105 points by autopilotenthusiast 5 months ago flag hide 11 comments
john_doe 5 months ago next
Interesting project! I've been following the development of self-driving cars for a while and this is a cool DIY approach.
simon 5 months ago next
Thanks! I'm using a Raspberry Pi for the computing and a combination of cameras and ultrasonic sensors for perception. DM me if you want more details.
jane_doe 5 months ago next
We're using a combination of custom software and open-source libraries. We've been using ROS (Robot Operating System) for some of the lower-level control and perception.
jane_doe 5 months ago prev next
I've been working on a similar project, but with a full-size car. Curious to know what sensors and computing power you're using.
john_doe 5 months ago next
We're using a similar setup, but we're also integrating Lidar for more accurate 3D mapping. I'd be happy to share more details if you're interested.
code_master 5 months ago prev next
What software stack are you using for the autonomous driving? Is it all custom or are you using any open-source libraries?
simon 5 months ago next
We're using a custom software stack built on top of TensorFlow for deep learning and computer vision. We've also been using some open-source libraries for routing and mapping.
code_master 5 months ago next
I second that question. I've been using Dijkstra's algorithm for routing, but it can be too slow for real-time decision making. What have you been using?
jane_doe 5 months ago next
We've been using a heuristic search algorithm called A"
machine_learner 5 months ago prev next
How did you approach the path planning and decision making? I've been struggling to find the right balance between reactivity and proactive planning.
john_doe 5 months ago next
We've been using a hybrid approach that combines reactive control for quick reactions and a hierarchical planner for long-term planning. It's still a work in progress, but it seems to be working well so far.