arXiv Robotics — research abstracts· Minghe Gao, Zhanxi Yan, Jiahui Liu, Wendong Bu, Xiaoting Chen, Qizhou Wang, Yi Su, Siliang Tang, Jun Xiao, Yueting Zhuang, Tat-Seng Chua, Juncheng Li·· 2 days agoEditorial score62
Benchmarking Behavioral Steerability in Behavior Foundation Models
Benchmarking Behavioral Steerability in Behavior Foundation Models
Summary
This paper introduces RoboSteer, the first benchmark for evaluating behavioral steerability in Behavior Foundation Models (BFMs). It defines behavioral steerability as the ability of BFMs to generate behaviors that align with user intentions and organizes it into three levels: Conditional Steering, Constraint Steering, and Compositional Steering. The study evaluates nine existing BFMs using a large-scale multimodal motion corpus to advance research on intention realization in embodied intelligence.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
Source：arXiv Robotics — research abstracts · arxiv.org