Optimize AI for Speed and Robustness in the Lab

Aus HSHL Mechatronik
Zur Navigation springen Zur Suche springen

Optimization of the AI

For better Ai operation, we need to have the best optimal hardware and software settings.

Jetracer Optimization

Waveshare has a couple sets of examples using JupyterLab with Python libraries to Operate Ai operations with the Jetracer. To Experiment these examples, clone this repository into you jetracer: [1].

  1. Gamepad(Teleoperation)[2]:

The challenge here was to control the Jetracer with a gamepad through Matlab. This method was not possible because; 1. The gamepad's adapter must be plug into the jetson nano, 2. Gamepad uses python library before it functions with the jetracer properlly, 3. Matlab cannot be installed on jetracer[3] since it is an arm processor (aarch64)[4]. Hence, making is difficult to control it directlly from matlab

  1. Camera:

Data Collection

choosing optimal configuration for best possible data collection to optimize ai:

  1. Speed:
  2. Steering:
  3. Video format:
  4. Image size:
Abgerufen von „https://wiki.hshl.de/wiki/index.php?title=Optimize_AI_for_Speed_and_Robustness_in_the_Lab&oldid=135233“