Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.

Introducing HiLMa-Res: a hierarchical RL framework for quadrupeds to tackle loco-manipulation tasks with sustained mobility! Designed for general learning tasks (vision-based, state-based, real-world data, etc), the robot now can step over stones🐾/navigate boxes📦/dribble⚽.

Exploiting morphological symmetries can enhance model-free RL sample efficiency, policy optimality, and sim2real transfer in legged locomotion and manipulation. Our #IROS2024 paper exploits these symmetries for RL methods. Code is open-sourced: 🌐 bit.ly/SymLoco🧵

Mechazilla has caught the Super Heavy booster!

Good morning

Kudos to Zhi Su Xiaoyu (Haytham) Huang for our #IROS24 paper exploiting morphological symmetries in model-free RL locomotion/ manipulation.

Just presented DiffuseLoco at #CoRL2024! DiffuseLoco learns diverse, multimodal skills for legged robots purely from offline datasets with a 6.8M transformer DDPM (YES it runs onboard at 30Hz!) A step towards large-scale learning for control. Code & ckpts👉Diffuselo.co

🚀 Introducing LeVERB, the first 𝗹𝗮𝘁𝗲𝗻𝘁 𝘄𝗵𝗼𝗹𝗲-𝗯𝗼𝗱𝘆 𝗵𝘂𝗺𝗮𝗻𝗼𝗶𝗱 𝗩𝗟𝗔 (upper- & lower-body), trained on sim data and zero-shot deployed. Addressing interactive tasks: navigation, sitting, locomotion with verbal instruction. 🧵 ember-lab-berkeley.github.io/LeVERB-Website/

With high-fidelity simulation and ray-tracing rendering, we can minimize the sim-to-real gap and achieve zero-shot sim-to-real transfer! We hope this is a critical step for scaling humanoid-specific data that is scarce atm.

Researchers from RAI Institute present Diffuse-CLoC, a new control policy that fuses kinematic motion diffusion models with physics-based control to produce motions that are both physically realistic and precisely controllable. This breakthrough moves us closer to developing

Want to achieve extreme performance in motion tracking—and go beyond it? Our preprint tech report is now online, with open-source code available!

The most interesting thing we learn is that adding basic domain randomization is already enough for dynamic motion tracking! Details in the preprint tech report.