Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Boston Dynamics’ robot-behavior team lead highlights three core initiatives aimed at advancing Atlas’s dexterity: ⦿ Reinforcement learning in simulation ⦿ Whole-body teleoperation to collect data for imitation learning ⦿ Tactile sensing grippers

The Humanoid Hub

60,420 subscribers

18,029 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics Education

Anya Rossi• Live Now

Private livecam show

7 Comments

The Humanoid Hub1 year ago

Source:

Rainmaker2 years ago

💡 Learn how Reinforcement Learning can boost your trading performance! In this free Substack article I share full code of a trading algorithm based on Reinforcement Learning that beats other Machine Learning models as well as simply buying and holding the stock.

Phil Trubey1 year ago

The biggest thing from vid was that automatic retry when initial attempt fails is an emergent behavior that comes with sim training at scale. Very very interesting. Bolsters Tesla approach building out their huge compute clusters and manufacturing a fleet for teleop training.

Judge DredD1 year ago

Bad optimus copy

The Robot Services Exchange1 year ago

solid

VentureMind AI1 year ago

Working together to build the future 🤝

MatRat211 year ago

Hell yeah Atlas!

Related Videos

TWIST: a real-time teleoperation system for humanoid robots to mimic whole-body motions. Reference motion data is generated by retargeting human motion-capture data to the robot. Then, the controller is trained in simulation using reinforcement learning and behavior cloning.

TWIST: a real-time teleoperation system for humanoid robots to mimic whole-body motions. Reference motion data is generated by retargeting human motion-capture data to the robot. Then, the controller is trained in simulation using reinforcement learning and behavior cloning.

The Humanoid Hub

46,715 views • 1 year ago

Reinforcement learning is used to speed the production of behavior for the Boston Dynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.

Reinforcement learning is used to speed the production of behavior for the Boston Dynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.

RAI Institute

76,647 views • 1 year ago

Using reinforcement learning, we trained policies for Boston Dynamics Spot that allow the robot to achieve record running speeds of 11.5 mph (5.2 m/s) — over three times faster than Spot's default max speed.

Using reinforcement learning, we trained policies for Boston Dynamics Spot that allow the robot to achieve record running speeds of 11.5 mph (5.2 m/s) — over three times faster than Spot's default max speed.

RAI Institute

98,538 views • 1 year ago

The AMO (Adaptive Motion Optimization) project, developed by researchers at UC San Diego, introduces a novel framework for enhancing the dexterity and adaptability of humanoid robots. This system integrates simulation-to-real reinforcement learning with trajectory optimization to achieve real-time, adaptive whole-body control Video Credit: USD #engineering #technology #robotics #robots

The AMO (Adaptive Motion Optimization) project, developed by researchers at UC San Diego, introduces a novel framework for enhancing the dexterity and adaptability of humanoid robots. This system integrates simulation-to-real reinforcement learning with trajectory optimization to achieve real-time, adaptive whole-body control Video Credit: USD #engineering #technology #robotics #robots

Wevolver

13,632 views • 1 year ago

🎉Excited to share a fun little hardware project we’ve been working on. GELLO is an intuitive and low cost teleoperation device for robot arms that costs less than $300. We've seen the importance of data quality in imitation learning. Our goal is to make this more accessible 1/n

🎉Excited to share a fun little hardware project we’ve been working on. GELLO is an intuitive and low cost teleoperation device for robot arms that costs less than $300. We've seen the importance of data quality in imitation learning. Our goal is to make this more accessible 1/n

Philipp Wu

162,934 views • 2 years ago

Today, we're joined by Nikita Rudin, co-founder and CEO of Flexion to discuss the gap between current robotic capabilities and what’s required to deploy fully autonomous robots in the real world. Nikita explains how reinforcement learning and simulation have driven rapid progress in robot locomotion—and why locomotion is still far from “solved.” We dig into the sim2real gap, and how adding visual inputs introduces noise and significantly complicates sim-to-real transfer. We also explore the debate between end-to-end models and modular approaches, and why separating locomotion, planning, and semantics remains a pragmatic approach today. Nikita also introduces the concept of "real-to-sim", which uses real-world data to refine simulation parameters for higher fidelity training, discusses how reinforcement learning, imitation learning, and teleoperation data are combined to train robust policies for both quadruped and humanoid robots, and introduces Flexion's hierarchical approach that utilizes pre-trained Vision-Language Models (VLMs) for high-level task orchestration with Vision-Language-Action (VLA) models and low-level whole-body trackers. Finally, Nikita shares the behind-the-scenes in humanoid robot demos, his take on reinforcement learning in simulation versus the real world, the nuances of reward tuning, and offers practical advice for researchers and practitioners looking to get started in robotics today. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:07 - Is robot locomotion solved? 06:04 - Sim-to-real gap 08:58 - Adding semantics to policies 09:42 - Modular vs end-to-end architectures 10:29 - Planner model 12:21 - Adapting RL techniques from quadrupeds to humanoids 15:39 - Behind robot demos 18:09 - Humanoid robots in home environments 22:03 - Training approach 23:56 - VLA models 27:59 - Closing the sim-to-real gap 32:55 - Task orchestration using VLMs 36:38 - Tool use 38:10 - Model hierarchy 43:37 - Simulator versus simulation environment 44:57 - Combining imitation learning and reinforcement learning 46:42 - RL in real world versus RL in simulation 52:58 - Reward tuning and value functions in robotics 56:38 - Predictions 1:00:10 - Humanoids, quadropeds, and wheeled platforms 1:02:45 - Advice, recommended robot kits, and community pla

Today, we're joined by Nikita Rudin, co-founder and CEO of Flexion to discuss the gap between current robotic capabilities and what’s required to deploy fully autonomous robots in the real world. Nikita explains how reinforcement learning and simulation have driven rapid progress in robot locomotion—and why locomotion is still far from “solved.” We dig into the sim2real gap, and how adding visual inputs introduces noise and significantly complicates sim-to-real transfer. We also explore the debate between end-to-end models and modular approaches, and why separating locomotion, planning, and semantics remains a pragmatic approach today. Nikita also introduces the concept of "real-to-sim", which uses real-world data to refine simulation parameters for higher fidelity training, discusses how reinforcement learning, imitation learning, and teleoperation data are combined to train robust policies for both quadruped and humanoid robots, and introduces Flexion's hierarchical approach that utilizes pre-trained Vision-Language Models (VLMs) for high-level task orchestration with Vision-Language-Action (VLA) models and low-level whole-body trackers. Finally, Nikita shares the behind-the-scenes in humanoid robot demos, his take on reinforcement learning in simulation versus the real world, the nuances of reward tuning, and offers practical advice for researchers and practitioners looking to get started in robotics today. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:07 - Is robot locomotion solved? 06:04 - Sim-to-real gap 08:58 - Adding semantics to policies 09:42 - Modular vs end-to-end architectures 10:29 - Planner model 12:21 - Adapting RL techniques from quadrupeds to humanoids 15:39 - Behind robot demos 18:09 - Humanoid robots in home environments 22:03 - Training approach 23:56 - VLA models 27:59 - Closing the sim-to-real gap 32:55 - Task orchestration using VLMs 36:38 - Tool use 38:10 - Model hierarchy 43:37 - Simulator versus simulation environment 44:57 - Combining imitation learning and reinforcement learning 46:42 - RL in real world versus RL in simulation 52:58 - Reward tuning and value functions in robotics 56:38 - Predictions 1:00:10 - Humanoids, quadropeds, and wheeled platforms 1:02:45 - Advice, recommended robot kits, and community pla

The TWIML AI Podcast

22,592 views • 7 months ago

In the last month, we’ve been building an open-source framework for robot learning and sim-to-real transfer, made for RL whole-body control from simple walking to complex human imitation Check out the details on HN: Get started in 5 minutes ⬇️

In the last month, we’ve been building an open-source framework for robot learning and sim-to-real transfer, made for RL whole-body control from simple walking to complex human imitation Check out the details on HN: Get started in 5 minutes ⬇️

K-Scale Labs

75,983 views • 1 year ago

In order for robots to be deployed in the real world, performing tasks of real value, they must be reliable. Unfortunately, even more, most robotic demos work maybe 70-80% of the time at best. The way to get better reliability is to do real-world reinforcement learning: having the robot teach itself how to perform the task up to a high level of success. The key to doing this is to start with a core of expert human data, use that to train a policy then iteratively improve it, until finally finishing with on-policy reinforcement learning. Kun Lei talks through a unified framework for imitation and reinforcement learning based on PPO, which enables this improvement process. In this episode, Kun Lei explains the theory behind his reinforcement learning method and how it allowed his robot to run in a shopping mall juicing oranges for seven hours at a time, among experiments on a wide variety of tasks and embodiments. Watch episode 58 of RoboPapers now, hosted by Michael Cho - Rbt/Acc and Chris Paxton!

In order for robots to be deployed in the real world, performing tasks of real value, they must be reliable. Unfortunately, even more, most robotic demos work maybe 70-80% of the time at best. The way to get better reliability is to do real-world reinforcement learning: having the robot teach itself how to perform the task up to a high level of success. The key to doing this is to start with a core of expert human data, use that to train a policy then iteratively improve it, until finally finishing with on-policy reinforcement learning. Kun Lei talks through a unified framework for imitation and reinforcement learning based on PPO, which enables this improvement process. In this episode, Kun Lei explains the theory behind his reinforcement learning method and how it allowed his robot to run in a shopping mall juicing oranges for seven hours at a time, among experiments on a wide variety of tasks and embodiments. Watch episode 58 of RoboPapers now, hosted by Michael Cho - Rbt/Acc and Chris Paxton!

RoboPapers

18,813 views • 6 months ago

Boston Dynamics has demonstrated its new Atlas humanoid robot lifting and carrying a 50-pound fridge. The robot uses its whole body to balance and move the heavy object in a natural, human-like way. Before doing it in the real world, Atlas practiced the task for millions of hours in a virtual simulation.

Boston Dynamics has demonstrated its new Atlas humanoid robot lifting and carrying a 50-pound fridge. The robot uses its whole body to balance and move the heavy object in a natural, human-like way. Before doing it in the real world, Atlas practiced the task for millions of hours in a virtual simulation.

Space and Technology

180,475 views • 2 months ago

A high-quality haptic control for robots as a weekend project? All for under $600. [📍 Save Github & arXiv for later] A team built DOGlove, an open-source haptic glove for robot teleoperation that you can assemble yourself for under $600. It is built for real control, not demos. • Tracks 21 degrees of freedom with a custom joint design • Provides cable-driven force feedback plus fingertip haptics • Can be used to collect data for imitation learning Affordable haptics could make teleoperation more reliable and improve the quality of data we use to train physical AI. Project link: Credit: DOGlove team, shared by Han Zhang —- Weekly robotics and AI insights. Subscribe free:

A high-quality haptic control for robots as a weekend project? All for under $600. [📍 Save Github & arXiv for later] A team built DOGlove, an open-source haptic glove for robot teleoperation that you can assemble yourself for under $600. It is built for real control, not demos. • Tracks 21 degrees of freedom with a custom joint design • Provides cable-driven force feedback plus fingertip haptics • Can be used to collect data for imitation learning Affordable haptics could make teleoperation more reliable and improve the quality of data we use to train physical AI. Project link: Credit: DOGlove team, shared by Han Zhang —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

18,290 views • 6 months ago

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

42,864 views • 6 months ago

Real-world robot data is expensive and slow to collect, creating a major challenge for humanoid development. 🤖 The NVIDIA GR00T N1.6 open vision language action model is pre-trained on a diverse mix of data, including thousands of hours of Stanford Vision and Learning Lab’s BEHAVIOR simulation data, which covers long-horizon everyday manipulation tasks. This diverse training is the key to robust cross-embodiment performance and real-world adaptability. 🌍 Read the blog 🔗

Real-world robot data is expensive and slow to collect, creating a major challenge for humanoid development. 🤖 The NVIDIA GR00T N1.6 open vision language action model is pre-trained on a diverse mix of data, including thousands of hours of Stanford Vision and Learning Lab’s BEHAVIOR simulation data, which covers long-horizon everyday manipulation tasks. This diverse training is the key to robust cross-embodiment performance and real-world adaptability. 🌍 Read the blog 🔗

NVIDIA Robotics

13,479 views • 6 months ago

1/🧠Humans are the best robot data source — but video alone misses one thing: force. 2/🙁Tactile gloves capture force — but they're costly and block the real touch manipulation depends on. 3/💪Maybe the future of touch lives on your wrist: surface EMG reads the muscles that cause force — tactile sensing without ever touching a tactile sensor. 4/🔥Want a fully open-source framework — hardware + software — to train your own force-aware learn-from-human-data robot policy? 🚀We introduce ForceBand: Learning Forceful Manipulation with sEMG -- bring force into human videos with sEMG, for force-aware manipulation ⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Force Beyond Vision ✦ Free-Hand Force Sensing ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Low-Cost & Easy-to-Implement Let's squeeze every bit of signal out of human data, and let robots feel the force! 🌐 Website: 📄 Paper: 💻 Code: 🎥 Video: 🧵 1/n

1/🧠Humans are the best robot data source — but video alone misses one thing: force. 2/🙁Tactile gloves capture force — but they're costly and block the real touch manipulation depends on. 3/💪Maybe the future of touch lives on your wrist: surface EMG reads the muscles that cause force — tactile sensing without ever touching a tactile sensor. 4/🔥Want a fully open-source framework — hardware + software — to train your own force-aware learn-from-human-data robot policy? 🚀We introduce ForceBand: Learning Forceful Manipulation with sEMG -- bring force into human videos with sEMG, for force-aware manipulation ⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Force Beyond Vision ✦ Free-Hand Force Sensing ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Low-Cost & Easy-to-Implement Let's squeeze every bit of signal out of human data, and let robots feel the force! 🌐 Website: 📄 Paper: 💻 Code: 🎥 Video: 🧵 1/n

Zhi (Leo) Wang

50,541 views • 1 month ago

Today at Meta FAIR we’re announcing three new cutting-edge developments in robotics and touch perception — and releasing a collection of artifacts to empower the community to build on this work. Details on all of this new work ➡️ 1️⃣ Meta Sparsh is the first general-purpose encoder for vision-based tactile sensing that works across many tactile sensors and many tasks. Trained on 460K+ tactile images using self-supervised learning. 2️⃣ Meta Digit 360 is a breakthrough artificial fingertip-based tactile sensor, equipped with 18+ sensing features to deliver detailed touch data with human-level precision and touch-sensing capabilities. 3️⃣ Meta Digit Plexus is a standardized platform for robotic sensor connections and interactions. It provides a hardware-software solution to integrate tactile sensors on a single robot hand and enables seamless data collection, control and analysis over a single cable. The potential impact of expanding capabilities and components like these for the open source community ranges from medical research to supply chain, manufacturing and much more. We’re excited to continue this work with the broader community.

Today at Meta FAIR we’re announcing three new cutting-edge developments in robotics and touch perception — and releasing a collection of artifacts to empower the community to build on this work. Details on all of this new work ➡️ 1️⃣ Meta Sparsh is the first general-purpose encoder for vision-based tactile sensing that works across many tactile sensors and many tasks. Trained on 460K+ tactile images using self-supervised learning. 2️⃣ Meta Digit 360 is a breakthrough artificial fingertip-based tactile sensor, equipped with 18+ sensing features to deliver detailed touch data with human-level precision and touch-sensing capabilities. 3️⃣ Meta Digit Plexus is a standardized platform for robotic sensor connections and interactions. It provides a hardware-software solution to integrate tactile sensors on a single robot hand and enables seamless data collection, control and analysis over a single cable. The potential impact of expanding capabilities and components like these for the open source community ranges from medical research to supply chain, manufacturing and much more. We’re excited to continue this work with the broader community.

AI at Meta

453,343 views • 1 year ago

My last PhD project at CMU will be presented today and tomorrow at Conference on Robot Learning as one of the Demos: SIAT (SIAT: Stretch control with Immersive AR Teleoperation) Find Vidhi Jain, Su Li and Yonatan Bisk who will be presenting this work in person. The original goal of me doing this project is to collect realistic human-robot interaction demonstration data just like the way you interact with your friends. But you can also use this package for non-social task data collection as well.

My last PhD project at CMU will be presented today and tomorrow at Conference on Robot Learning as one of the Demos: SIAT (SIAT: Stretch control with Immersive AR Teleoperation) Find Vidhi Jain, Su Li and Yonatan Bisk who will be presenting this work in person. The original goal of me doing this project is to collect realistic human-robot interaction demonstration data just like the way you interact with your friends. But you can also use this package for non-social task data collection as well.

Hao Zhu

12,458 views • 1 year ago

Training a Whole-Body Control Foundation Model -- new work from my team at Agility Robotics A neural network for controlling our humanoid robots which is robust to disturbances, can handle heavy objects, and is a powerful platform for learning new whole-body skills learn more in our blog post ->

Training a Whole-Body Control Foundation Model -- new work from my team at Agility Robotics A neural network for controlling our humanoid robots which is robust to disturbances, can handle heavy objects, and is a powerful platform for learning new whole-body skills learn more in our blog post ->

Chris Paxton

45,068 views • 11 months ago

🎾Your humanoid tennis player is here!🤖 Introducing LATENT (Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data) — the world’s first real-time whole-body planning and control algorithm for athletic humanoid tennis. For the first time, a humanoid robot can sustain high-dynamic, long-horizon tennis rallies with millisecond-level reactions, precise ball striking, and natural whole-body motion. This marks a leap from mechanical motion imitation to intelligent, decision-driven athletic interaction. #Galbot #Robotics #Innovation #AI #Technology #Humanoid

🎾Your humanoid tennis player is here!🤖 Introducing LATENT (Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data) — the world’s first real-time whole-body planning and control algorithm for athletic humanoid tennis. For the first time, a humanoid robot can sustain high-dynamic, long-horizon tennis rallies with millisecond-level reactions, precise ball striking, and natural whole-body motion. This marks a leap from mechanical motion imitation to intelligent, decision-driven athletic interaction. #Galbot #Robotics #Innovation #AI #Technology #Humanoid

Galbot

45,818 views • 4 months ago

VLAI Robotics Launches High-Dexterity Dual-Arm Robot Starting at ~$5,500 USD VLAI Robotics, utilizing the open-source design of Japan’s OpenArm team, has introduced a high-dexterity, low-cost bimanual robotic system. The product is priced from 39,900 RMB (approximately 5,500 USD), making high-level research tools accessible to institutions and developers. The robot features a human-scale, arm-hand integrated design with up to 16 DOF (8 DOF per arm, including the gripper). It can handle a dual-arm peak payload of 12 kg while maintaining high precision. A key breakthrough is its ability to replicate human upper limb movement trajectories, which enhances data quality for imitation learning and remote operation. VLAI Robotics handled the domestic engineering, manufacturing, and VLA (Vision-Language-Action) algorithm integration, with quality control organized according to the strict standards of the OpenArm R&D framework. The robot is highly adaptable for research, education, and Physical AI training, supporting easy expansion for features like VR teleoperation.

VLAI Robotics Launches High-Dexterity Dual-Arm Robot Starting at ~$5,500 USD VLAI Robotics, utilizing the open-source design of Japan’s OpenArm team, has introduced a high-dexterity, low-cost bimanual robotic system. The product is priced from 39,900 RMB (approximately 5,500 USD), making high-level research tools accessible to institutions and developers. The robot features a human-scale, arm-hand integrated design with up to 16 DOF (8 DOF per arm, including the gripper). It can handle a dual-arm peak payload of 12 kg while maintaining high precision. A key breakthrough is its ability to replicate human upper limb movement trajectories, which enhances data quality for imitation learning and remote operation. VLAI Robotics handled the domestic engineering, manufacturing, and VLA (Vision-Language-Action) algorithm integration, with quality control organized according to the strict standards of the OpenArm R&D framework. The robot is highly adaptable for research, education, and Physical AI training, supporting easy expansion for features like VR teleoperation.

RoboHub🤖

12,961 views • 9 months ago

Sports like tennis are great examples of the sort of dynamic whole-body interaction that’s possible with humanoid robots. But capturing examples of fast, dynamic interactions from humans is really difficult. Enter LATENT, which uses lower-quality human data plus reinforcement learning to teach a robot to play tennis, able to complete back-and-forth volleys at a human level. LATENT has three steps: (1) collecting imperfect human data like a backswing, (2) using these to learn a latent action space, and (3) they train a high-level policy in simulation which can compose these actions and execute tennis skills on a robot. Haofei Lu and Yunrui Lian join us to tell us about their method. Watch Episode #80 of RoboPapers, with Chris Paxton and Jiafei Duan, now to learn more!

Sports like tennis are great examples of the sort of dynamic whole-body interaction that’s possible with humanoid robots. But capturing examples of fast, dynamic interactions from humans is really difficult. Enter LATENT, which uses lower-quality human data plus reinforcement learning to teach a robot to play tennis, able to complete back-and-forth volleys at a human level. LATENT has three steps: (1) collecting imperfect human data like a backswing, (2) using these to learn a latent action space, and (3) they train a high-level policy in simulation which can compose these actions and execute tennis skills on a robot. Haofei Lu and Yunrui Lian join us to tell us about their method. Watch Episode #80 of RoboPapers, with Chris Paxton and Jiafei Duan, now to learn more!

RoboPapers

30,004 views • 2 months ago

I was really impressed by the UMI gripper (Cheng Chi et al.), but a key limitation is that **force-related data wasn’t captured**: humans feel haptic feedback through the mechanical springs, but the robot couldn’t leverage that info, limiting the data’s value for fine-grained manipulation tasks. Led by my amazing students Yolanda Zhu and Binghao Huang, we designed a **portable visuo-tactile gripper** by integrating our dense, flexible tactile arrays with the UMI gripper to enable large-scale in-the-wild data collection. 🔗 We demonstrate **cross-modal representation learning** and **downstream policy learning** on tasks requiring in-hand state estimation (e.g., test tube reorientation) and fine-grained force sensing (e.g., pipette fluid transfer). Key takeaways: - Our flexible tactile arrays store the rich haptic information humans perceive as dense tactile signals. - Portability and robustness are key for in-the-wild data collection; our portable gripper is compact, lightweight, and durable. - Touch provides precise, robust measurements of in-hand object pose, invariant to lighting and viewpoint. - Cross-modal pretraining on large-scale in-the-wild data significantly improves policy robustness and sample efficiency (as shown many times before — and verified again here!). Also check out our previous investigations of dense, flexible tactile grids for understanding human-robot-environment interactions: - Dense tactile glove (Nature ’19): - 3D-ViTac (CoRL ’24):

I was really impressed by the UMI gripper (Cheng Chi et al.), but a key limitation is that force-related data wasn’t captured: humans feel haptic feedback through the mechanical springs, but the robot couldn’t leverage that info, limiting the data’s value for fine-grained manipulation tasks. Led by my amazing students Yolanda Zhu and Binghao Huang, we designed a portable visuo-tactile gripper by integrating our dense, flexible tactile arrays with the UMI gripper to enable large-scale in-the-wild data collection. 🔗 We demonstrate cross-modal representation learning and downstream policy learning on tasks requiring in-hand state estimation (e.g., test tube reorientation) and fine-grained force sensing (e.g., pipette fluid transfer). Key takeaways: - Our flexible tactile arrays store the rich haptic information humans perceive as dense tactile signals. - Portability and robustness are key for in-the-wild data collection; our portable gripper is compact, lightweight, and durable. - Touch provides precise, robust measurements of in-hand object pose, invariant to lighting and viewpoint. - Cross-modal pretraining on large-scale in-the-wild data significantly improves policy robustness and sample efficiency (as shown many times before — and verified again here!). Also check out our previous investigations of dense, flexible tactile grids for understanding human-robot-environment interactions: - Dense tactile glove (Nature ’19): - 3D-ViTac (CoRL ’24):

Yunzhu Li

13,188 views • 1 year ago