Haochen Shi (@HaochenShi74) header
Haochen Shi (@HaochenShi74) profile picture

CS PhD at Stanford

Stanford, CA
Joined January 2021
Excited to release Minimalist Compliance Control! We achieve robust, compliant robot interaction across robot arms, dexterous hands, and humanoids, with NO force sensors or learning. If you’re wondering what remains, please see the thread below😉 Website: minimalist-compliance-contro…
9
49
8
278
32,354
Wow exciting! Congrats to the team! @HaoL1R @yimengq0219
Today, we're introducing @Nimo_Robotics. We're building deployable dexterity: the fastest path from human expertise to validated robot skills for industrial work. Most dexterous hands replicate the human hand, joint for joint. But is that the most efficient path? High degrees of freedom and the embodiment gap are why dexterous manipulation demands so much data today. We went back to first principles: what is the minimal system that can complete real industrial tasks, such as multi-step assembly? Our answer is the N1 glove and D1 hand: to our knowledge, the highest-DoF commercial UMI system with matched visuals and kinematics. Nine independently actuated finger DoF keep the action space compact. Matched kinematics and appearance close the embodiment gap. What an expert demonstrates is what the robot learns. Nimo Core, our learning system, turns demonstrations into skills using vision, touch, and sound. It can hear a connector click into place as well as see it. Our goal: from human demonstration to a trained, validated, and deployed robot skill in one day. We're opening the Nimo beta program for 20 researchers and developers from academia and industry. Enjoy our launch film! Apply for the beta or discuss an industrial pilot: nimobot.ai/
1
13
2,216
The speed, subconscious movements, and cross-embodiment results are super impressive. Big congrats to the team 🔥🔥🔥
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids. - learned directly from human manipulation data - no teleop/robot data - close to human-level dexterity and efficiency - multi-robot collab
3
3
33
2,885
Haochen Shi retweeted
💡💡💡Wednesday’s Thing is coming... with a humanoid mode. 🤖 Meet Handroid: a 33 cm, 2.05 kg, 27-DoF desktop robot that reconfigures the same hardware into a five-finger dexterous hand or a humanoid. 🖐️ As a 20-DoF hand, Handroid picks up paper, pours water, grasps a ball, stacks cups, removes a glove, and reorients a cube in-hand. Its stack combines Vision Pro teleoperation, Diffusion Policy grasping, an1d RL-based in-hand reorientation. 🚶 Reconfigure it: five finger modules become a head, two arms, and two legs. Handroid walks, turns, sidesteps, squats, pushes boxes, and even does push-ups and pull-ups. We validate RL tracking and velocity control in simulation, and deploy keyframe motions on hardware. 🖐️🚶🖐️ In one long-horizon demo, Handroid starts docked to a Franka arm as a hand, becomes a humanoid, undocks, moves around an obstacle, and pushes a box within reach. It then returns to hand form, re-docks, picks up a bottle, and places it in the box. 💡 A robot does not have to be defined from the outset as only a hand, a pair of legs, or a body locked into one fixed form. Its joints can be reassigned, its modules recombined, and the same hardware can take on entirely different roles as tasks change. When morphology becomes a reconfigurable, reusable resource rather than a fixed boundary on capability, new possibilities emerge. Handroid is not the final answer, but a starting point. We hope it inspires researchers to rethink what robots can be and what they can do. 🌐 handroid.org 📄 arxiv.org/abs/2607.16187 #Robotics
1
5
487
This is exactly the kind of "transformer" I imagine. Creatively extending the otherwise limited workspace of a robot arm in a way that just makes sense. A perfect example of a brilliant idea + amazing execution. Enjoyed collaborating with the team a lot!
🤖 A robot that transforms between humanoid and dexterous hand? Introducing Handroid, a reconfigurable robot with a shared 27-DoF body 🖐️→🚶→🖐️: • The same joints, different roles • Expanded robot task space • Shared sensing and control interfaces handroid.org
6
2
26
6,116
A person walks around campus for 5 hours with cameras. That's it. That's the training data. The result? A humanoid robot that traverses unseen buildings, crowds, and glass walls — zero robot data, zero finetuning. EgoNav is here. egonav.weizhuowang.com/ None of these behaviors were pre-programmed: • Waiting for a door to open before entering • Steering around glass walls invisible to depth sensors • Yielding to pedestrians and resuming • Re-routing when furniture is rearranged All emerged from 5 hours of a human walking around. The prior is real. (1/6) #Humanoid #Robotics #DiffusionModel #EgoNav
14
67
4
303
36,463
🤲Tactile sensing is powerful for robot manipulation, but hardware is still difficult to access, reproduce, and scale. 🎯That’s why we built FlexiTac: an open-source, low-cost, and scalable tactile sensing solution designed for real robotic systems. • Project page: flexitac.github.io/ We hope FlexiTac can help democratize tactile sensing for robotics research. (1/n)
12
38
11
247
48,263
Haochen Shi retweeted
I’m so tired of writing rebuttals to this kind of “lack of novelty” review: “This paper trivially combines A, B, and C, so the algorithmic novelty is limited.” Technically, most (if not all) robotics papers are convex combinations of existing ideas. I still deeply appreciate A+B+C papers—especially when they deliver: - New capabilities: the “trivial combination” unlocks behaviors we simply couldn’t achieve before - Sensible & organic design: A+B+C is clearly the right composition—not some arbitrary A′+B+C′ - Nontrivial interactions: careful analysis of the dynamics, coupling, or failure modes between A, B, C - Rehabilitating old ideas: A was dismissed for years, but paired with modern B/C, it suddenly works—and teaches us why - System-level & "interface" insight: the contribution is not any single piece, but how the pieces talk to each other - Scaling laws or regimes: identifying when/why A+B+C works (and when it doesn’t) - Engineering clarity: making something actually work robustly in the real world is not “trivial” - New problem formulations: sometimes the real novelty is in the reformulation—only under this view does A+B+C make sense. Maybe worth keeping these in mind when reviewing the next A+B+C paper : )
29
123
25
987
118,613
Haochen Shi retweeted
Can we learn whole-body mobile manipulation directly from human demonstrations? Introducing Whole-Body Mobile Manipulation Interface (HoMMI) Egocentric + UMI, 0 teleop -> bimanual & whole-body manipulation, long-horizon navigation, active perception hommi-robot.github.io
12
70
7
338
85,356
Haochen Shi retweeted
We find that RL post-training can substantially improve BC policies without teaching them anything fundamentally new. So what is RL doing? In DICE-RL, it contracts a broad behavior prior toward high-value modes. (1/n) zhanyisun.github.io/dice.rl.…
6
41
1
276
29,756
Haochen Shi retweeted
1/ World models are getting popular in robotics 🤖✨ But there’s a big problem: most are slow and break physical consistency over long horizons. 2/ Today we’re releasing Interactive World Simulator: An action-conditioned world model that supports stable long-horizon interaction. 3/ Key result: ✅ 10+ minutes of interactive prediction ✅ 15 FPS ✅ on a single RTX 4090🔥 4/ Why this matters: it unlocks two critical robotics applications: 🚀 Scalable data generation for policy training 🧪 Faithful policy evaluation 5/ You can play with our world model NOW at yixuanwang.me/interactive_wo…. NO git clone, NO pip install, NO python. Just click and play! NOTE ⚠️ ALL videos here are generated purely by our model in pixel space! They are **NOT** from a real camera More details coming 👇 (1/9) #Robotics #AI #MachineLearning #WorldModels #RobotLearning #ImitationLearning
26
85
28
505
131,312
As long as your robot uses modern servos (e.g., Dynamixel) or QDD motors, even without current sensing or current control, our method still works! It is truly embodiment-agnostic and democratizes compliant control for low-cost robots. Try it out here: github.com/real-stanford/min…
Excited to release Minimalist Compliance Control! We achieve robust, compliant robot interaction across robot arms, dexterous hands, and humanoids, with NO force sensors or learning. If you’re wondering what remains, please see the thread below😉 Website: minimalist-compliance-contro…
2
6
39
5,054
To evaluate our compliance controller against learning-based methods, we compare against two RL-based baselines, UniFP and FACET.
1
1
8
595