Self-Monitoring Navigation Agent (no beam search; Progress Inference)

Reported on 5 benchmarks across 1 task · 1 paper · 5 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots5 results

Vision and Language NavigationonVLN Challenge
error· 2019-01-10
5.67
best: 1.61 (human)
SOTA
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation arXiv:1901.03035
Vision and Language NavigationonVLN Challenge
length· 2019-01-10
18.04
best: 1257.38 (Speaker-Follower)
SOTA
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation arXiv:1901.03035
Vision and Language NavigationonVLN Challenge
oracle success· 2019-01-10
0.59
best: 1 (FOAM-Beam Search)
SOTA
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation arXiv:1901.03035
Vision and Language NavigationonVLN Challenge
spl· 2019-01-10
0.35
best: 0.76 (human)
SOTA
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation arXiv:1901.03035
Vision and Language NavigationonVLN Challenge
success· 2019-01-10
0.48
best: 0.86 (human)
SOTA
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation arXiv:1901.03035