HumanTracker introduces a 153-hour categorized humanoid tracking benchmark and a preference-trained metric, HumanScore, that agrees with human judgments better than kinematic error metrics.
Learning multi-modal whole-body control for real-world humanoid robots
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark
HumanTracker introduces a 153-hour categorized humanoid tracking benchmark and a preference-trained metric, HumanScore, that agrees with human judgments better than kinematic error metrics.