End to End Learning based Self-Driving using JacintoNet

Viswanath, Prashanth; Nagori, Soyeb; Mody, Mihir; Mathew, Manu; Swami, Pramod

doi:10.1109/icce-berlin.2018.8576190

Cited by 19 publications

(7 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pionerring work of (Pomerleau (1988)) intoduced IL for self-driving -where a direct mapping from the sensor data to steering angle and acceleration is learned. (Zeng et al (2019); Viswanath et al (2018)) also follow the similar approach of going from sensor data to throttle and steering. With the advent of high end driving simulators like (Dosovitskiy et al (2017)), approaches like (Codevilla et al (2018)) exploit conditional models with additional exploit conditional models with additional high-level commands such as continue, turn-left, turn-right.…”

Section: Related Workmentioning

confidence: 99%

Bridging Sim2Real Gap Using Image Gradients for the Task of End-to-End Autonomous Driving

Nair¹,

Sharma²,

Parihar³

et al. 2022

Preprint

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Bridging Sim2Real Gap Using Image Gradients for the Task of End-to-End Autonomous Driving

Nair¹,

Sharma²,

Parihar³

et al. 2022

Preprint

View full text Add to dashboard Cite

“…The movement of the robot in the traffic lane is addressed in recognition using a convolutional neural network (CNN) to achieve end-to-end training. End-to-end platform [21,22], a new model for self-driving cars (i.e., autonomous cars), was presented as a brain-inspired cognitive model with attention (CMA). This model functions to simulate the operation of the human brain.…”

Section: Recognition Using a Convolutional Neural Networkmentioning

confidence: 99%

“…The computer vision techniques used in autonomous robots are important for object detection [16,17] in conjunction with a human operator. Computer vision techniques have been used in various models of autonomous robots, such as road data collection [18][19][20][21][22][23][24] and target tracking [25][26][27][28]. However, although using autonomous robots to help manage an inventory system is beneficial, path planning is also required for this task.…”

Section: Introductionmentioning

confidence: 99%

An Intelligent Autonomous Document Mobile Delivery Robot Using Deep Learning

Ganokratanaa

Ketcham

2022

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

This paper presents an intelligent autonomous document mobile delivery robot using a deep learning approach. The robot is built as a prototype for document delivery service for use in offices in which it can adaptively move across different surfaces, such as terrazzo, canvas, and wooden. In this work, we introduce a convolutional neural network (CNN) to recognize the traffic lanes and the stop signs with the assumption that all surfaces have identical traffic lanes. We train the model using a custom indoor traffic lane and stop sign dataset with the label of motion directions. CNN extracts a direction-of-motion feature to estimate the robot's direction and to stop the robot based on an input image monocular camera view. These predictions are used to adjust the robot's direction and speed. The experimental results show that this robot can move across different surfaces along with the same structured traffic lanes, achieving the model accuracy of 96.31%. The proposed robot helps to facilitate document delivery for office workers, allowing them to work on other tasks more efficiently.

show abstract

“…The generation of discrete variables by a machine learning algorithm is known as regression and is a widely studied problem [28]. Regression models for DNN use the gradient descent function to search for the optimal weights that minimize the loss function.…”

Section: Deep Learning End-to-end Architectures Classificationmentioning

confidence: 99%

End-to-End Deep Neural Network Architectures for Speed and Steering Wheel Angle Prediction in Autonomous Driving

et al. 2021

View full text Add to dashboard Cite

The complex decision-making systems used for autonomous vehicles or advanced driver-assistance systems (ADAS) are being replaced by end-to-end (e2e) architectures based on deep-neural-networks (DNN). DNNs can learn complex driving actions from datasets containing thousands of images and data obtained from the vehicle perception system. This work presents the classification, design and implementation of six e2e architectures capable of generating the driving actions of speed and steering wheel angle directly on the vehicle control elements. The work details the design stages and optimization process of the convolutional networks to develop six e2e architectures. In the metric analysis the architectures have been tested with different data sources from the vehicle, such as images, XYZ accelerations and XYZ angular speeds. The best results were obtained with a mixed data e2e architecture that used front images from the vehicle and angular speeds to predict the speed and steering wheel angle with a mean error of 1.06%. An exhaustive optimization process of the convolutional blocks has demonstrated that it is possible to design lightweight e2e architectures with high performance more suitable for the final implementation in autonomous driving.

show abstract

End to End Learning based Self-Driving using JacintoNet

Cited by 19 publications

References 2 publications

Bridging Sim2Real Gap Using Image Gradients for the Task of End-to-End Autonomous Driving

Bridging Sim2Real Gap Using Image Gradients for the Task of End-to-End Autonomous Driving

An Intelligent Autonomous Document Mobile Delivery Robot Using Deep Learning

End-to-End Deep Neural Network Architectures for Speed and Steering Wheel Angle Prediction in Autonomous Driving

Contact Info

Product

Resources

About