Awesome Robotics Manipulation · full_paper

GraSP-VLA: Graph-based Symbolic Action Representation for Long-Horizon Planning with VLA Policies

作者：Ma¨elic Neau, Zoe Falomir, Paulo E. Santos, Anne-Gwenn Bosser, C´edric Buche · 单位：Computing Science Department, Ume˚a University, Ume˚a, Sweden · 会议/期刊：arXiv · 日期：2025-11-06 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Structured Vision Language Action Models

抓取任务规划视觉语言动作机器人学习
新标签打开 AlphaXiv新标签打开 Paper
GraSP-VLA: Graph-based Symbolic Action Representation for Long-Horizon Planning with VLA Policies figure
AlphaXiv 中文论文页面（可滚动查看）