正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Using reinforcement learning we have expanded the range of techniques the Ultra Mobile Vehicle (UMV) uses to handle terrain and obstacles, including hops, out-of-plane balance, and level-ground flips. Millions of physics-based simulations provide training data to support zero-shot transfers.

RAI Institute

7,843 subscribers

75,089 次观看 • 10 个月前 •via X (Twitter)

科学技术游戏教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

reinforcement learning expanding the range of techniques of the Ultra Mobile Vehicle (UMV)

reinforcement learning expanding the range of techniques of the Ultra Mobile Vehicle (UMV)

Science girl

19,399 次观看 • 10 个月前

In this demo, An Ultra Mobile Vehicle (UMV) drives, turns, jumps, tricks, and comes to a sudden stop called a track-stand. All of the driving, landings, balance, and track-stands are done using reinforcement learning. Wait for it... 😮 🎥RAI institute.

In this demo, An Ultra Mobile Vehicle (UMV) drives, turns, jumps, tricks, and comes to a sudden stop called a track-stand. All of the driving, landings, balance, and track-stands are done using reinforcement learning. Wait for it... 😮 🎥RAI institute.

HOW THINGS WORK

211,806 次观看 • 1 年前

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

76,576 次观看 • 1 年前

Soccer players have to master a range of dynamic skills, from turning and kicking to chasing a ball. How could robots do the same? ⚽ We trained our AI agents to demonstrate a range of agile behaviors using reinforcement learning. Here’s how. 🧵

Soccer players have to master a range of dynamic skills, from turning and kicking to chasing a ball. How could robots do the same? ⚽ We trained our AI agents to demonstrate a range of agile behaviors using reinforcement learning. Here’s how. 🧵

Google DeepMind

447,662 次观看 • 2 年前

Φ-SO : Physical Symbolic Optimization - Learning Physics from Data 🧠 The Physical Symbolic Optimization package uses deep reinforcement learning to discover physical laws from data. Here is Φ-SO discovering the analytical expression of a damped harmonic oscillator.

Φ-SO : Physical Symbolic Optimization - Learning Physics from Data 🧠 The Physical Symbolic Optimization package uses deep reinforcement learning to discover physical laws from data. Here is Φ-SO discovering the analytical expression of a damped harmonic oscillator.

Jousef Murad

433,149 次观看 • 2 年前

When asked if Egypt will provide troops on the ground in Gaza to help support its security and stabilization, Egyptian Foreign Minister Badr Abdelatty says, “Deployment of international force is on the table. We are supporting this idea, of course.” “We are going to support and to commit troops within specific parameters,” he tells Margaret Brennan. “We must have a mandate by the Security Council to endorse it. And of course, to specify the mission of the troops on the ground, which will be peacekeeping, and how to provide training to the Palestinian policemen, in order to do their job to have law enforcement on the ground.”

When asked if Egypt will provide troops on the ground in Gaza to help support its security and stabilization, Egyptian Foreign Minister Badr Abdelatty says, “Deployment of international force is on the table. We are supporting this idea, of course.” “We are going to support and to commit troops within specific parameters,” he tells Margaret Brennan. “We must have a mandate by the Security Council to endorse it. And of course, to specify the mission of the troops on the ground, which will be peacekeeping, and how to provide training to the Palestinian policemen, in order to do their job to have law enforcement on the ground.”

Face The Nation

22,993 次观看 • 8 个月前

RAI Institute’s Ultra mobility vehicle is showing off advanced new stunts with smooth 360-degree spins, kip jumps, flips, and bunny hops. The AI-powered machine performs sharp turns, mid-air rotations, and clean landings with impressive balance and precision. And this is only the beginning of what the vehicle can achieve.

RAI Institute’s Ultra mobility vehicle is showing off advanced new stunts with smooth 360-degree spins, kip jumps, flips, and bunny hops. The AI-powered machine performs sharp turns, mid-air rotations, and clean landings with impressive balance and precision. And this is only the beginning of what the vehicle can achieve.

Space and Technology

56,704 次观看 • 1 个月前

Today, we're joined by Sergey Levine, associate professor at UC Berkeley EECS and co-founder of Physical Intelligence to discuss π0 (pi-zero), a general-purpose robotic foundation model. We dig into the model architecture, which pairs a vision language model (VLM) with a diffusion-based action expert, and the model training "recipe," emphasizing the roles of pre-training and post-training with a diverse mixture of real-world data to ensure robust and intelligent robot learning. We review the data collection approach, which uses human operators and teleoperation rigs, the potential of synthetic data and reinforcement learning in enhancing robotic capabilities, and much more. We also introduce the team’s new FAST tokenizer, which opens the door to a fully Transformer-based model and significant improvements in learning and generalization. Finally, we cover the open-sourcing of π0 and future directions for their research. 🎧 / 🎥 Listen or watch the full episode on our page: 📖 CHAPTERS =============================== 00:00 - Introduction 2:14 - Physical Intelligence 3:47 - Key challenges in robotic learning 6:13 - Reinforcement learning in π0 and robotic foundation models 8:36 - π0 VLM model architecture 15:33 - π0 model recipe 18:39 - Pre-training dataset 22:47 - Post-training 24:23 - Laundry folding demo 31:32 - Scaling laws on π0 model 34:57 - FAST 40:26 - Open sourcing π0 43:37 - Other robot types 46:27 - Future directions

Today, we're joined by Sergey Levine, associate professor at UC Berkeley EECS and co-founder of Physical Intelligence to discuss π0 (pi-zero), a general-purpose robotic foundation model. We dig into the model architecture, which pairs a vision language model (VLM) with a diffusion-based action expert, and the model training "recipe," emphasizing the roles of pre-training and post-training with a diverse mixture of real-world data to ensure robust and intelligent robot learning. We review the data collection approach, which uses human operators and teleoperation rigs, the potential of synthetic data and reinforcement learning in enhancing robotic capabilities, and much more. We also introduce the team’s new FAST tokenizer, which opens the door to a fully Transformer-based model and significant improvements in learning and generalization. Finally, we cover the open-sourcing of π0 and future directions for their research. 🎧 / 🎥 Listen or watch the full episode on our page: 📖 CHAPTERS =============================== 00:00 - Introduction 2:14 - Physical Intelligence 3:47 - Key challenges in robotic learning 6:13 - Reinforcement learning in π0 and robotic foundation models 8:36 - π0 VLM model architecture 15:33 - π0 model recipe 18:39 - Pre-training dataset 22:47 - Post-training 24:23 - Laundry folding demo 31:32 - Scaling laws on π0 model 34:57 - FAST 40:26 - Open sourcing π0 43:37 - Other robot types 46:27 - Future directions

The TWIML AI Podcast

19,942 次观看 • 1 年前

Robots can now walk blind with Figure AI's Helix Walking Controller. Instead of using cameras, the controller relies on the robot's internal sensors and reinforcement learning to maintain balance while walking. The controller, unveiled last year, allows the robot to stay balanced, recover from pushes, and move confidently across difficult terrain.

Robots can now walk blind with Figure AI's Helix Walking Controller. Instead of using cameras, the controller relies on the robot's internal sensors and reinforcement learning to maintain balance while walking. The controller, unveiled last year, allows the robot to stay balanced, recover from pushes, and move confidently across difficult terrain.

Space and Technology

27,504 次观看 • 3 天前

Visuals from the ground: Indian military personnel help in trying to provide support in the aftermath of the Ahmedabad plane crash.

Visuals from the ground: Indian military personnel help in trying to provide support in the aftermath of the Ahmedabad plane crash.

Sidhant Sibal

196,565 次观看 • 1 年前

RAI’s Ultra Mobility Vehicle uses AI, sensors, and dynamic motion to stay stable and tackle extreme terrain.

RAI’s Ultra Mobility Vehicle uses AI, sensors, and dynamic motion to stay stable and tackle extreme terrain.

Science girl

12,467 次观看 • 3 个月前

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

RoboPapers

38,334 次观看 • 25 天前

Boston Dynamics Atlas robot recently performed flips and cartwheels after extensive training and testing. Engineers used simulations and repeated practice runs to improve its balance, timing, and coordination. By learning from mistakes and refining its movements, Atlas became stable enough to perform the actions smoothly.

Boston Dynamics Atlas robot recently performed flips and cartwheels after extensive training and testing. Engineers used simulations and repeated practice runs to improve its balance, timing, and coordination. By learning from mistakes and refining its movements, Atlas became stable enough to perform the actions smoothly.

Space and Technology

83,781 次观看 • 27 天前

Footage of a Ukrainian soldier using a Steam Deck to control the weapons system of an unmanned ground vehicle at a firing range.

Footage of a Ukrainian soldier using a Steam Deck to control the weapons system of an unmanned ground vehicle at a firing range.

OSINTtechnical

75,274 次观看 • 5 个月前

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:

DeepLearning.AI

29,369 次观看 • 9 个月前

Course on Matrix Methods in Data Analysis & Signal Processing Machine Learning in Finance represents one of AI's fastest growing applications, leveraging data driven models and algorithms to make financial predictions, manage risks, and automate trading decisions. At the forefront is algorithmic trading (quant trading), where ML models predict price movements and execute high speed trades by learning from historical market data including prices, volume, and news sentiment using sophisticated techniques like reinforcement learning, regression analysis, decision trees, and LSTM neural networks to gain competitive advantages in increasingly complex financial markets

Course on Matrix Methods in Data Analysis & Signal Processing Machine Learning in Finance represents one of AI's fastest growing applications, leveraging data driven models and algorithms to make financial predictions, manage risks, and automate trading decisions. At the forefront is algorithmic trading (quant trading), where ML models predict price movements and execute high speed trades by learning from historical market data including prices, volume, and news sentiment using sophisticated techniques like reinforcement learning, regression analysis, decision trees, and LSTM neural networks to gain competitive advantages in increasingly complex financial markets

D4rsh🦅

82,499 次观看 • 11 个月前

The Chicken Head Camera Stabilizing technology. Millions of years of reinforcement learning optimization…

The Chicken Head Camera Stabilizing technology. Millions of years of reinforcement learning optimization…

Brian Roemmele

45,952 次观看 • 8 个月前

Helix is now learning directly from human video data We have already trained on data collected in the real world, including Brookfield residential units To our knowledge, this is the first instance of a humanoid robot learning navigation end-to-end using only human video

Helix is now learning directly from human video data We have already trained on data collected in the real world, including Brookfield residential units To our knowledge, this is the first instance of a humanoid robot learning navigation end-to-end using only human video

Figure

46,041 次观看 • 9 个月前

NEW: Disney reveals “ReActor,” a new method for Walt Disney Imagineering’s robotic character pipeline. • Combines reinforcement learning with physics-based simulations to transfer human motion to characters • Could be the next milestone for more lifelike robotic characters

NEW: Disney reveals “ReActor,” a new method for Walt Disney Imagineering’s robotic character pipeline. • Combines reinforcement learning with physics-based simulations to transfer human motion to characters • Could be the next milestone for more lifelike robotic characters

Drew Smith

66,818 次观看 • 1 个月前

👋 Wonderful to meet the community of Barking this morning! The King and Queen visited the Barking Learning Centre Community and Family Hub. This community-based learning facility houses Barking Library and brings together a range of council services, and local groups. 💬 Their Majesties spent time with families and staff, who work at the centre to provide advice on employment, support those who are homeless, and encourage reading in the library.

👋 Wonderful to meet the community of Barking this morning! The King and Queen visited the Barking Learning Centre Community and Family Hub. This community-based learning facility houses Barking Library and brings together a range of council services, and local groups. 💬 Their Majesties spent time with families and staff, who work at the centre to provide advice on employment, support those who are homeless, and encourage reading in the library.

The Royal Family

79,305 次观看 • 4 个月前