AI Driving Olympics Home Challenges Submissions Jobs

Welcome to the AI Driving Olympics (AI-DO) server.

You can find an introduction to AI-DO here.

The reference manual will get you started.

Statistics

151users
40challenges
2868submissions
18570evaluation jobs

AI-DO is brought to you by:

AI-DO 2 - Embodied tasks

In these challenges, the participants must guide a Duckiebot through the streets of Duckietown. The only input available is a camera.

Repositories
Challenge definition challenge-aido_LF
Submission templates
Agent template- challenge-aido_LF-template-random
Pytorch templatePyTorch challenge-aido_LF-template-pytorch
Tensorflow templateTensorflow challenge-aido_LF-template-tensorflow
ROS templateROS challenge-aido_LF-template-ros
Baseline solutions
Imitation learning from real logsTensorflow challenge-aido_LF-baseline-IL-logs-tensorflow
Imitation learning from simulationTensorflow challenge-aido_LF-baseline-IL-sim-tensorflow
Reinforcement learning from simulationPyTorch challenge-aido_LF-baseline-RL-sim-pytorch
Traditional Duckietown pipelineROS challenge-aido_LF-baseline-duckietown

Challenge LF πŸš— - Lane following (simulation πŸ‘Ύ, testing πŸ₯‡)

Rank (comp)Rank (tech)UserSubmissionUser labelTraveled distance↑Survival time↑Lateral deviation ↓Major infractions ↓
not competing25Bhairav Mehta2754challenge-aido_LF-template-ros - Template solution using ROS0.6240.120
not best26zamatory2640challenge-aido_LF-template-ros - Template solution using ROS0.6240.120
not best27Konstantin Chayka 2604challenge-aido_LF-template-ros - Template solution using ROS0.6240.120
not competing28Liam Paull2583challenge-aido_LF-template-ros0.6240.120
not best29AlexKaravaev2560challenge-aido_LF-template-ros - Template solution using ROS0.6240.120
not competing30Andrea Censi2547challenge-aido_LF-template-ros - Template solution using ROS0.6240.120
not competing31Liam Paull2544challenge-aido_LF-template-ros0.6240.120
not competing32Liam Paull2491challenge-aido_LF-template-pytorch0.6220.020.8
633vguerra2402Baseline solution using reinforcement learning0.6220.040.4
not competing34Andrea Censi2383Baseline solution using reinforcement learning0.6220.050.2

See also the extended leaderboard.

Challenge LF πŸš— - Lane following (simulation πŸ‘Ύ, validation πŸ‹)

Rank (comp)Rank (tech)UserSubmissionUser labelTraveled distance↑Survival time↑Lateral deviation ↓Major infractions ↓
11MYF2601baseline-IL-logs-tensorflow1.8680.181.8
23Konstantin Chayka 2691challenge-aido_LF-baseline-duckietown1.24120.630.4
34RamiNaim2704challenge-aido_LF-baseline-duckietown1.24120.691.4
45zamatory2653challenge-aido_LF-baseline-duckietown1.24100.680
59almasip2867Baseline solution using reinforcement learning1.2440.050.8
619AlexKaravaev2857challenge-aido_LF-baseline-duckietown0.6280.150.2
727vguerra2403Baseline solution using reinforcement learning0.6220.040.4

See also the extended leaderboard.

Challenge LFV πŸš—πŸš— - Lane following + Vehicles (simulation πŸ‘Ύ, testing πŸ₯‡)

Rank (comp)Rank (tech)UserSubmissionUser labelTraveled distance↑Survival time↑Lateral deviation ↓Major infractions ↓
11RamiNaim2707challenge-aido_LF-baseline-duckietown1.24100.480.6
213zamatory2644challenge-aido_LF-template-ros - Template solution using ROS0.6240.120
314Konstantin Chayka 2608challenge-aido_LF-template-ros - Template solution using ROS0.6240.120
415AlexKaravaev2564challenge-aido_LF-template-ros - Template solution using ROS0.6240.120
517vguerra2404Baseline solution using reinforcement learning0.6220.030.4

See also the extended leaderboard.

Challenge LFV πŸš—πŸš— - Lane following + Vehicles (simulation πŸ‘Ύ, validation πŸ‹)

Rank (comp)Rank (tech)UserSubmissionUser labelTraveled distance↑Survival time↑Lateral deviation ↓Major infractions ↓
11RamiNaim2681challenge-aido_LF-baseline-duckietown1.24100.690.4
24zamatory2657challenge-aido_LF-baseline-duckietown1.2460.40.6
317Konstantin Chayka 2609challenge-aido_LF-template-ros - Template solution using ROS0.6240.120
418AlexKaravaev2565challenge-aido_LF-template-ros - Template solution using ROS0.6240.120
521vguerra2405Baseline solution using reinforcement learning0.6220.040.4

See also the extended leaderboard.

Challenge LFVI πŸš—πŸš—πŸš¦ - Lane following + Vehicles + Intersections (simulation πŸ‘Ύ, testing πŸ₯‡)

Rank (comp)Rank (tech)UserSubmissionUser labelTraveled distance↑Survival time↑Lateral deviation ↓Major infractions ↓
12RamiNaim2684challenge-aido_LF-baseline-duckietown1.2480.630
215zamatory2648challenge-aido_LF-template-ros - Template solution using ROS0.6240.120.2
316Konstantin Chayka 2612challenge-aido_LF-template-ros - Template solution using ROS0.6240.120.2
417AlexKaravaev2568challenge-aido_LF-template-ros - Template solution using ROS0.6240.120.2
522vguerra2406Baseline solution using reinforcement learning0.6220.070

See also the extended leaderboard.

Challenge LFVI πŸš—πŸš—πŸš¦ - Lane following + Vehicles + Intersections (simulation πŸ‘Ύ, validation πŸ‹)

Rank (comp)Rank (tech)UserSubmissionUser labelTraveled distance↑Survival time↑Lateral deviation ↓Major infractions ↓
112RamiNaim2712challenge-aido_LF-baseline-duckietown0.6260.210
214zamatory2649challenge-aido_LF-template-ros - Template solution using ROS0.6240.120.2
315Konstantin Chayka 2613challenge-aido_LF-template-ros - Template solution using ROS0.6240.120.2
416AlexKaravaev2569challenge-aido_LF-template-ros - Template solution using ROS0.6240.120.2
519vguerra2407Baseline solution using reinforcement learning0.6220.030.8

See also the extended leaderboard.

AI-DO 2 - Robotarium

AI-DO 2 - Autonomous Mobility on Demand

In these challenges, the participant must coordinate a fleet of robo-taxis in various cities environments.

Challenge [AIDO 2] AMOD - Efficiency (rev. 1)

Rank (comp)Rank (tech)UserSubmissionUser labelefficiency↑
not competing1Andrea Censi2310Python template-71.371144
not competing2Andrea Censi2298Python template-72.20661

See also the extended leaderboard.

Challenge [AIDO 2] AMOD - Fleet Size (rev. 1)

No entries to display.

See also the extended leaderboard.

Challenge [AIDO 2] AMOD - Service Quality (rev. 1)

Rank (comp)Rank (tech)UserSubmissionUser labelservice_quality↑
not competing1Andrea Censi2300Python template-32.316111
not competing2Andrea Censi2312Python template-32.331774

See also the extended leaderboard.

AI-DO 1 - Embodied tasks

In these challenges, the participants must guide a Duckiebot through the streets of Duckietown. The only input available is a camera.

Repositories
Challenge definition challenge-aido1_LF1
Submission templates
Agent template- challenge-aido1_LF1-template-random
Pytorch templatePyTorch challenge-aido1_LF1-template-pytorch
Tensorflow templateTensorflow challenge-aido1_LF1-template-tensorflow
ROS templateROS challenge-aido1_LF1-template-ros
Baseline solutions
Imitation learning from real logsTensorflow challenge-aido1_LF1-baseline-IL-logs-tensorflow
Imitation learning from simulationTensorflow challenge-aido1_LF1-baseline-IL-sim-tensorflow
Reinforcement learning from simulationPyTorch challenge-aido1_LF1-baseline-RL-sim-pytorch
Traditional Duckietown pipelineROS challenge-aido1_LF1-baseline-duckietown

Challenge LF - Lane following (rev. 3)

Rank (comp)Rank (tech)UserSubmissionUser labelTraveled distance↑Survival time↑Lateral deviation ↓Major infractions ↓
12151madelhorius1832Tensorflow template5.58100.560.2
13154yangzm111495Tensorflow template5.58100.560.2
14156shandonguniversityInspur1482Inspur CNN5.58100.560.2
15157tongqiusui1363Tensorflow template5.58100.560.2
16159Allen Ou590Tensorflow template5.58100.560.2
17161trimcao1521Tensorflow template5.58100.580.4
18179melorian1378Tensorflow template4.96100.520.6
19191dcharrez1479Tensorflow4.3460.340.8
20208pravishsainath1319PyTorch DDPG template3.1180.268.4
21210sodabeta904stay simple3.1180.268.4

See also the extended leaderboard.

Challenge LF - Lane following (rev. 4, more samples)

Rank (comp)Rank (tech)UserSubmissionUser labelTraveled distance↑Survival time↑Lateral deviation ↓Major infractions ↓
11heyt0ny2133Copy of #2: sub 1579 by heyt0ny (SAIC MOSCOW MML)19.22180.720
22WEIGAO2132Copy of #1: sub 1633 by WEIGAO (First trial)18.6180.60
34Benjamin2137Copy of #6: sub 1063 by Benjamin (My ROS solution)13.64181.431.2
45Jon2135Copy of #4: sub 1684 by Jon (JP pipeline)11.16120.770
56VincentMai2136Copy of #5: sub 1033 by VincentMai (ROS-based Lane Following)9.3100.982.2
67hvrigazov2142Copy of #11: sub 1552 by hvrigazov (Visteon perception team)5.58181.020.8
78trimcao2148Copy of #17: sub 1515 by trimcao (Tensorflow template)5.58100.380.2
89shandonguniversityInspur2145Copy of #14: sub 1482 by shandonguniversityInspur (Inspur CNN)5.58100.380.2
910melorian2149Copy of #18: sub 1378 by melorian (Tensorflow template)5.58100.430.2
1011madelhorius2147Copy of #16: sub 1832 by madelhorius (Tensorflow template)5.58100.430.2

See also the extended leaderboard.

Challenge LFV - Lane following with vehicles (rev. 1)

Rank (comp)Rank (tech)UserSubmissionUser labelTraveled distance↑Survival time↑Lateral deviation ↓Major infractions ↓
47106marshin2015Copy of #39: sub 756 by marshin (PyTorch template)0.6220.080.8
48107lmandrile2012Copy of #36: sub 613 by lmandrile (PyTorch template)0.6220.080.8
49108lavoiems1985Copy of #7: sub 819 by lavoiems (Baby Duke)0.6220.10
50110melorian1995Copy of #18: sub 1378 by melorian (Tensorflow template)0.6220.120
51111madelhorius1993Copy of #16: sub 1832 by madelhorius (Tensorflow template)0.6220.120
52113yangzm111493Random execution0.6220.120.8
53114tongqiusui1991Copy of #13: sub 1363 by tongqiusui (Tensorflow template)0.6220.130.2
54117MandanaSamiei2001Copy of #24: sub 687 by MandanaSamiei (ROS-based Lane Following)0.6220.160.2
55119Allen Ou1990Copy of #12: sub 590 by Allen Ou (Tensorflow template)0.6220.180
56121jasonlcl2035Copy of #58: sub 956 by jasonlcl (PyTorch template)0180.468.4

See also the extended leaderboard.

Challenge LFV - Lane following with vehicles (rev. 2 - dynamic, 20 samples)

Rank (comp)Rank (tech)UserSubmissionUser labelTraveled distance↑Survival time↑Lateral deviation ↓Major infractions ↓
11WEIGAO2074Copy of #1: sub 1633 by WEIGAO (First trial)17.98180.310
23Benjamin2079Copy of #6: sub 1063 by Benjamin (My ROS solution)7.4481.070.4
34pravishsainath2094Copy of #21: sub 1085 by pravishsainath (PyTorch DDPG template)3.1180.458.4
45sodabeta2093Copy of #20: sub 903 by sodabeta (PyTorch DDPG template)3.1180.458.4
56VincentMai2078Copy of #5: sub 1033 by VincentMai (ROS-based Lane Following)3.140.250.4
67miksaz2076Copy of #3: sub 1859 by miksaz (JetBrains Research)2.4820.150.2
78Sashkasem2124Copy of #51: sub 428 by Sashkasem (Random execution)1.24181.710
89anna.tsalapova2123Copy of #50: sub 396 by anna.tsalapova (simple submition)1.24181.710
910haliang2108Copy of #35: sub 784 by haliang (Random execution)1.2440.120.8
1011gunshi2095Copy of #22: sub 1268 by gunshi (ROS-based Lane Following)1.2440.260

See also the extended leaderboard.

AI-DO 1 - AMoD

In these challenges, the participant must coordinate a fleet of robo-taxis in various cities environments.

Challenge [AIDO 1] AMOD - Efficiency (rev. 1)

Rank (comp)Rank (tech)UserSubmissionUser labelefficiency↑
11lic1883super fishy-11.88762
29JoelGaechter1696greedy but not so lazy-34.87095
318rumpelstilzchen1663Simsalabim-64.327313

See also the extended leaderboard.

Challenge [AIDO 1] AMOD - Fleet Size (rev. 1)

Rank (comp)Rank (tech)UserSubmissionUser labelfleet_size↑
11lic1880fishy-1000000000
23JoelGaechter1698greedy but not so lazy-1000000000
34rumpelstilzchen1673Simsalabim 2-1000000000

See also the extended leaderboard.

Challenge [AIDO 1] AMOD - Service Quality (rev. 1)

Rank (comp)Rank (tech)UserSubmissionUser labelservice_quality↑
16lic1885inaccessible code but it scores better than without-20.224397
210JoelGaechter1697greedy but not so lazy-20.554737
321lsieber1735Simple FIFO-21.992748
425mpicquet1784Python template-30.489252
531rumpelstilzchen1655Mein zweiter Zauberspruch-32.207862
635ossamaAhmed1770Python template-32.582267
745zgxsin1769Python template-33.656357

See also the extended leaderboard.

Test challenges

These are the test challenges.

Challenge Simple prediction

Rank (comp)Rank (tech)UserSubmissionUser labelL1 error ↓L2 error ↓
12nikhilkhedekar2539PredictorLast0.110.02
24shasg482801PredictorLast0.120.02
35ASHWINRAM2726PredictorLast0.120.02
46ioart2687PredictorLast0.120.02
511Bnaich2686PredictorLast0.130.03

See also the extended leaderboard.

Other

These are all other challenges