Institute of Computer Science
  1. Courses
  2. 2021/22 fall
  3. Autonomous Vehicles Project (LTAT.06.012)
ET
Log in

Autonomous Vehicles Project 2021/22 fall

  • Overview
  • Meetings
  • ADL Project
  • Openpilot Project
  • DeltaX Project
  • Research Project
  • Useful Links

Openpilot

The goal of this project is to implement open-source data collection and training pipeline for comma.ai Openpilot. This involves:

  • implementing custom comma.ai API for data collection,
  • creating high-precision GNSS trajectories with Laika,
  • implementing neural network training,
  • integrating the trained network into Openpilot.

Organization

The students will pick roles in the team:

  • data engineer - data collection and preprocessing trajectories
  • web engineer - comma.ai API, Explorer, Cabana
  • NN engineer - neural network training, Qualcomm SDK for neural network inference
  • device engineer - everything that happens in the device

If there are not enough people, data and web engineer roles can be skipped. In this case the training will be performed on existing comma2k19 dataset.

Schedule

DateTopicPresenterMaterials
8.09.2021Openpilot introTambetTowards a superhuman driving agent
15.09.2021How does Openpilot work?Rustam (video)How does openpilot work?
A Tour Through openpilot
How Do We Control The Car?
Building a Super Human Driving Agent
skippedCAN bus and DBC???Opendbc
How to write a car port for openpilot
Openpilot port guide for Toyota models
Toyota interface used for Lexus
22.09.2021Explorer and CabanaMikeExplorer Web
Explorer GitHub
Cabana Web
Cabana GitHub
29.09.2021Openpilot data formatNikita (slides)Replay driving data
fetch_image_from_route.py
Open Sourcing openpilot Development Tools
Code for training on Openpilot data
6.10.2021comma.ai APIMikecomma API spec
13.10.2021(skipped)  
20.10.2021GNSS postprocessing for high precision trajectoriesNikita (video)comma2k19
Laika
Rednose
Reference Frames in Openpilot
27.10.2021Openpilot driving modelGautamDecoding comma.ai/openpilot
End-to-end lateral planning
Reverse engineer openpilot
Extracted standalone Openpilot model
Code for training on Openpilot data
Building a Super Human Driving Agent
3.11.2021Running Openpilot against CarlaRustamRun openpilot in the driving simulator CARLA
Openpilot in simulator
10.11.2021Qualcomm Neural Processing SDKGautamDecoding comma.ai/openpilot
Qualcomm Neural Processing SDK for AI
17.11.2021Joystick steering test???Debug car controls
Open Sourcing openpilot Development Tools
24.11.2021Running Openpilot from laptop with webcam???Self-Driving Car For Free
Run openpilot with webcam on PC/laptop
1.12.2021   
8.12.2021   
15.12.2021   
22.12.2021Project demo  

Links

Other useful sources of information:

  • Openpilot wiki
  • comma.ai blog
  • comma.ai Discord
  • comma.ai YouTube channel, including COMMA_CON presentations
  • George Hotz YouTube channel

Deliverables

  • Each student should present one topic to others. The presentation should include live demo.
  • All students together should train one neural network model and demonstrate it driving in comma two device. The driving does not have to be perfect. Either self-collected data or comma2k19 dataset can be used for training.

Contact

Autonomous Driving Lab (room 3095)
Tambet Matiisen
tambet.matiisen@ut.ee

  • Institute of Computer Science
  • Faculty of Science and Technology
  • University of Tartu
In case of technical problems or questions write to:

Contact the course organizers with the organizational and course content questions.
The proprietary copyrights of educational materials belong to the University of Tartu. The use of educational materials is permitted for the purposes and under the conditions provided for in the copyright law for the free use of a work. When using educational materials, the user is obligated to give credit to the author of the educational materials.
The use of educational materials for other purposes is allowed only with the prior written consent of the University of Tartu.
Terms of use for the Courses environment