithms. We performed an evaluation in a 13-meter sizer route, where our vehicle was evaluated. The results show that behavior cloning allows for a smooth and precise route, allowing it to be a full-sized vehicle and enabling an effective transition from small-scale experiments to real-world implementations.
title Behavior Cloning for Mini Autonomous Car Path Following
topic Robotics
url https://arxiv.org/abs/2410.07209