Arvutiteaduse instituut
  1. Kursused
  2. 2020/21 sügis
  3. Isejuhtivate sõidukite projekt (LTAT.06.012)
EN
Logi sisse

Isejuhtivate sõidukite projekt 2020/21 sügis

  • Overview
  • Meetings
  • DeltaX Track
  • Research Track
  • ADL Track
  • Links

ADL Track

Autonomous Driving Lab has a cooperation project with Bolt to evaluate the state of self-driving technology. Bolt has sponsored us to buy a Lexus RX450h vehicle fully equipped with sensors and drive-by-wire technology.

As part of that project we are trying to make our test car to drive in real city traffic. We chose Autoware.AI open-source software as a basis for that experiment, for its use of already established technologies (ROS) and large user community.

In practice we have experienced many difficulties and bugs with Autoware, especially with its planner component called OpenPlanner. Therefore we would like to evaluate other open-source options for self-driving.

In this course you will have hands-on experience with one open-source self-driving software. As part of that, you will also learn some theoretical background in autonomous vehicle design and operation. We have chosen following softwares for the evaluation:

  • Autoware.Auto (new version of Autoware)
  • Baidu Apollo
  • NVidia DriveWorks
  • Comma.ai Openpilot

Organization

The course is organized such that we will divide students into teams and each team will take one software (if we have too few students, we can skip some of the softwares). Each of the softwares has accompanied online lectures that each team should watch independently. Every week we have a class meeting dedicated on one topic. Everybody should watch the lecture on the topic at home or preferably together with the team. One student prepares a test on the topic for others. In class we all take the test and after the test there is discussion of right answers.

The online materials to learn from are as follows:

  • Autoware.Auto: https://www.autoware.org/awf-course
  • Baidu Apollo: https://apollo.auto/devcenter/devcenter.html
  • NVidia DriveWorks: https://developer.nvidia.com/drive/training
  • Comma.ai Openpilot: https://medium.com/@comma_ai,
    https://medium.com/@chengyao.shen/decoding-comma-ai-openpilot-the-driving-model-a1ad3b4a3612,
    https://arxiv.org/abs/2003.06404

Each team is assigned a supervisor from Autonomous Driving Lab.

Teams

 Autoware.AutoBaidu Apollo
TeamDmytro Zabolotnii, Kent Zuntov, Ivan HladkyiRomet Aidla, Enlik, Tetiana Shtym, Navid Bamdad Roshan
SupervisorMaxandre OgeretJan Aare van Gent

We have reserved Delta classroom 2006 on Tuesdays 16-20 for you to work on the project and meet your teammates. The classroom has 24 computers with NVIDIA GTX 2070 GPUs, so that you can run the software and simulator on different computers. The software needs Ubuntu Linux and you need to boot it up from external hard drives we will give you. The LGSVL simulator can be run from Windows and should be already on D: drive.

Tutorials

Here are some tutorials that might come handy during experiments:

TutorialAutoware.AutoBaidu Apollo
InstallationAutoware.Auto with LGSVL Simulator
Autoware Setup by Max
LGSVL Setup by Max
Running latest Apollo with LGSVL Simulator
Apollo Setup by Tanya
LGSVL Setup by Tanya
Full Tutorial by Navid
Full Tutorial by Enlik
ROS2/CyberRT BasicsLecture 1
Lecture 2
Lecture 3
Visualizing data in ROS2 by Max
Create and work with workspaces by Max
Working with bags by Max
ROS2 Workspace Architecture by Max
Build and run ROS1 bridge by Max
TBD
Creating point cloud mapGenerating a map by MaxHow to record lidar point cloud? by Tanya
How to turn that lidar point cloud into a map? by Tanya
Localizing on point cloud mapLocalization by MaxHow to localize yourself on that map (or using GNSS in Apollo) and record waypoints? by Tanya
Recording and following waypointsPath Following by MaxHow to make the car follow previously recorded waypoints? by Tanya
Lexus car instructionsTBDTesting Apollo on Lexus Car by Navid
Testing Apollo on Lexus Car by Enlik

Tests

Tests can be created using Google Forms. Tests need to be sent to supervisors by Monday morning on the week the test is performed, for quality assurance. Guidelines for creating the tests can be found here.

Schedule

All the class meetings are in Delta room 1022 on Wednesdays 14:15-15:45.

DateTopicStudentAutoware lecturesApollo lecturesNVidia webinars
9.09.2020Course overview (slides)Tambet  
7.10.2020Intro to self-driving (test)TambetLecture 5, Lecture 6Lecture 1Clip, Webinar 1, Webinar 2
14.10.2020Mapping
(test)
KentLecture 14Lecture 2Webinar
21.10.2020Localization
(test) (slides)
EnlikLecture 10Lecture 3Clip
28.10.2020Perception: LIDAR
(test)
NavidLecture 7Lecture 4Clip, Webinar 1, Webinar 2
4.11.2020Perception: Camera
(test)
TetianaLecture 8Lecture 4DRIVE Networks, Webinar 1, Webinar 2
11.11.2020Perception: Radar
(test)
MaxandreLecture 9 Clip
18.11.2020Prediction
(test)
Romet Lecture 5Webinar, Clip 1, Clip 2
24.11.2020Final date for demoing mapping in simulation    
25.11.2020Simulations
(test)
IvanLecture 11CARLA Talks 2020DRIVE Constellation
2.12.2020Planning
(test)
DmytroLecture 12Lecture 6Webinar
9.12.2020Control
(test)
JanLecture 12Lecture 7Webinar, Clip
16.12.2020Hardware Lecture 4 Webinar 1, Webinar 2
22.12.2020First date for parking lot demo    
23.12.2020Infrastructure Lecture 13 Webinar, Clip
27.01.2020Second date for parking lot demo    

Choose the topic you would like to create a test for here.

Deliverables

To earn 6 ECTS from this course each participant should:

  • Create a test on one topic for other students and grade it.
  • Get at least 60% of points from all tests created by other students.
  • Demonstrate the respective software running on their computer against a simulator.
  • Each team has to demonstrate the software running on Lexus car by driving a short pre-defined trajectory on parking lot. In case that turns out to be too complicated, the team should produce written report of their experiments and failures.

Follow-up

There is also a follow-up course planned in the next semester, where we make the teams compete to finish a demo track on the parking lot with the least amount of safety driver interventions.

Contact

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

  • Arvutiteaduse instituut
  • Loodus- ja täppisteaduste valdkond
  • Tartu Ülikool
Tehniliste probleemide või küsimuste korral kirjuta:

Kursuse sisu ja korralduslike küsimustega pöörduge kursuse korraldajate poole.
Õppematerjalide varalised autoriõigused kuuluvad Tartu Ülikoolile. Õppematerjalide kasutamine on lubatud autoriõiguse seaduses ettenähtud teose vaba kasutamise eesmärkidel ja tingimustel. Õppematerjalide kasutamisel on kasutaja kohustatud viitama õppematerjalide autorile.
Õppematerjalide kasutamine muudel eesmärkidel on lubatud ainult Tartu Ülikooli eelneval kirjalikul nõusolekul.
Courses’i keskkonna kasutustingimused