Hello, and welcome! This week, I wrapped up work on the blog and began working on the ML-Rover project.

I started the week by refining the blog, adding dark mode, and making a few minor improvements. For now, the blog is complete, except for the weekly post summarizing my coding progress.

Dark mode:

I felt the need to refresh my understanding of CNN concepts, so I watched a couple of videos on the topic and revisited the ImageNet Classification with Deep Convolutional Neural Networks paper by Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton.

Now seems like a good time to mention that I use the Cursor editor—the AI integration is a really cool feature!

For the ML-Rover, my goal is to create multiple AI models, each serving a specific purpose, to create a fully integrated and advanced AI system for the rover.

Here are some of the models I plan to build:

• computer vision projects –> object detection
• driving behavior cloning
• autonomous navigation with deep reinforcement learning
• visual SLAM (simultaneous localization and mapping)
• voice command navigation
• dynamic path planning
• imitation learning with style transfer –> aggressive, cautious, smooth