Arvutiteaduse instituut
  1. Kursused
  2. 2024/25 kevad
  3. Isejuhtivate sõidukite projekt (LTAT.06.012)
EN
Logi sisse

Isejuhtivate sõidukite projekt 2024/25 kevad

  • Overview
  • First Meeting
  • Robot Orienteering
  • 1:10 scale car track
  • Useful Links

Robot Orienteering

You will participate in The EarthRover Challenge, part of ICRA 2025 robotics conference. In this competition the participants have to guide teleoperated robots in various cities over the world to pass given GPS waypoints. The robots are controlled remotely by AI using Earth Rovers SDK. As everything is happening remotely, you are not restricted by robot hardware or compute capabilities. All the software runs in your own laptop (or cloud) and any machine learning model can be used.

The Earth Rover Challenge organizers will give us three robots to run locally near Delta. Additionally we will be given access token to control any fleet robot in the world. You should keep in mind that during the competition the missions are in different cities (mainly US, South America and Canada), so do not overfit to Tartu. You can test drive a robot here. Training data for machine learning models can be found here.

Important dates

DateDescriptionLocation
11.02.2025 12:15First meetingDelta Room 2006
...IRL Training (20hrs/week/team)remote
31.03.2025Practice session Iremote
15.04.2025Practice session IIremote
30.04.2025Practice session IIIremote
19.05.2025Dry run on siteAtlanta, USA or remote
20-21.05.2025Main competitionAtlanta, USA or remote
30.05.2025Write a blog post or report of your experience

Prerequisites

  • Good command of Python
  • Experience with machine vision
  • Some familiarity with robotics

Deliverables

To earn 3 ECTS your team must:

  • Meaningfully participate in the competition, i.e. participate at least one practice session and the final competition.
  • Write a blog post or report of your experience.

Bonus:

  • If from practice sessions it seems that your team is a plausible candidate for top 3, ADL will pay for the trip to Atlanta, USA.

Contact(s)

Course instructor(s):

  • Tambet Matiisen, tambet.matiisen@ut.ee
  • Anish Shrestha, anish.shrestha@ut.ee

Tambet and Anish can be found in Autonomous Driving Lab (room 3095 in Delta, behind Sandbox).

  • 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