Open Source Self Driving Race Cars Powered by @tensorflow. Join the community at https://xitter.cf/t.co/TJMu1fA3VB
The Race Track
Joined August 2018
- Tweets236
- Following40
- Followers1.4K
- Likes334
Donkey Car retweeted
Our next @diyrobocars event will be an AI navigation hackathon at @circuitlaunch in Oakland on Sun. Aug 30.
You bring a small autonomous car of any sort (Donkeycar is a good start, but anything with a camera will do) and then over the course of the day you'll figure out how to use AI to help it navigate the city.
There will be "roads" with signs and intersections. First to make it from one side to the other wins!
luma.com/rzb0plq0 via @LumaHQ
Donkeycar release 5.3 is out and performing well. Switches to TFlite (AKA LiteRT) for significantly improved inference performance on the Pi.
Next version, coming in a few weeks, will support latest @Raspberry_Pi OS (Trixie) and Python 3.13
github.com/autorope/donkeyca…
If you're looking for a smaller car for smaller tracks, consider the LaTrax 1:18 scale ones, which work great with the Donkeycar RC hat
diyrobocars.com/2026/01/20/a…
If you're looking for a RC car to use with Donkeycar, the 1:18 scale LaTrax Rally is the right size for smaller tracks and works great with the RC Hat
diyrobocars.com/product/rc-h…
amzn.to/45jWFDD
Our next race is Feb 21 at UCSD: meetup.com/diyrobocars/event…
Too cold and rainy for outdoor racing? Donkeycar is about to support tiny 1:28 scale cars, too! Full end-to-end neural network autonomous driving with a RaspberryPi Zero 2 W, for less than $150 all told.
Coming in January
Donkey Car retweeted
Come see the autonomous car racing this weekend in booth J8 at @opensauce with the @donkey_car @diyrobocars teams
If you are at Open Sauce today or tomorrow, visit the Donkey Car track - if you are not, you can check out the live stream on twitch
twitch.tv/roboticists
Donkey Car retweeted
For every 10 likes this gets, I will ask ChatGPT to make more data go into this Lakehouse
Donkey Car retweeted
Today, more than 80% of the table metadata updates on Databricks are AI-assisted. It took 2 engineers, 1 month, and less than $1000 in compute cost to develop the custom LLM for this task. databricks.com/blog/creating…
Donkey Car retweeted
Sad about the chaos around OpenAI, which was crazier than anyone imagined, and how it’s affecting people, especially those on visas. I hope everyone lands on their feet!
Donkey Car retweeted
At Replit, we extensively use Spark on Databricks for all our training data work.
We run highly customized transformations on code like parsing, deduping, PII redaction, code filtering, tokenization, and more, written with low-level Spark primitives.
High quality data is key.
Donkey Car retweeted
Lots of people are wondering whether #GPT4 and #ChatGPT's performance has been changing over time, so Lingjiao Chen, @james_y_zou and I measured it. We found big changes including some large decreases in some problem-solving tasks: arxiv.org/pdf/2307.09009.pdf
Donkey Car retweeted
MPCC
Simulation environments in C++ and Matlab of the Model Predictive Contouring Controller (MPCC) for Autonomous Racing developed by the Automatic Control Lab (IfA) at ETH Zurich
github.com/alexliniger/MPCC
Donkey Car got a nice mention in @tomshardware tomshardware.com/news/donkey…
Donkey Car retweeted
Insightful benchmark of Linux Foundation Delta Lake and Apache Iceberg by @BrooklynData that shows Delta is up to 8x faster in workloads with data updates. Most storage benchmarks only test reads, but with updates, care is needed to maintain performance. brooklyndata.co/blog/benchma…
