Understand the Existing System Framework

Hardware Setup And Requirement

Tabelle 1: Software and Hardware Requirements

#	Name	Description
1	External PC	Matlab will be installed and Gpu for training
2	Jetracer TX1	Camera senor, game pad, AI chip, external monitor, mouse and keyboard (to access the software)
3	SD Card	16Gb SD-cerd and SD-card reader
4	Matlab	Version compatible with cuda 10.2 [1]
5	Jetpack SDK 4.6.1	Flash software with balenaEtcher on SD-cerd

Setup

• For the setup of Jetracer hardware it can be easily done following the manual [2], [3] and assemble it [4] .
• For Matlab, install the following AdOns:

Connect MATLAB & JETRACER

Jetracer Setup

• Connect JETRACER with a computer with HDMI, mouse, ethernet cable and keyboard.
• It will bring default Linux version and keep procced to setup. Keep username = jetracer & password = jetson during setup.
• After setup open the command window and give command ifconfig to get the Ip address of Jetracer.
• If connection is via WLAN the Ip will change and change accordingly.
• Install PuTTY on pc to use SSH key

Library to be installed

• Install the following adons in matlab

Tabelle 2: Matlab Setup Requirements

#	Name	Description
1	Matlab Adons installation

• Download and open the terminal locally or on PuTTY to install these libraries :

Tabelle 3: Download And Installation Requirements

#	Name	Download	Description	command
1	install sdl 1.2 version.		Cuda development libraries	sudo apt-get update sudo apt-get install libsdl1.2-dev
2	Install the CUDA repo metadata	Link [5]	If There's any package error, use this link [6]
3	Install "CuDNN"	cuDNN link[7]	CuDNN link[8]
4	add Path		it should look like this[9]	# Add CUDA bin & library paths export PATH=/usr/local/cuda-10.2/bin:$PATH export LD_LIBRARY_PATH=/usr/local/cuda-10.2/lib64:$LD_LIBRARY_PATH source ~/.bashrc
5	nvcc errors		Here were the errors i had and thiere solutions [10]

Results

Tabelle 4: Results

#	Overview	matlab	jetracer
1