PulseAugur
EN
LIVE 10:25:05
中文(ZH) 速腾聚创第二代全固态感知平台发布,要做物理AI数据入口|最前线

RoboSense launches E2 perception platform for physical AI data

RoboSense has launched its second-generation all-solid-state perception platform, E2, designed to serve as a data input for physical AI. This new platform utilizes the company's proprietary "Peacock" SPAD-SoC chip and a 2D VCSEL chip, offering significantly improved accuracy and field of view compared to its predecessor. RoboSense aims to provide high-precision 3D spatial data, which is crucial for training embodied AI models that require a deeper understanding of the physical world beyond traditional visual data. The E2 platform is already being integrated into various robots for applications in complex environments like homes and industrial settings. AI

IMPACT This platform aims to bridge the gap between simulated and real-world data for embodied AI, potentially accelerating the practical application of robots in complex environments.

RANK_REASON Product launch of a new perception platform by a company in the embodied AI space. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on 36氪 (36Kr) →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

RoboSense launches E2 perception platform for physical AI data

COVERAGE [1]

  1. 36氪 (36Kr) TIER_1 中文(ZH) ·

    RoboSense's Second-Generation Solid-State Perception Platform Released, Aiming to Be the Data Entry for Physical AI | Frontline

    <p>&nbsp;作者|黄楠</p> <p>编辑|袁斯来</p> <p>当下具身智能赛道正完成一轮关键转型。此前行业大量研发、展示集中在人形、四足机器人舞台演示,如今产业评判标准落地到工厂、园区、家庭等真实场景的长期稳定作业能力。</p> <p>但一个现实的问题是:多数基础模型仅依托二维图像、仿真虚拟数据训练,缺少真实三维空间里物体距离、材质、受力、动态交互的原生高精度信息,以至于机器人只能看懂画面,却难以真正理解物理世界的运行规律。</p> <p>单纯视觉传感器易受强光、遮挡、雨雪干扰,测距与空间结构测算存在天然误差;仿真环境构建的物理规则和现实工况差…