PulseAugur
中
实时 22:35:29
English(EN) Reward AI Releases OM-1: A Robot Policy Trained on Human Demonstrations Only, With No Teleoperation or On-Robot Data

Reward AI 推出 OM-1 机器人策略，仅基于人类演示训练

作者 PulseAugur 编辑部 · [1 个来源] ·

机器人初创公司 Reward AI 推出了 OM-1，这是一种通用操作策略，仅通过传感器手套捕获的人类演示进行训练。与使用遥操作或机器人本体数据的典型方法不同，OM-1 直接从人类运动中学习，旨在更广泛地应用于不同的机器人实体。该系统使用一种名为 Omnibody Hand 的新型可穿戴设备进行精确运动捕捉，并采用单阶段训练过程来训练 OM-1 策略，但该技术目前仅限于内部使用，尚未公开。 AI

影响 这种方法可以通过将训练与特定机器人硬件分离，从而实现更具适应性和通用性的机器人操作。

排序理由 机器人初创公司发布新模型。[lever_c_demoted from frontier_release: ic=1 ai=1.0]

在 MarkTechPost 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Reward AI 推出 OM-1 机器人策略，仅基于人类演示训练

本文如何被排名

Signal score
61 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
机器人初创公司发布新模型。[lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    Reward AI 发布 OM-1：仅基于人类演示训练的机器人策略，无远程操作或机器人本体数据

    <p>Reward AI has released OM-1 (Omnibody Model 1), a general-purpose manipulation policy trained entirely on human demonstrations captured with a 7-DoF wearable glove, with no teleoperation or on-robot data. The policy runs on industrial arms and humanoids at human speed, learns …

相关话题