Skip to content
Hot eventLive

SIGMA:自动驾驶仿真在环快慢协同推理框架

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026年10月8日,arXiv·Robotics 发布一手报道,介绍面向决策关键型自动驾驶的仿真在环(simulation-in-the-loop)框架 SIGMA。该框架用于自动驾驶中任务导向的快慢协作推理,把规划器嵌入不确定性评估,并提出期望规划增益(EPG)指标,用来决定何时调用云端大视觉语言模型(VLM)进行推理。目前报道仅披露框架设计与指标思路,未给出实验数据、评测结果或开源信息。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 8, 2026
  1. arXiv · Robotics
    SIGMA:面向决策关键型自动驾驶的仿真在环快慢推理框架

    SIGMA 是一种仿真在环(simulation-in-the-loop)框架,用于自动驾驶中任务导向的快慢协作,把规划器嵌入不确定性评估,并提出期望规划增益(EPG)指标来决定何时调用云端大视觉语言模型(VLM)推理。

Heat trend

Current heat 9·Comparable peak 10(Oct 8)·Comparable change over 24 hours –

02.557.510Oct8Oct8Oct8Oct8

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.