Skip to content
Hot eventLive

Proprioceptive Action Models(PAM):本体感知草图作为长期意图

1 reports1 sources16 hr ago updated

Get the story

AI overview

2026年10月5日,研究者在 arXiv·Robotics 发布 Proprioceptive Action Models(PAM)。该方法在单一 Transformer 去噪器中联合生成两类输出:紧凑、无时间戳的关节空间路径草图,以及稠密可执行动作块;路径草图采用弧长参数化,用以捕捉与执行时序无关的几何意图,作为生成式动作策略的长期意图。目前公开信息仅涉及该方法的核心设计,未报道实验结果、基准对比或开源情况。

Generated from reports · updated 16 hr ago

Timeline

Follow the coverage from different angles.

Oct 5, 2026
  1. arXiv · Robotics
    Proprioceptive Action Models(PAM):用本体感知草图作为生成式动作策略的长期意图

    研究者提出 Proprioceptive Action Models(PAM),在单一 Transformer 去噪器中联合生成紧凑、无时间戳的关节空间路径草图与稠密可执行动作块,以弧长参数化捕捉与执行时序无关的几何意图。

Heat trend

Current heat 7·Comparable peak 10(Oct 5)·Comparable change over 24 hours –

02.557.510Oct5Oct5Oct5Oct6

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.