ROBOSHACKLES: A Safety Dataset for Human-Injury Prevention in Embodied Foundation Models
技术动态
来源：arXiv cs.RO发布时间待核实
arXiv:2606.18632v2 Announce Type: replace Abstract: Embodied Foundation Models (EFMs) integrate multimodal understanding, future-state reasoning, and executable robot actions. Yet their safety alignment for human-injury prevention remains underexplored, primarily because real-world data of robots harming humans or creating hazardous household situations cannot be safely or ethically collected.