Jianzhi Robotics Launches DAS 2.0 System to Address Data Scarcity in Embodied AI
数据采集设备越来越多,为什么可训练数据还是不够用?
Jianzhi Robotics has introduced the DAS 2.0 system, comprising the Dex 2.0 dexterous glove and Ego 2.0 first-person view head-mounted unit, designed to capture aligned physical causal chains for embodied AI training. The system addresses data scarcity by ensuring complete observation-action-contact-feedback loops through direct kinematic measurement and reliable tactile sensing, aiming to provide high-fidelity human skill translation for robot learning.
Source: RoboSpeak — WeChat · Read original article ↗
English translation unavailable. Choose the original article to read it.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
frames per second
30
View original evidence
视觉上 ,2颗500万像素加4颗200万像素全局快门相机,六路30fps同步成像,指尖追踪精度可达4mm; 视野上 ,水平视场从上一代270°扩展至340°,垂直最高120°,扩大对人体上半身、周身环境及侧后方区域的覆盖; 工程化上 ,竖向绑带加柔性缓冲适配不同头围,配套采集帽降低发丝遮挡,一键录制+语音反馈,App头姿和遮挡检测,磁吸电池不关机更换,单电池包2.5-3小时续航,标准mcap格式输出。
Open source S23horizontal field of view
340
View original evidence
视觉上 ,2颗500万像素加4颗200万像素全局快门相机,六路30fps同步成像,指尖追踪精度可达4mm; 视野上 ,水平视场从上一代270°扩展至340°,垂直最高120°,扩大对人体上半身、周身环境及侧后方区域的覆盖; 工程化上 ,竖向绑带加柔性缓冲适配不同头围,配套采集帽降低发丝遮挡,一键录制+语音反馈,App头姿和遮挡检测,磁吸电池不关机更换,单电池包2.5-3小时续航,标准mcap格式输出。
Open source S23vertical field of view
120
View original evidence
视觉上 ,2颗500万像素加4颗200万像素全局快门相机,六路30fps同步成像,指尖追踪精度可达4mm; 视野上 ,水平视场从上一代270°扩展至340°,垂直最高120°,扩大对人体上半身、周身环境及侧后方区域的覆盖; 工程化上 ,竖向绑带加柔性缓冲适配不同头围,配套采集帽降低发丝遮挡,一键录制+语音反馈,App头姿和遮挡检测,磁吸电池不关机更换,单电池包2.5-3小时续航,标准mcap格式输出。
Open source S23battery runtime
2.5–3 hours
View original evidence
视觉上 ,2颗500万像素加4颗200万像素全局快门相机,六路30fps同步成像,指尖追踪精度可达4mm; 视野上 ,水平视场从上一代270°扩展至340°,垂直最高120°,扩大对人体上半身、周身环境及侧后方区域的覆盖; 工程化上 ,竖向绑带加柔性缓冲适配不同头围,配套采集帽降低发丝遮挡,一键录制+语音反馈,App头姿和遮挡检测,磁吸电池不关机更换,单电池包2.5-3小时续航,标准mcap格式输出。
Open source S23joint angle resolution
0.2
View original evidence
21DoF、0.2°关节角度分辨率、指尖位置精度小于1mm、编码器厚度约3mm、外骨骼主体约60g,这些参数背后是一个更重要的判断,数据标签应是具有明确运动学含义的直接测量信号。
Open source S15tip position accuracy
4
View original evidence
视觉上 ,2颗500万像素加4颗200万像素全局快门相机,六路30fps同步成像,指尖追踪精度可达4mm; 视野上 ,水平视场从上一代270°扩展至340°,垂直最高120°,扩大对人体上半身、周身环境及侧后方区域的覆盖; 工程化上 ,竖向绑带加柔性缓冲适配不同头围,配套采集帽降低发丝遮挡,一键录制+语音反馈,App头姿和遮挡检测,磁吸电池不关机更换,单电池包2.5-3小时续航,标准mcap格式输出。
Open source S23
- paper: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
视觉上 ,2颗500万像素加4颗200万像素全局快门相机,六路30fps同步成像,指尖追踪精度可达4mm; 视野上 ,水平视场从上一代270°扩展至340°,垂直最高120°,扩大对人体上半身、周身环境及侧后方区域的覆盖; 工程化上 ,竖向绑带加柔性缓冲适配不同头围,配套采集帽降低发丝遮挡,一键录制+语音反馈,App头姿和遮挡检测,磁吸电池不关机更换,单电池包2.5-3小时续航,标准mcap格式输出。
Open source S23
21DoF、0.2°关节角度分辨率、指尖位置精度小于1mm、编码器厚度约3mm、外骨骼主体约60g,这些参数背后是一个更重要的判断,数据标签应是具有明确运动学含义的直接测量信号。
Open source S15
Source:RoboSpeak — WeChat · mp.weixin.qq.com