Lei Ye (Raymon Yip) @MasterYip3

RSI taking place physically

Mattie Fairchild @Scav

3 days ago

Confirmed that @taurobots can get to those hard to reach places

12 8 139 6K 24

Like the C550 metioned in the wandering earth II: Self-organizing, self-adaptive, self-sensing, and self-programming. cool work.

Yilun Du @du_yilun

2 days ago

Robotics has spent years scaling demonstration data and model size. What happens when we scale EXPLORATION for robot agents? We're incredibly excited to share RAX, an agentic robotics system that learns by scaling online exploration. A coding agent connects directly to the

31 90 482 42K 342

Robotics has spent years scaling demonstration data and model size. What happens when we scale EXPLORATION for robot agents? We're incredibly excited to share RAX, an agentic robotics system that learns by scaling online exploration. A coding agent connects directly to the robot’s perception and control APIs, learns from feedback, and builds programs that perceive, plan, and act. The model stays frozen. As exploration scales, the agent improves its programs and builds up reusable skills. The results: • ZERO teleoperation or action demonstrations on real robots—from insertion with 0.1 mm clearance and air-fryer manipulation to deformable objects and long-horizon mobile whole-body control. • +37 percentage points on average over leading learned policies across five simulation benchmarks: RoboDojo, BEHAVIOR-1K, HumanoidArena, DexJoCo’s bimanual tasks, and LIBERO-Pro. • One framework spanning single-arm, bimanual, dexterous, humanoid, and mobile robots, with new embodiments connected through APIs. The craziest part: on each real-world embodiment, going from scratch to mastering the tasks took roughly two hours. No teleop. No model finetuning. We’re open-sourcing the full framework AND every experiment session. We can’t wait to see what people build with it! Project + sessions: robot-agent-exploration.com Paper: assets.robot-agent-exploration.com/paper/rax.pdf GitHub: N Project fully led by @RunhanH and @xczhangxx who are absolutely awesome. How it works, experiments, and robot videos below 🧵 (1/N)

Can humanoids adapt to new terrain using only flat-ground references? 🤖 Meet P-BFM! 🥳 We learn a terrain-agnostic intent space with unsupervised RL and forward-backward representations, paired with a terrain-aware policy that adapts across diverse terrains—without terrain-specific demonstrations. 📄🎬💻 Check out our paper, video, and code here! 🌐 roboparty.github.io/P-BFM/

See it move. Imagine what you'll build. Meet RP1 — the full-stack open-source humanoid.

Excited to share 𝗕𝗥𝗔𝗖𝗘: a whole-body tracker for humanoids that can exert forces from diverse poses and adapt to varied terrains. Humanoid whole-body trackers are typically trained to follow references recorded on flat ground, carrying nothing. As a result, they know 𝗻𝗲𝗶𝘁𝗵𝗲𝗿 𝘁𝗵𝗲 𝗳𝗼𝗿𝗰𝗲𝘀 𝘁𝗵𝗲 𝗿𝗼𝗯𝗼𝘁 𝗺𝘂𝘀𝘁 𝗲𝘅𝗰𝗵𝗮𝗻𝗴𝗲 𝘄𝗶𝘁𝗵 𝗼𝗯𝗷𝗲𝗰𝘁𝘀 𝗻𝗼𝗿 𝗰𝗮𝗻 𝘁𝗵𝗲𝘆 𝗮𝗱𝗮𝗽𝘁 𝘁𝗼 𝗱𝗶𝘃𝗲𝗿𝘀𝗲 𝘁𝗲𝗿𝗿𝗮𝗶𝗻𝘀. BRACE closes both gaps in a single tracker. Our key innovation is a 𝗿𝗲𝗳𝗲𝗿𝗲𝗻𝗰𝗲-𝗮𝗱𝗮𝗽𝘁𝗮𝘁𝗶𝗼𝗻 𝗳𝗼𝗿𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻. Given humanoid reference trajectories, we adapt them to the terrain and the commanded force, then train the controller on these adapted references. Tracking them naturally produces the stance and bracing needed to handle the terrain and exert the force (or compensate for external loads). 𝗧𝗵𝗲 𝗿𝗲𝘀𝘂𝗹𝘁𝗶𝗻𝗴 𝗰𝗼𝗻𝘁𝗿𝗼𝗹𝗹𝗲𝗿 𝗱𝗲𝗽𝗹𝗼𝘆𝘀 𝗱𝗶𝗿𝗲𝗰𝘁𝗹𝘆 𝗼𝗻 𝘁𝗵𝗲 𝗿𝗲𝗮𝗹 𝗿𝗼𝗯𝗼𝘁. To know more, please visit our: Project page: multiplylabs.github.io/brace/ Interactive demo: multiplylabs.github.io/robogym-online… More details in this thread🧵 1/n

Recursive self improvement

Holy ＊. Now tesla make every vehicle into satellite.

Tesla @Tesla

3 days ago

Real life, baby

19K 96K 774K 95.1M 89K

This is what i really want to do before. the way they collect data is eye-catching. super.

Galbot @GalbotRobotics

5 days ago

Perceiving the environment, understanding spatial constraints, and coordinating whole-body motion are essential for humanoid robots to integrate into human society—and remain major challenges in robotics. To address this, the Galbot team introduces PASSAGE, a framework that

3 14 76 7K 32

Love how easy it is to swap the hands and head, the remote emergency stop, and the ability to change the battery without turning the robot off. 🦾🔋 Best of all, the design files are fully open source—a real sign of trust in the developer community. It’s been amazing to watch this team build it from the ground up, step by step! 🚀

RoboParty @RoboParty_DEV

4 days ago

🚀RP1 is officially here. 🌍Putting control of robotics back in developers’ hands. Introducing RP1 (ROBOTO 01) by RoboParty—a high-performance, fully open-source humanoid robotics platform for frontier robotics research and embodied AI model development. 🤖 Open across the full

52 64 404 32K 243

🚀RP1 is officially here. 🌍Putting control of robotics back in developers’ hands. Introducing RP1 (ROBOTO 01) by RoboParty—a high-performance, fully open-source humanoid robotics platform for frontier robotics research and embodied AI model development. 🤖 Open across the full hardware and software stack: • Robot platform: mechanical CAD, bill of materials, and assembly documentation • Actuators: in-house ROMOMO joint designs and related technical resources • Control: electrical systems, firmware, low-level drivers, and motion control implementations • Development: simulation models, SDKs, data processing tools, and training tools • Engineering foundations: technical documentation and research materials Open the black box. Understand the system. Make it your own. A deviation in motion can originate in the model, control policy, actuator response, or mechanical structure. RP1 opens up the design and implementation of these layers so developers can trace problems, modify the system, and validate changes on real hardware. Open-source algorithms for advanced motion control RP1 has demonstrated continuous walking, recovery from disturbances, getting back up after a fall, and human motion tracking. UFO and MimicLite connect motion learning, control policies, and execution on real hardware. The open toolchain connects data collection, simulation training, hardware deployment, and experimental validation—supporting joint iteration across models, control, and hardware. From RPO to RP1, we’re turning one team’s engineering experience into a starting point for many more. Opening the future of embodied AI to everyone ready to explore it. 🔗RP1 on GitHub: github.com/Roboparty/RP1 #RoboParty #RP1 #OpenSourceRobotics #EmbodiedAI

I saw many people say this is trivial (at least on the idea level). But if you have ever tried any adaptive curriculum thing before (like simple monotonic succ-rate scheduling, or progress-based ones), you will be amazed that how SGS is way more stable, with such a weight curve.

Octi Zhang @octi_zhang

a week ago

(3/5) So how does pure RL find these behaviors? Scale, but scale alone isn’t enough. With uniform task sampling, adding more parallel environments often doesn’t help: most experience goes to tasks the robot has already mastered or tasks still far beyond its current capabilities.

1 3 85 13K 32

Google’s Fruit Fly Brain Map Becomes an #AIAgent That Controls Robots by @ZentrixHQ #ArtificialIntelligence #AI #Neuroscience #BrainComputerInterface

JEPAs & BFMs folks, Remember INTACT in July? From JEPA into RL: meet LOGO in I-BFM 🤖 Local intent. Long-horizon purpose. Two horizons, one actor. G1 MuJoCo carry success: 51.0% → 94.3% with LOGO. 🎬 No retraining. Just use next reward, next action. How it works + paper & code 👇

@DavidSunok47 @xiaohuiyuan translation needed bro

@tokufxug so is it about 4d assets generation?

🤖 Coming soon. 🚀 RP1 — The fully open-source humanoid robot. Built for developers. Born for intelligence. #RoboParty #RP1 #OpenSource

Different from motion planning and tracking, I-BFM uses FB representation to handle the box-carrying task. In the demonstration, the robot performs the pick-and-place task without palpable phase switching. FB makes the whole task into a "higher-level optimal control problem" that aims to move the box to the goal in any way with the lowest "energy".

Ziqi Han @HanZiqi666

6 days ago

Can humanoids recover in interaction tasks? 📦🤖 Excited to share I-BFM! Reward-conditioned policy: carry, push, kick. FB: robot–object–contact dynamics; LOGO: contact now → task goal later. G1 MuJoCo Carry: 94.3% → 89.3% after robot disturbance. 🌐 iamhardworking.github.io/I-BFM/

19 15 237 1.7M 60

3DGS looks real—until you shift the camera or insert a car. 🚗 Excited to unveil SPVC, our joint work with @GWMGlobal! 4 upgrades to photorealistic driving video fixing: 🔹 Structured: Geometry-guided, not unconstrained. 🔹 Panoptic: Background + foreground, not just one. 🔹 Video: Temporally consistent, not frame-by-frame. 🔹 Cross-Dataset: One model across Waymo, nuScenes & PandaSet. One unified video diffusion fixer. See the difference! 👇 📄 Paper: arxiv.org/pdf/2608.17420 🌐 Project: li00147.github.io/SPVC-Project-P…

SGS shows unbelievable results in locomotion, it learns locomotion skills& behaviors without motion references

Mateo Guaman Castro @mateoguaman

a week ago

Our manipulation results were mind-blowing the first time I saw them, but earlier on, my favorite result was this locomotion run. Many great people have done parkour-type skills with locomotion already, but as far as I am aware, most, if not all, of these works trained separate

7 13 152 32K 107