The sixth meetup of WSDC group was held in Space from Facebook in Warsaw, Poland on 10th of February 2020. We meet to discuss about the current state of the art solutions in self-driving, share our experiences and show what we do. During this meetup we had 3 presentations by our members:
Can a robot race like a pro? State of the art of high-velocity vehicle control – Adam Gotlib
Adam Gotlib talked about autonomous racing.
Videos used in the presentation:
- Tyre slip angle
- Stanford’s autonomous car, Shelley, speeds around track without driver
- The World’s FATEST Autonomous Car | Robocar Guiness World Records | Roborace
- Beyond the Limits: MARTYkhana
- ORCA – MPCC with static and dynamic obstacle avoidance
- Learning-based motion planning for AMZ Driverless
- GT AutoRally: Aggressive Driving with MPPI Control Overview
- Autonomous vehicle control at the limits of handling
- Towards Automated Vehicle Control Beyond the Stability Limits: Drifting Along a General Path
- Optimization-Based Autonomous Racing of 1:43 Scale RC Cars
- Learning-based Model Predictive Control for Autonomous Racing
- Aggressive driving with model predictive path integral control
From zero to simple self-driving car using DonkeyCar – Michał Sochoń
Michał Sochoń talked about his own experience with DonkeyCar. He is a Senior Systems and Network Engineer, helping within a team and organization in overall automation, especially in CI/CD integration, managing and helping from moving from testing to production systems idependently if it is on-premise, hybrid or pure cloud setup. He always wanted to have a RC car and also was recently getting interested with ML/AI, but never had time to even start it. By coincidence he discovered DonkeyCar project, which integrates both technologies, but in the pricing range of a hobby and not a full-time job. In his presentation we will be able to get more details how to start with self-driving car in 1:16 scale from complete zero.
Training a neural network for driving an autonomous RC car – Maciej Dziubiński
Maciej Dziubiński presented a RC-based model of an autonomous car that can drive around a pond next to my house. The main sensor is an Intel D435i depth camera (IMU included) and the main computational unit is the Jetson TX1 which has a GPGPU which I utilized for faster inference. The car is controlled by a tiny convnet (trained on low-res depth images) that yields predictions in 3.5 ms (on average). The presentation will be in a form of Q&A where I’ll try to answer questions like:
- how to build a car like this?
- where to look for resources / inspirations?
- what limitations should one be aware of before starting?
- what else can one do with a simple model like this?
- and, hopefully, other questions from the participants of the talk.
The presentation is an extension / discussion of a blog post published on Medium: