Online qualifying
Two qualifying competitions were held: recognition category and control category.
recognition department
The top teams of the AI Edge Contest will participate in the final competition.
Click here for details on the AI Edge Contest ≫
control department
Top teams from Autoware simulation competition participate
Control Division Preliminary Online Simulation Competition Results7.31 update
| Ranking | Team name | Overall score | acc | avoider | traffic_light |
|---|---|---|---|---|---|
| #1 | 🔧🌟@ | 221.65 | 22.30 | 99.95 | 99.40 |
| #2 | Shallow Learners | 212.68 | 16.72 | 99.41 | 96.54 |
| #3 | cats | 211.02 | 15.52 | 97.56 | 97.94 |
| #4 | MPRG | 169.03 | 7.34 | 61.74 | 99.95 |
| #5 | CHD | 119.27 | 0.00 | 19.34 | 99.93 |
| #6 | NWC-WIN | 111.02 | 11.12 | 99.89 | 0.00 |
| #7 | DeepLearners | 103.57 | 4.80 | 98.77 | 0.00 |
| #8 | Windridge | 99.73 | 1.89 | 0.00 | 97.84 |
| #9 | Self-driving car study session | 0.00 | 0.00 | 0.00 | 0.00 |
Scenario script for control division qualifying online simulation competition
Download has finished.
The Association will not be held responsible for any problems or failures that may occur to your computer or network environment due to downloading this file. Furthermore, the Association is not responsible for any damage caused by these events.
Control division qualifying schedule4.16 update
| 3 / 2 (month) | Recruitment of participants begins on this site |
| 3 / 6 (gold) | Local simulator distribution started on this site |
| 4 / 13 (month) | Issue and notification of account for online simulator Online simulator started operating and started accepting codes. (Rankings updated from time to time) |
| 4/30 (Thu) 17:XNUMX | Online simulator closed/grading deadline |
| Early May (planned) | Ranking confirmed |
Simulation overview
◎Build scenarios based on the open source simulator (LGSVL) available in Autoware.
◎We will conduct simulations using the following three scenarios.
Accelerator control (maintaining distance to the vehicle in front)
Maintain a distance of 5m from the vehicle that appears in front of your vehicle for a certain amount of time.
Avoiding vehicles parked on the street
After driving to avoid a vehicle parked on the shoulder of the road in front of you within a 1.2m distance, you must pass through the checkpoints in front of both sides of the road within the specified time.
Traffic light recognition, start
Recognize traffic lights during the day. Depending on the traffic light situation, the vehicle aims to stop 0.5m before the stop line and depart within 3 seconds after the light turns green.
◎Participants will first perform local simulations on the code generated in their local environment, verify it, and repeat improvements.
◎After the online simulator starts operating, upload the completed code and receive an online simulator evaluation.
◎Rankings will be determined by adding points, subtracting points, and disqualifying each scenario, and adding up the scores.
- Click here to download the local simulator (ZIP:160MB)
- Click here for binaries for Windows environment (ZIP:102MB)
Disclaimer regarding this simulator
The Association will not be held responsible for any problems or failures that may occur to your computer or network environment as a result of participants downloading this file, regardless of the reason. Furthermore, the Society is not responsible for any damage caused by these events. - Click here for local simulator setup instructions
Development code rights and disclaimer
The rights to the code uploaded to the competition system belong to the code developer. JSAE and its subcontractors will use the electronically submitted data (code) only for the purpose of scoring competition tasks and verifying the results, and the developer will grant permission for such use. In addition, it shall be destroyed once the above purpose has been completed. Developers agree in advance that the code they submitted will be deleted by JSAE and its subcontractors after the qualifying round, and shall not raise any objections to this. JSAE and its subcontractors (including subcontractors for cloud environments, etc.) will handle electromagnetically submitted data (code) with the due care of a prudent administrator, but they will not be responsible for any damage caused by theft, hacking, or other force majeure. (Excluding cases caused by intentional or negligent behavior of the Society or its outsourced parties).
Recommended Environment
◎Autoware recommended environment
*“Autoware” is a registered trademark of The Autoware Foundation.
| 要素 | Recommended specifications |
|---|---|
| OS | Linux(Ubuntu18.04) |
| CPU | Intel Corei7 (8 cores) |
| memory | 16GB or more |
| storage | SSD 30GB or more |
| GPU | NVIDIA Geforce GTX 1080 or higher (if using nodes with GPU implementation) |
◎LGSVL recommended environment
- Equivalent to the Autoware recommended environment above.
- When starting at the same time as Autoware, 32GB or more memory and RTX2080 or higher GPU are recommended.
Since this simulator also runs on Windows, a separate environment may be prepared.
Click here for Q&A for the Control Division Preliminary Online Simulation Competition≫