Sharpa

Sharpa is an AI robotics company dedicated to developing ultra-high performance robots and core components.
We Manufacture Time by Making Robots Useful.

[Sharpa @SharpaRobotics]

SharpaDex v1.0 is live on Hugging Face! 🚀

300h of real-world manipulation: 28,993 demos, 59 tasks, 32.4M frames—collected by our humanoid robot with two Sharpa Wave (W01) hands!

Get started with our visual data explorer:

🌐 https://t.co/wF51kWMSyQ

🤗 https://t.co/NwivmdiqLi

[Sharpa @SharpaRobotics]

300 hours. 28,993 demonstrations. 59 tasks.
Touch on all 10 fingertips, in every frame.

We're thrilled to share SharpaDex v1.0 with the robotics community! To our knowledge, SharpaDex is the largest publicly available real-robot dexterous-hand manipulation dataset with fingertip tactile sensing, measured by publicly released demonstration hours containing tactile data as of October 2026.

This release brings together:

• Diverse manipulation: tool use, assembly, deformable-object handling, and long-horizon tasks.

• Synchronized sensing: multi-view RGB, fingertip tactile images, fingertip force/torque, and 65-dimensional joint actions.

• Contact-rich data: approximately 195 hours with at least one fingertip in contact, including 55 hours of simultaneous contact across both hands.

• Hierarchical language annotations: task descriptions, 217,642 temporally grounded subtask segments covering 89.3% of frames, and 45 distinct skill labels.

What excites us most is what comes next: researchers using these data to explore how robots can learn from touch, coordinate both hands, and perform increasingly complex tasks.

We hope SharpaDex becomes a useful resource for visual-tactile VLA models, tactile representation learning, and general-purpose dexterous manipulation. We can't wait to see what you build—and learn alongside you.

Available in LeRobot v3.0 and v2.1 formats under CC BY-NC 4.0.
Explore the data, tasks, and annotations through our report and interactive visualizations, or download the dataset to get started:

Dataset on Hugging Face：https://t.co/doQsZcM0de

[Sharpa @SharpaRobotics]

Round of applause for Embodied Playground pushing the frontier forward with 410 simulated tasks challenging AI agents across physics, strategy, and spatial reasoning.

Great work by the team! 🚀

[Feng Chen @Winniechen02]

Can an LLM agent play Angry Birds?

Introducing Embodied Playground 🤖
410 simulated task environments that test physical, strategic, and spatial reasoning.

🌏 Website: https://t.co/FTXefmkSOM
📄 Paper: https://t.co/3Cep6AvfnW
💻 Code: https://t.co/NgHLnMr19V

[Sharpa @SharpaRobotics]

Congratulations to the Exciting work from @Wei_ZHAN_ and the team on X-Reset!

Great to see the Sharpa 22-DoF dexterous hand supporting research that pushes scalable reinforcement learning, cross-embodiment transfer, and sim-to-real dexterous manipulation forward!

[Wei ZHAN @Wei_ZHAN_]

Reinforcement Learning (RL) in simulation is a scalable strategy to learn dexterous skills, but naive exploration from scratch often fails to discover manipulation strategies for diverse objects.

At @AppliedInt, we propose X-Reset, a straightforward method to resolve the exploration problem for generalist RL policies by randomly sampling resets from human hand-object states.
- We train a single dexterous policy to manipulate a variety of objects to any goal pose, ranging from small markers to heavy powerdrills with zero teleoperation data
- The learned policy zero-shot generalizes well beyond the training set (DexYCB), and transfers from sim-to-real using object pose-tracking models

We are continuously expanding robotics research at @AppliedInt beyond X-Reset, with the bounds of simulation and synthetic data for dexterous manipulation pushed. Stay tuned and join us!

🌐 Project Page: https://t.co/xEXMnWxja2
📄 Paper: https://t.co/28Ewh0pUYS

[Sharpa @SharpaRobotics]

Exciting work from @HaozhiQ and @Ying_yyyyyyyy the team on FOMO-Dex with Sharpa gloves serving as the human teleoperation interface for force-aware dexterous manipulation!

Great to see Sharpa's hardware supporting research that pushes contact-rich manipulation from better demonstrations toward stronger autonomous policies.

[Haozhi Qi @HaozhiQ]

It's interesting that I have spent quite some time working on sim-to-real for screwdriving, often using it as an example of why finger coordination is too hard to teleoperate and why we need simulation.

But is that really the case?

We explore whether carefully designed low-level control, especially with compliance, can actually make these tasks teleoperable. Checkout the original thread ⬇️

And the @SharpaRobotics glove has been amazing to work with! It played a key role in making this project possible!

[Ying Yuan @Ying_yyyyyyyy]

Can we make dexterous robots compliant without sacrificing precise control?

Excited to introduce FOMO-Dex: Force-Modulated Dexterity! 🖐️

FOMO-Dex brings force-aware compliance to dexterous teleoperation, enabling robots to pick up thin cards and chips 🃏, cut paper 🔪, turn nuts 🔩, and use screwdrivers 🪛.

These force-aware demonstrations also train better autonomous policies!

🎥 Videos & paper: https://t.co/SC3bdKXOai

🧵👇 (1/8)

[Sharpa @SharpaRobotics]

300 hours. 28,993 demonstrations. 59 tasks.
Touch on all 10 fingertips, in every frame.

We're thrilled to share SharpaDex v1.0 with the robotics community! To our knowledge, SharpaDex is the largest publicly available real-robot dexterous-hand manipulation dataset with fingertip tactile sensing, measured by publicly released demonstration hours containing tactile data as of October 2026.

This release brings together:

• Diverse manipulation: tool use, assembly, deformable-object handling, and long-horizon tasks.

• Synchronized sensing: multi-view RGB, fingertip tactile images, fingertip force/torque, and 65-dimensional joint actions.

• Contact-rich data: approximately 195 hours with at least one fingertip in contact, including 55 hours of simultaneous contact across both hands.

• Hierarchical language annotations: task descriptions, 217,642 temporally grounded subtask segments covering 89.3% of frames, and 45 distinct skill labels.

What excites us most is what comes next: researchers using these data to explore how robots can learn from touch, coordinate both hands, and perform increasingly complex tasks.

We hope SharpaDex becomes a useful resource for visual-tactile VLA models, tactile representation learning, and general-purpose dexterous manipulation. We can't wait to see what you build—and learn alongside you.

Available in LeRobot v3.0 and v2.1 formats under CC BY-NC 4.0.
Explore the data, tasks, and annotations through our report and interactive visualizations, or download the dataset to get started:

Dataset on Hugging Face：https://t.co/doQsZcM0de

[Sharpa @SharpaRobotics]

@melonTree68 No we are autonomous

[Sharpa @SharpaRobotics]

Sharpa North has been at work at DQ Shanghai.

Making Blizzards for real customers, using the same setup and workflow as the rest of the store.

We’ve learned a lot along the way - from customers, and from the DQ team working alongside Sharpa North.

Here’s a closer look at one order, step by step. 👇

[Sharpa @SharpaRobotics]

Collar off.
Cup flips.
Nothing spills.
✌️

[Sharpa @SharpaRobotics]

Spoon placement is a two-hand job.

One hand holds the Blizzard. The other picks up the spoon, places it, then pushes the ice cream off the collar and back into the cup.

Small motion. Tight tolerance.

[Sharpa @SharpaRobotics]

A simple paper airplane. A serious challenge for robotic dexterity. ✈️🤖

Proud to team up with @BitRobotNetwork for the first-ever Origami Challenge at #IROS2026.

Huge congratulations to all 14 finalist teams! Excited to see how far we can push the boundaries of dexterous manipulation together.

[BitRobot 🦾 @BitRobotNetwork]

The first ever Origami Challenge with @SharpaRobotics at @ieeeiros IROS 2026 concluded.

We asked teams to fold a paper airplane to test policies in dexterous manipulation.

14 global teams made it to the final round. Here are the results ↓

[Sharpa @SharpaRobotics]

Sharpa at Silicon Valley 101 Alignment 2026 Summit.

We brought Sharpa D01 and our latest dexterous hand, Sharpa W02, to the Bay Area — putting our latest work in robotic manipulation directly in front of the AI and robotics community.

From full-body execution to dexterous hand manipulation, we’re showing how Sharpa is building the hardware foundation for robots to operate in the physical world.

If you’re around the Bay Area, come see Sharpa in action.
https://t.co/wXJ3gA12xm

#Sharpa #Robotics #HumanoidRobotics #DexterousManipulation #DexterousHand #EmbodiedAI #RobotLearning #Teleoperation

[Sharpa @SharpaRobotics]

Impressive work from @liwenjiao2 and the team, turning human video into deployable visual-tactile dexterous manipulation policies with the Sharpa W01 22-DoF dexterous hand.

A strong step toward learning complex manipulation directly from human demonstrations and bringing it into real-world robotic execution.

[Wenqiao Li @liwenjiao2]

🚩Human touch can help scale robot dexterity, not just human motion.
🤖Introduce UVTA: a universal system leverage human tactile data for dexterous manipulation.
✉️ Project available at: https://t.co/0tjqqHxjve
Arxiv: https://t.co/R0qJ52dZZG

[Sharpa @SharpaRobotics]

We’re glad to see @TaraSadjadpour and the Morphometric Imitation team advancing research in morphology adaptation, one-shot learning, and sim-to-real transfer with our 22-DoF dexterous hands.

Sharpa provides simulation assets with faithful kinematics and dynamics, while its human-like morphology enables a broad range of dexterous motions.

Interested in exploring it yourself? Get in touch or download the simulation assets from our website: https://t.co/lmHm70mPXh

[Tara Sadjadpour @TaraSadjadpour]

One human demonstration. Any multi-fingered hand. Zero-shot sim-to-real visuomotor policy.

https://t.co/fqkm4Fc1qv

Collaborators: @he_siming @ckwolfeofficial @HaozhiQ @LeaMue27 Shankar Sastry, Claire Tomlin, @JitendraMalikCV

[Sharpa @SharpaRobotics]

Human video is an undiscovered goldmine for robot learning.

Excited to see @jwang633 and the team exploring its potential with Sharpa’s dexterous hands. The human-like form of Sharpa W01 makes it well suited to translating natural hand motion into robotic movement.

The team takes this further, showing how human video can become a powerful source for robots to learn real-world, long-horizon, contact-rich manipulation.

[Jeffrey Wang @jwang633]

Learning bimanual dexterous manipulation from a single human video? Agents can be a solution!

Introducing DexAgent, an agentic Human2Sim2Robot framework for dexterous manipulation with a self-evolving tool library.

We evaluated DexAgent on 11 real-world, long-horizon dexterous manipulation tasks spanning rigid, articulated, and deformable objects.

🤖 63.6% policy rollout success rate, compared with 18.2% for the strongest baseline

⚡ 2.1 hours average inference time with the tool library, compared with 3.3 hours for the baseline

🧰 A self-evolving library with 103 skills + 188 verifiers, designed to keep growing as DexAgent encounters new tasks and objects

Learn more and contribute to the growing tool library:
Project Website: https://t.co/BNRZihjElC
Arxiv: https://t.co/hao8B4btBX