RLinf v0.4 released: an upgrade to the open-source training framework for embodied reinforcement learning
RLinf, an open-source training framework for embodied reinforcement learning developed by Tsinghua University, Infinigence AI, together with the Beijing Zhongguancun Academy and other institutions, has officially released v0.4, iterating across four directions: a LEGO-style real-robot system, real-robot post-training algorithms, full-modality model support, and a domestic computing power foundation.
Highlights
Isaac Lab 3.0 released: multi-backend architecture, most workflows no longer require installing Isaac Sim
Isaac Lab 3.0 has been officially released, and the official recommendation is that new projects and projects migrating from 2.x use v3.0.0 as their base. The new version adopts a multi-backend architecture with a unified task API and supports backends such as Newton and OV Libraries; supported tasks can switch physics, rendering, and visualization backends without rewriting logic, and most workflows do not require installing or launching Isaac Sim.
Xbotics具身智能实验室 · 微信公众号Source ↗Ropedia releases open-world model W0, trained on roughly ten thousand hours of first-person human video
Ropedia releases the open-world model W0, trained on approximately 10,000 hours of first-person human video; a single set of weights can predict the first-person perspective of humans, robotic arms, and humanoid robots (Unitree G1, Fourier GR-1), using a shared camera-plus-skeleton representation, and integrating a new robot requires only its URDF.
Model releases/updates
Ropedia releases open-world model W0, trained on roughly ten thousand hours of first-person human video
Ropedia releases the open-world model W0, trained on approximately 10,000 hours of first-person human video; a single set of weights can predict the first-person perspective of humans, robotic arms, and humanoid robots (Unitree G1, Fourier GR-1), using a shared camera-plus-skeleton representation, and integrating a new robot requires only its URDF.
Product releases/updates
RLinf v0.4 released: an upgrade to the open-source training framework for embodied reinforcement learning
RLinf, an open-source training framework for embodied reinforcement learning developed by Tsinghua University, Infinigence AI, together with the Beijing Zhongguancun Academy and other institutions, has officially released v0.4, iterating across four directions: a LEGO-style real-robot system, real-robot post-training algorithms, full-modality model support, and a domestic computing power foundation.
Xbotics具身智能实验室 · 微信公众号Source ↗Isaac Lab 3.0 released: multi-backend architecture, most workflows no longer require installing Isaac Sim
Isaac Lab 3.0 has been officially released, and the official recommendation is that new projects and projects migrating from 2.x use v3.0.0 as their base. The new version adopts a multi-backend architecture with a unified task API and supports backends such as Newton and OV Libraries; supported tasks can switch physics, rendering, and visualization backends without rewriting logic, and most workflows do not require installing or launching Isaac Sim.
Xbotics具身智能实验室 · 微信公众号Source ↗