Tag
Ropedia W0 是首个跨人类与多机器人具身的 loco-manipulation 世界基础模型，通过统一运动学表征和 10k 小时人类 + 3k 小时机器人数据实现五个基准上的最先进性能，蒸馏后支持实时分钟级 rollout 与 VR 交互。
InternW0 is a foundational physical world model from Shanghai AI Laboratory that jointly learns visual dynamics and robot control for efficient real-world interactions, trained on heterogeneous data and evaluated on scientific tasks.
WuJi has open-sourced its MINT model and EgoPipeline for reconstructing 3D hand and camera motion from first-person video, along with 1,021 hours of egocentric data to aid robot learning.
This article evaluates open weights VLMs for egocentric data processing using HFlow, showing that models like Gemma and Qwen achieve high accuracy compared to the Gemini baseline while being cheaper and suitable for self-hosting.
Macrodata Labs releases a research blog on scaling robotics with egocentric video data by recovering 3D hand motion signals using only open-source models.
A journalist receives a free meal from a private chef wearing a hat camera to record hand movements, part of Shift's initiative to collect egocentric data for training robots.
Encord and Zander Labs are experimenting with brain wave headsets to collect richer training data for physical AI, aiming to solve the scarcity of real-world robotics data.
A Wired writer spends a week recording herself doing household chores to generate egocentric video data for training humanoid robots, exploring the growing gig-economy trend of human data collection for AI.
A company is collecting egocentric (first-person) data from 30,000 factory workers wearing headsets during their shifts, offering to connect interested parties.
MobileEgo Anywhere is a mobile-based framework for collecting long-duration egocentric robot data using smartphone sensors, enabling large-scale training of vision-language-action models by lowering hardware barriers.