Scenario
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Scenario 1
100Success Rate (SR)
4
Scenario S3
40.162Trajectory Length (m)
4
Scenario S2
40.023Path Length (m)
4
Scenario 3 Model B (n=10000)
0.192MSE ($ au=0.05$)
4
Scenario 3 Model B (n=5000)
0.294MSE (τ=0.05)
4
Scenario 3 Model B (n=1000)
0.693MSE (τ=0.05)
4
Scenario 3 Model A (n=10000)
0.23MSE (τ=0.05)
4
Scenario 3 Model A (n=5000)
0.321MSE (τ=0.05)
4
Scenario 3 Model A
0.866MSE (τ=0.05)
4
Scenario 2 Model B (n=10000)
0.047MSE (τ=0.05)
4
Scenario 2 Model B (n=5000)
0.065MSE (τ=0.05)
4
Scenario 2 Model B (n=1000)
0.136MSE (τ=0.05)
4
Scenario 2 Model A (n=1000)
0.167MSE (τ=0.05)
4
Scenario 1 Model B
0.055MSE (τ=0.05)
4
Scenario 1 Model B (n=1000)
0.191MSE (τ=0.05)
4
Scenario 1 Model A (n=5000)
0.047MSE (τ=0.05)
4
Scenario B
8.4Average runtime [s]
4
Scenario A
6.4Average runtime [s]
4
Scenario 1 2D Free Space
0.048Lpde
4
Scenario (test)
86.3Delta 1 Accuracy
4
scenario mild v0.3.2
100.1Retention
3
Scenario 4 Drop Forward Transfer
88.9Success Rate
3
Scenario 4 (Drop, Forward) Seen
94.4Success Rate
3
Scenario 3 Poke Nudge Transfer
91.7Success Rate
3
Scenario Poke, Nudge Seen 3
97.2Success Rate
3