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.

Learning about active perception with Haoyu Xiong -- your robot needs a head, and to be able to control where it's looking, in order to perform complex tasks!

Chris Paxton

29,114 subscribers

22,784 views • 10 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

We finished evaluating π0.7, our new model at Physical Intelligence. What I'm most excited about with π0.7 is that it's starting to show some surprising emergent compositional generalization, being able to both perform complex tasks and learn new tasks just from instructions.

We finished evaluating π0.7, our new model at Physical Intelligence. What I'm most excited about with π0.7 is that it's starting to show some surprising emergent compositional generalization, being able to both perform complex tasks and learn new tasks just from instructions.

Sergey Levine

60,882 views • 3 months ago

The delete parasite’s end goal is to be able to control your mind, so they can control your energy. In order to do so they have to be able to control your behaviour and the physical aspects

The delete parasite’s end goal is to be able to control your mind, so they can control your energy. In order to do so they have to be able to control your behaviour and the physical aspects

TruthSeeker01011

24,001 views • 5 months ago

Optimus is becoming more and more useful, and soon it will be able to perform tasks like those in Video 2, performing complex processes skillfully and quickly.

Optimus is becoming more and more useful, and soon it will be able to perform tasks like those in Video 2, performing complex processes skillfully and quickly.

CyberRobo

14,939 views • 1 year ago

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Max Fu

40,466 views • 1 year ago

With about an hour of training you will be able to set up your Stretch to perform tasks around the home. Here: navigation and end-to-end door opening via Diffusion Policy.

With about an hour of training you will be able to set up your Stretch to perform tasks around the home. Here: navigation and end-to-end door opening via Diffusion Policy.

Chris Paxton

14,306 views • 2 years ago

Your best ability to impact a team is your coachABILITY. CoachABLE means: ABLE to listen to feedback ABLE to learn from mistakes ABLE to adapt to what the team needs ABLE to attack hard tasks with enthusiasm ABLE to hold yourself accountable Be willing and ABLE...coachABLE.

Your best ability to impact a team is your coachABILITY. CoachABLE means: ABLE to listen to feedback ABLE to learn from mistakes ABLE to adapt to what the team needs ABLE to attack hard tasks with enthusiasm ABLE to hold yourself accountable Be willing and ABLE...coachABLE.

The Winning Difference

64,548 views • 2 years ago

Every home is different. That means that to build a useful home robot, we must be able to perform zero-shot generalization on a wide range of tasks. Humanoid company 1X has a solution: world models. 1X Director of Evaluations Daniel Ho joins us on RoboPapers to talk about: - why world models are the future for scaling robot learning - how to use world models for robot control - what world models unlock for evaluating robot model performance - how we can hill-climb from here to general purpose robots Watch Episode #61 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, now!

Every home is different. That means that to build a useful home robot, we must be able to perform zero-shot generalization on a wide range of tasks. Humanoid company 1X has a solution: world models. 1X Director of Evaluations Daniel Ho joins us on RoboPapers to talk about: - why world models are the future for scaling robot learning - how to use world models for robot control - what world models unlock for evaluating robot model performance - how we can hill-climb from here to general purpose robots Watch Episode #61 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, now!

RoboPapers

27,567 views • 6 months ago

Train your avatars to interact with 3D scenes. We use adversarial imitation learning and reinforcement learning to train physically-simulated characters that perform scene interaction tasks in a natural and life-like manner. Today at #SIGGRAPH2023.

Train your avatars to interact with 3D scenes. We use adversarial imitation learning and reinforcement learning to train physically-simulated characters that perform scene interaction tasks in a natural and life-like manner. Today at #SIGGRAPH2023.

Michael Black

46,237 views • 3 years ago

This indie developer is making a game where you are able to launch and combine dice (with physics!) in order to launch powerful attacks, with the merging mechanics looking so satifsying. It's called Rune Dice, will you be getting this?

This indie developer is making a game where you are able to launch and combine dice (with physics!) in order to launch powerful attacks, with the merging mechanics looking so satifsying. It's called Rune Dice, will you be getting this?

Best Indie Games

135,412 views • 3 months ago

Physical Intelligence's π₀, a general-purpose robot foundation model that combines Internet-scale vision-language pretraining with robot interaction data to execute tasks. They aim "to develop foundation models that can control any robot to perform any task" Autonomous demos:

Physical Intelligence's π₀, a general-purpose robot foundation model that combines Internet-scale vision-language pretraining with robot interaction data to execute tasks. They aim "to develop foundation models that can control any robot to perform any task" Autonomous demos:

The Humanoid Hub

196,055 views • 1 year ago

“We need to be able to reach people in order to avoid catastrophic consequences.” Ted Chaiban was recently in Kassala, Sudan, where UNICEF and partners are supporting displaced children and families with urgent humanitarian needs.

“We need to be able to reach people in order to avoid catastrophic consequences.” Ted Chaiban was recently in Kassala, Sudan, where UNICEF and partners are supporting displaced children and families with urgent humanitarian needs.

UNICEF

23,002 views • 1 year ago

This is a single uncut video, showing a robot learning several tasks instantly, after just one demonstration each ... This is possible because we've now been able to achieve in-context learning for everyday robotics tasks, and I'm very excited to announce our latest paper: 🎆 Instant Policy: In-Context Imitation Learning via Graph Diffusion 🎆 (1/6) 🧵👇

This is a single uncut video, showing a robot learning several tasks instantly, after just one demonstration each ... This is possible because we've now been able to achieve in-context learning for everyday robotics tasks, and I'm very excited to announce our latest paper: 🎆 Instant Policy: In-Context Imitation Learning via Graph Diffusion 🎆 (1/6) 🧵👇

Edward Johns

74,683 views • 1 year ago

🤖 What if a humanoid robot could make a hamburger from raw ingredients—all the way to your plate? 🔥 Excited to announce ViTacFormer: our new pipeline for next-level dexterous manipulation with active vision + high-resolution touch. 🎯 For the first time ever, we demonstrate ~2.5 minutes of continuous, autonomous control—combining active vision, high-res touch, and high-DoF robot hands SharpaWave — to complete complex, real-world tasks. Code is fully released; check out our: Homepage: Paper link: Github:

🤖 What if a humanoid robot could make a hamburger from raw ingredients—all the way to your plate? 🔥 Excited to announce ViTacFormer: our new pipeline for next-level dexterous manipulation with active vision + high-resolution touch. 🎯 For the first time ever, we demonstrate ~2.5 minutes of continuous, autonomous control—combining active vision, high-res touch, and high-DoF robot hands SharpaWave — to complete complex, real-world tasks. Code is fully released; check out our: Homepage: Paper link: Github:

Haoran Geng

95,549 views • 1 year ago

Tomorrow’s Science, Today’s Robot A humanoid robot is a type of robot designed to look and act like a human being. It usually has a body structure with a head, torso, arms, and legs, and may be programmed to walk, talk, or perform tasks similar to humans. Some humanoid robots are made mainly for research and testing, while others are used in healthcare, customer service, education, or entertainment. Advanced ones even use artificial intelligence (AI) to recognise speech, facial expressions, and interact naturally with people.

Tomorrow’s Science, Today’s Robot A humanoid robot is a type of robot designed to look and act like a human being. It usually has a body structure with a head, torso, arms, and legs, and may be programmed to walk, talk, or perform tasks similar to humans. Some humanoid robots are made mainly for research and testing, while others are used in healthcare, customer service, education, or entertainment. Advanced ones even use artificial intelligence (AI) to recognise speech, facial expressions, and interact naturally with people.

NTANetwork

349,326 views • 10 months ago

“A man in order to avoid prostate problem, failure and cardiac problem, he needs to be able to knack 21 times a month” — Dr. Rasheed Abassi.

“A man in order to avoid prostate problem, failure and cardiac problem, he needs to be able to knack 21 times a month” — Dr. Rasheed Abassi.

YabaLeftOnline

373,219 views • 1 month ago

This poop-looking robot could one day perform tasks inside the human body. The robot is made of magnetic slime that can be controlled by external magnets to move, rotate, and form shapes. #gigadgets #medical #robootics #slime #research

This poop-looking robot could one day perform tasks inside the human body. The robot is made of magnetic slime that can be controlled by external magnets to move, rotate, and form shapes. #gigadgets #medical #robootics #slime #research

GiGadgets

54,845 views • 3 years 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

How to teach robots to perform long-horizon tasks efficiently and robustly🦾? Introducing MimicPlay - an imitation learning algorithm that uses "cheap human play data". Our approach unlocks both real-time planning through raw perception and strong robustness to disturbances!🧵👇

How to teach robots to perform long-horizon tasks efficiently and robustly🦾? Introducing MimicPlay - an imitation learning algorithm that uses "cheap human play data". Our approach unlocks both real-time planning through raw perception and strong robustness to disturbances!🧵👇

Chen Wang

288,642 views • 3 years ago