Understand the Existing System Framework: Unterschied zwischen den Versionen

Aus HSHL Mechatronik
Zur Navigation springen Zur Suche springen
← Zum vorherigen Versionsunterschied
Evrard.leuteu-feukeu@stud.hshl.de (Diskussion | Beiträge)
wiki-autoren
413 Bearbeitungen
Keine Bearbeitungszusammenfassung
Evrard.leuteu-feukeu@stud.hshl.de (Diskussion | Beiträge)
wiki-autoren
413 Bearbeitungen
Keine Bearbeitungszusammenfassung
 
(21 dazwischenliegende Versionen desselben Benutzers werden nicht angezeigt)
Zeile 1: Zeile 1:
== Hardware Setup And Requirement ==
== Hardware Setup And Requirement ==
{| class="wikitable"
{| class="wikitable"
|+ Tabelle 1: SoftwareRequirements
|+ Tabelle 1: Software and Hardware Requirements
|-
|-
! # !! Name !! Description
! # !! Name !! Description
Zeile 9: Zeile 9:
| 2 || Jetracer TX1 || Camera senor, game pad, AI chip, external monitor, mouse and keyboard (to access the software)  
| 2 || Jetracer TX1 || Camera senor, game pad, AI chip, external monitor, mouse and keyboard (to access the software)  
|-
|-
| 3 || Image Writer ||   balenaEtcher auf SD-Karte reader
| 3 || SD Card || 16Gb SD-cerd and SD-card reader
|-
| 4 || Matlab || Version compatible with cuda 10.2 [https://www.mathworks.com/help/releases/R2021b/parallel-computing/gpu-support-by-release.html]
|-
| 5 || [https://developer.nvidia.com/embedded/jetpack-sdk-461 Jetpack SDK 4.6.1] ||  Flash software with balenaEtcher on SD-cerd
|}
|}


=== Setup ===
=== Setup ===
* For the setup of Jetracer hardware it can be easily done following the manual [https://www.waveshare.com/w/upload/f/fa/Jetracer_pro_Assembly_EN.pdf], [[https://wiki.hshl.de/wiki/index.php/JetRacer:_Teach-In_Tutorial]] and assemble it [https://youtu.be/Mn2QYPFADdo] .
* For the setup of Jetracer hardware it can be easily done following the manual [https://www.waveshare.com/w/upload/f/fa/Jetracer_pro_Assembly_EN.pdf], [https://wiki.hshl.de/wiki/index.php/JetRacer:_Teach-In_Tutorial] and assemble it [https://youtu.be/Mn2QYPFADdo] .
*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 <code> username = jetracer & password = jetson</code> during setup.
* After setup open the command window and give command <code>ifconfig</code> 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
[[Datei:PuTTY configuration.png|mini|Fig. 1: PuTTY Configuration]]
 
 
 
=== Library to be installed ===
* Install the following adons in matlab
{| class="wikitable"
|+ Tabelle 2:  Matlab Setup Requirements
|-
! # !! Name !! Description
|-
| 1 || Matlab Adons installation || [[Datei:Matlab adons.png|mini|Fig. 2: Matlab Add-ons List]]
|}


== Software Setup And Requirement ==
* Download and open the terminal locally or on PuTTY to install these libraries :
=== Requirements ===
{| class="wikitable"
{| class="wikitable"
|+ Tabelle 1: SoftwareVorbereitung
|+ Tabelle 3: Download And Installation Requirements
|-
|-
! # !! Quelle !! Beschreibung !! Dauer
! # !! Name !! Download !! Description !! command
|-
|-
| 1 || [https://developer.nvidia.com/embedded/jetpack-sdk-461 Jetpack SDK 4.6.1] || Image herunterladen || 5&#8239;min
| 1 || install sdl 1.2 version. || || Cuda development libraries || <code> sudo apt-get update</code>    <code>sudo apt-get install libsdl1.2-dev</code>
|-
|-
| 2 || [https://etcher.balena.io/ balenaEtcher] || Image Writer herunterladen || 2&#8239;min
| 2 || Install the CUDA repo metadata || Link [https://elinux.org/Jetson/Installing_CUDA] || If There's any package error, use this link [https://forums.developer.nvidia.com/t/solution-dpkg-error-processing-package-nvidia-l4t-bootloader-configure/208627]  ||  
|-
|-
| 3 || Image schreiben || Image mit balenaEtcher auf SD-Karte schreiben || 45&#8239;min
| 3 || Install "CuDNN" || cuDNN link[https://developer.nvidia.com/rdp/cudnn-archive]  || CuDNN link[https://de.mathworks.com/help/gpucoder/ref/gpucodersetup-app.html] ||
[[Datei:CuDDN.jpg|mini|Fig. 3: CuDDN]]
|-
| 4 || add Path||      || it should look like this[https://wiki.hshl.de/wiki/index.php/Datei:Screenshot_2024-07-18_144029.jpg]  || 
  # 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
 
|-
|-
| 4 || Image verifizieren || Dieser Punkt kann ggf. übersprungen werden. || 45&#8239;min
| 5 || nvcc errors || || Here were the errors i had and thiere solutions [https://wiki.hshl.de/wiki/index.php/Diskussion:JetRacer:_Spurführung_mit_künstlicher_Intelligenz] ||
|}
|}
* For Jetracer use the jetpack 4.6.1 [https://developer.nvidia.com/embedded/jetpack-sdk-461] which is supported by MATLAB latest version.


* For Software setup firstly the Jetracer which has the Jetracer AI Kit on SD card to set it up and all the config. which the full process can be found in [https://www.waveshare.com/wiki/JetRacer_AI_Kit].
== Results ==
 
{| class="wikitable"
* MATLAB also is been installed on the local device to operate and manage the Jetracer. Then the addon package of [https://de.mathworks.com/hardware-support/nvidia-jetson.html nvidia-jetson] is also installed for the hardware package. Various other package also been installed for this project such as [https://de.mathworks.com/products/deep-learning.html Deep-learning], [https://de.mathworks.com/products/computer-vision.html computer-vision], also [https://de.mathworks.com/solutions/gpu-computing.html gpu-computing].
|+ Tabelle 4: Results
 
|-
=== Matlab Setup ===
! # !! Overview !! matlab !! jetracer
 
|-
 
| 1 || [[Datei:Matlabssh.png|mini|Fig. 4: Matlab Ssh]] || [[Datei:Matlab connection.png|mini|Fig. 5: Matlab Connection]] ||
=== Jetracer Setup ===
[[Datei:Jetsonpic.jpg|mini|Fig. 6: Jetson Ssh Panel]]
|}

Aktuelle Version vom 12. Juni 2025, 20:40 Uhr

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
Fig. 1: PuTTY Configuration


Library to be installed

  • Install the following adons in matlab
Tabelle 2: Matlab Setup Requirements
# Name Description
1 Matlab Adons installation
Fig. 2: Matlab Add-ons List
  • 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]
Fig. 3: CuDDN
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
Fig. 4: Matlab Ssh
Fig. 5: Matlab Connection
Fig. 6: Jetson Ssh Panel
Abgerufen von „https://wiki.hshl.de/wiki/index.php?title=Understand_the_Existing_System_Framework&oldid=136309“