Embodied AI TopConf · ICLR2025

AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation

ICLR2025 / Planning and Reasoning

规划/推理感知
新标签打开 AlphaXiv新标签打开 Project
AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation figure
AlphaXiv 中文论文页面（可滚动查看）