Empirical Inference Department

Results

Final Results of the Real-Robot Stage

# Username Push/Expert Push/Mixed Lift/Expert Lift/Mixed Score Report Rating Report
1. excludedrice 624 ±144 635 ±137 956 ±431 923 ±442 784 + Download report
2. decimalcurlew 639 ±112 613 ±134 841 ±415 717 ±383 703 + Download report
3. superiordinosaur
jealousjaguar
618 ±143
639 ±121
575 ±191
561 ±178
856 ±452
855 ±392
571 ±346
506 ±348
655
640
0
+
Download report
Download report

Task-specific scores are given as mean ±std (failed runs get a score of 0). The score is the average over all tasks.

As the scores of superiordinosaur and jealousjaguar are pretty close and we deem the report of jealousjaguar to be of higher quality, we are awarding a shared third place to both teams with split prize money.

We will contact the teams in the next days regarding the administrative details for receiving the prize money.

Thank you all for your participation in the Real Robot Challenge 2022!

Leaderboard from 2022-09-30

# Username Push/Expert Push/Mixed Lift/Expert Lift/Mixed Score
1. excludedrice 621 ±140 621 ±150 976 ±437 387 ±204 651
2. superiordinosaur 564 ±196 526 ±212 779 ±453 600 ±353 618
3. decimalcurlew 608 ±168 564 ±201 823 ±467 396 ±259 598
4. jealousjaguar 623 ±124 0 ±0 0 ±0 0 ±0 156

Task-specific scores are given as mean ±std (failed runs get a score of 0). The score is the average over all tasks.

Leaderboard from 2022-09-26

# Username Push/Expert Push/Mixed Lift/Expert Lift/Mixed Score
1. excludedrice 666 ±61 663 ±103 1122 ±381 922 ±366 843
2. decimalcurlew 659 ±104 635 ±98 942 ±382 900 ±420 784
3. superiordinosaur 647 ±122 558 ±210 1005 ±375 861 ±432 768
4. jealousjaguar 558 ±161 0 ±0 0 ±0 0 ±0 139

Task-specific scores are given as mean ±std (failed runs get a score of 0). The score is the average over all tasks.

Leaderboard from 2022-09-16

# Username Push/Expert Push/Mixed Lift/Expert Lift/Mixed Score
1. decimalcurlew 644 ±71 648 ±99 1055 ±379 566 ±314 729
2. superiordinosaur 624 ±116 585 ±188 1055 ±378 550 ±255 704
3. jealousjaguar 580 ±151 0 ±0 0 ±0 0 ±0 145
4. excludedrice 0 ±0 0 ±0 0 ±0 0 ±0 0

Task-specific scores are given as mean ±std (failed runs get a score of 0). The score is the average over all tasks.

Leaderboard from 2022-09-09

# Username Push/Expert Push/Mixed Lift/Expert Lift/Mixed Score
1. superiordinosaur 623 ±159 573 ±196 909 ±450 533 ±337 660
2. decimalcurlew 626 ±119 385 ±277 928 ±431 409 ±284 587
3. excludedrice 0 ±0 0 ±0 590 ±420 593 ±396 296
4. jealousjaguar 587 ±147 0 ±0 0 ±0 0 ±0 147

Task-specific scores are given as mean ±std (failed runs get a score of 0). The score is the average over all tasks.

Leaderboard from 2022-09-02

# Username Push/Expert Push/Mixed Lift/Expert Lift/Mixed Score
1. decimalcurlew 665 ±76 656 ±120 899 ±444 835 ±367 764
2. superiordinosaur 646 ±104 573 ±207 859 ±469 528 ±327 651
3. excludedrice 0 ±0 0 ±0 799 ±420 637 ±464 359

Task-specific scores are given as mean ±std (failed runs get a score of 0). The score is the average over all tasks.

Participants from whom no executable code was available are not listed in the leaderboard.