Welcome to my Final Year Project as an undergraduate, the aim of this project is to have a semi autonomous vehicle that naturally has the ability to toggle between assisted. This will be done utilising a Pi 4, Coral TPU and explorerHAT Pro.

• Create a Raspberry Pi RC Car
• Provide a suitable GUI control
• Include autonomous driving elements, utilising computer vision
• Provide suitable security

Some of the above aren't exactly what I bought and in some cases I had parts laying around from previous projects. This is just a guide to what you may need if you fully recreate.

I have had a lot of help from a friend designing a chassis to fit the items I've accumilated, you can use whatever you want for your body... but the CAD models and designs will be displayed within a folder shortly.

As noted in my 2nd report, an Issue was running the Object detection model as well as onboard camera display using the same input. A simple workaround was using two cameras and mounting the second on top.

Step 1: Install Coral TPU - https://coral.ai/docs/accelerator/get-started/

echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add - sudo apt-get update

sudo apt-get install libedgetpu1-std

Step 2: Install TF for Python - https://www.tensorflow.org/lite/guide/python

pip3 install https://dl.google.com/coral/python/tflite_runtime-2.1.0.post1-cp37-cp37m-linux_armv7l.whl

Step 3: Check Installs by running a model

mkdir coral && cd coral git clone https://github.com/google-coral/tflite.git

cd tflite/python/examples/classification bash install_requirements.sh

python3 classify_image.py
--model models/mobilenet_v2_1.0_224_inat_bird_quant_edgetpu.tflite
--labels models/inat_bird_labels.txt
--input images/parrot.jpg

Step 1:

Enable i2c, SSH, Camera and VNC in Raspberry Pi config.

Step 2:

Download the project if you haven't already.

Step 3:

Unzip

Step 4:

Navigate to the directory (/DriveAwAI-Nathanlloyd7) through terminal, here you can find the requirements doc. Then Run
pip install --user --requirement Requirements.txt

Step 5:

Run main: default password on SenseHat PIN password = 4321. Have fun with your new car