This week I focused on trying to finalise the design details of our project. After our presentation, we reconsidered the possibility of using LIDAR in our project, and decided against it. The reason for this is cheap LIDAR sensors don’t produce rich enough point maps to make meaningful object detection decisions. The good object detection algorithms require heavy computation and high quality point maps which isn’t possible with the hardware we are planning on getting. Instead we researched and found out a way of manipulating PS4 cameras to work with Python and OpenCV to perform depth calculations. We are heavily considering using this as an alternative to buying Intel Depth cameras since they are expensive.
Aside from this, I also looked into IMU units and found that the BMI160 IMU is compatible with the NVIDIA Jetson Nano. The communication is done with I2C, but supports SPI for faster data transfers. I looked into how setting up SPI would work, since we would want accelerometer and gyroscope information from the IMU fairly often in order to successively communicate with the following car. I also researched a bit on integration and it appears to be fairly straightforward since the BMI160 communicates via MMIO
Moving forward, we want to research more into outfitting the PS4 camera with the Jetson Nano and seeing if the tutorial on getting depth sensing to work is accurate enough. I also plan to look more into algorithms that can do object detection without needing to default to colour filters and painting all our obstacles the same colour.