Загрузка видео...

Не удалось загрузить видео

На главную

The robot is learning several novel tasks instantly, after just ONE demonstration each... Instant Policy makes it possible: no extra training, no weight updates, just pure in-context learning. It just got accepted at ICLR 2025, and it’s changing how robots learn. With just a single demo, a robot can...

IlirAliu_'s profile picture

Ilir Aliu

49,464 subscribers

46,285 просмотров • 1 год назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 6

Фото профиля Mark Ruby
Mark Ruby1 год назад

I'm waiting for the robot to become sentient, then impatient, and slap him.

Фото профиля Luke Liem
Luke Liem1 год назад

This combines imitation learning and graph representation. Apparently a transformer is also involved in the architecture - to learn context?

Фото профиля The Rundown AI
The Rundown AI1 год назад

If you're not learning AI in 2025, you're falling behind. Join 1,000,000+ early adopters reading and learn AI in just 5 minutes a day (for free).

Фото профиля Dayder
Dayder1 год назад

Dum-E from Iron Man is so close😁 Amazing progress.

Фото профиля Jamal Jalal
Jamal Jalal1 год назад

يتعلم ذراع الروبوت من توجيه واحد فقط ولايتأثر بتغير البيئه , اعتقد انهم اقتربوا من صناعة هواتف الموبايل بالروبوتات ,حيث كان الهدف قبل سنوات ان ينفذ الروبوت ما يراه اي يتم تعليمه كما يتعلم البشر من النظر,كان ينبغي على الدول العربيه السير بهذا الطريق وهو مربح للغايه ايضا

Фото профиля Renato Pudo
Renato Pudo1 год назад

🤯

Похожие видео

What if robots could learn real-world tasks from your perspective… without ever touching a robot? This is a system that trains robot policies using nothing but human-first, egocentric video data from smart glasses. No robots, no teleop, no sensors, just humans doing real tasks in the real world. Why it matters ✅ Learns robot policies from 20 minutes of human video; zero robot demos ✅ Generalizes to new objects, views, and even robot morphologies ✅ Uses 3D points for interpretable, spatially grounded learning ✅ Deploys directly to real-world robots with strong zero-shot success Thank you, Vincent Liu, for sharing!!! Learn more here: 🔗 Paper: 🌐 Website: 📍 BOOKMARK FOR LATER
0:30

What if robots could learn real-world tasks from your perspective… without ever touching a robot? This is a system that trains robot policies using nothing but human-first, egocentric video data from smart glasses. No robots, no teleop, no sensors, just humans doing real tasks in the real world. Why it matters ✅ Learns robot policies from 20 minutes of human video; zero robot demos ✅ Generalizes to new objects, views, and even robot morphologies ✅ Uses 3D points for interpretable, spatially grounded learning ✅ Deploys directly to real-world robots with strong zero-shot success Thank you, Vincent Liu, for sharing!!! Learn more here: 🔗 Paper: 🌐 Website: 📍 BOOKMARK FOR LATER

Ilir Aliu - eu/acc

10,509 просмотров • 1 год назад

The $10k robot arms that can learn from a handful of demos: Most robots still lose the cost equation. They’re slow, expensive, and take months to deploy, which means… they only make sense for huge factories. The The Robot Learning Company (YC X25) is building affordable, general-purpose robot arms that can pick up new tasks from just a few human demonstrations. Why it matters: ✅ Under $10k per pair of stationary arms ✅ Adapts to new tasks with imitation + reinforcement learning ✅ Deployable in days, not months From small manufacturers to service providers, this makes robotic labor accessible to companies that could never justify it before. Saying hi to founder Jannik Grothusen 👋 More here:
0:39

The $10k robot arms that can learn from a handful of demos: Most robots still lose the cost equation. They’re slow, expensive, and take months to deploy, which means… they only make sense for huge factories. The The Robot Learning Company (YC X25) is building affordable, general-purpose robot arms that can pick up new tasks from just a few human demonstrations. Why it matters: ✅ Under $10k per pair of stationary arms ✅ Adapts to new tasks with imitation + reinforcement learning ✅ Deployable in days, not months From small manufacturers to service providers, this makes robotic labor accessible to companies that could never justify it before. Saying hi to founder Jannik Grothusen 👋 More here:

Ilir Aliu - eu/acc

36,336 просмотров • 11 месяцев назад

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:
1:03

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Kaustubh Sridhar

52,158 просмотров • 11 месяцев назад

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:
0:29

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

42,804 просмотров • 5 месяцев назад

How precise can a robot get… without ever seeing the object move? Turns out, just a geometric model is enough. A robot hit 73 precise 3D goals in a row, using only a geometric model. No demonstrations. No imitation learning. No fancy vision models. The secret? Sample where the robot could make contact. Let local contact-implicit control take over from there. That’s it. ✅ Real-time performance ✅ Natural contact making and breaking ✅ Works on tricky tasks like pushing and rotating This approach mixes global planning with local MPC. Fast. Accurate. Sample-efficient. Thanks for sharing, Michael Posa ! 📍Watch it in action: Paper:
0:46

How precise can a robot get… without ever seeing the object move? Turns out, just a geometric model is enough. A robot hit 73 precise 3D goals in a row, using only a geometric model. No demonstrations. No imitation learning. No fancy vision models. The secret? Sample where the robot could make contact. Let local contact-implicit control take over from there. That’s it. ✅ Real-time performance ✅ Natural contact making and breaking ✅ Works on tricky tasks like pushing and rotating This approach mixes global planning with local MPC. Fast. Accurate. Sample-efficient. Thanks for sharing, Michael Posa ! 📍Watch it in action: Paper:

Ilir Aliu

19,012 просмотров • 1 год назад

🚀 We just shipped a big upgrade to our imitation-learning-in-simulation playground in LeRobot, built together with Lightwheel ! You can now teleoperate robots in sim (keyboard or real robot) and collect training demos instantly. This makes it possible to run real IL research on harder, more realistic manipulation tasks, even if you don’t have hardware. New tasks: 🟠 pick orange to the plate 🧺 fold cloth (yes!) 📦 pick 2 “e” toys to the box 🔴 lift red cube Through our partnership with Lightwheel, LeIsaac was integrated into EnvHub on day one, a best-practice integration that strengthens both ecosystems and pushes simulation-first robotics forward. 👉 Load a task via EnvHub, start teleop-ing, record your demo, upload the data on the hub and you’re ready to train or test.
0:22

🚀 We just shipped a big upgrade to our imitation-learning-in-simulation playground in LeRobot, built together with Lightwheel ! You can now teleoperate robots in sim (keyboard or real robot) and collect training demos instantly. This makes it possible to run real IL research on harder, more realistic manipulation tasks, even if you don’t have hardware. New tasks: 🟠 pick orange to the plate 🧺 fold cloth (yes!) 📦 pick 2 “e” toys to the box 🔴 lift red cube Through our partnership with Lightwheel, LeIsaac was integrated into EnvHub on day one, a best-practice integration that strengthens both ecosystems and pushes simulation-first robotics forward. 👉 Load a task via EnvHub, start teleop-ing, record your demo, upload the data on the hub and you’re ready to train or test.

LeRobot

44,647 просмотров • 7 месяцев назад

A new robot policy just cleaned up a kitchen it had never seen before [watch what happens. paper included ⬇️] Pi-0.5 builds on top of Pi-0 and shows how smart co-training with diverse data can unlock real generalization in the home. It doesn’t just learn from one setup but adapts to many, including homes it’s never seen. What it does ✅ Handles new homes without training in them ✅ Follows complex language instructions ✅ Cleans, places dishes, handles spills ✅ Matches in-home training models using cross-embodiment and web data Robots that understand tasks and adapt to new spaces are finally within reach. More in the blog: Read the paper ⬇️ Physical Intelligence, co-founded by UC Berkeley professor Sergey Levine, is a robotics startup developing general-purpose AI foundation models that enable robots to perform a wide variety of real-world tasks with human-like adaptability, recently raising $400 million to advance this vision.
1:22

A new robot policy just cleaned up a kitchen it had never seen before [watch what happens. paper included ⬇️] Pi-0.5 builds on top of Pi-0 and shows how smart co-training with diverse data can unlock real generalization in the home. It doesn’t just learn from one setup but adapts to many, including homes it’s never seen. What it does ✅ Handles new homes without training in them ✅ Follows complex language instructions ✅ Cleans, places dishes, handles spills ✅ Matches in-home training models using cross-embodiment and web data Robots that understand tasks and adapt to new spaces are finally within reach. More in the blog: Read the paper ⬇️ Physical Intelligence, co-founded by UC Berkeley professor Sergey Levine, is a robotics startup developing general-purpose AI foundation models that enable robots to perform a wide variety of real-world tasks with human-like adaptability, recently raising $400 million to advance this vision.

Ilir Aliu - eu/acc

18,120 просмотров • 1 год назад

🚨🇺🇸FIGURE ROBOT LEARNS TO WALK IN HOURS Turns out you can teach a robot to walk—if you’ve got a few years to burn in a physics simulator (or a few hours of GPU time). Figure’s team trained a neural network using reinforcement learning to mimic natural human locomotion, and the wild part is it worked on the first try with real hardware. No tuning. No fiddling. Just plug and strut. Thanks to sim-to-real transfer and some sneaky domain randomization, the robot didn’t just wobble out of the lab—it walked like it had somewhere to be. Next up: running. Not terrifying at all. Source: Figure
0:54

🚨🇺🇸FIGURE ROBOT LEARNS TO WALK IN HOURS Turns out you can teach a robot to walk—if you’ve got a few years to burn in a physics simulator (or a few hours of GPU time). Figure’s team trained a neural network using reinforcement learning to mimic natural human locomotion, and the wild part is it worked on the first try with real hardware. No tuning. No fiddling. Just plug and strut. Thanks to sim-to-real transfer and some sneaky domain randomization, the robot didn’t just wobble out of the lab—it walked like it had somewhere to be. Next up: running. Not terrifying at all. Source: Figure

Mario Nawfal

117,866 просмотров • 1 год назад

Force is arguably the most overlooked ingredient in modern robot learning. Introducing FACTR 2: it turns *any* commodity robot into a force-aware system with no force sensors required. Train a tiny force network in <1min with <10mins of data and drop it into any existing teleop pipelines: ✅ Free force sensing for both the robot and the operator arm ✅ Makes demos higher-quality → fewer of them needed. ✅ A new force-aware learning algorithm (FIRST) uses those recovered forces to figure out which parts of a demo actually matter, making learning data-efficient. ✅ Strong performance on complex tasks with fewer demos and even no pretraining! More details below.
0:40

Force is arguably the most overlooked ingredient in modern robot learning. Introducing FACTR 2: it turns *any* commodity robot into a force-aware system with no force sensors required. Train a tiny force network in <1min with <10mins of data and drop it into any existing teleop pipelines: ✅ Free force sensing for both the robot and the operator arm ✅ Makes demos higher-quality → fewer of them needed. ✅ A new force-aware learning algorithm (FIRST) uses those recovered forces to figure out which parts of a demo actually matter, making learning data-efficient. ✅ Strong performance on complex tasks with fewer demos and even no pretraining! More details below.

Deepak Pathak

38,418 просмотров • 1 месяц назад

2. NVIDIA is building the GPT of humanoid robots. They just launched Isaac GR00T N1.5 - a foundation model for general purpose robotics. Here’s how it works: → A human demos the task once → Cosmos (their physics AI model) generates 1,000s of variations → Omniverse simulates the motions in high fidelity → The robot trains entirely in simulation → Then fine-tunes itself in the real world Robots can now learn general skills across tasks, tools, even body types with just one human demo. AI isn’t just thinking in text anymore. It’s perceiving. Reasoning. Moving. Physical AI is here and it’s training itself.
2:21

2. NVIDIA is building the GPT of humanoid robots. They just launched Isaac GR00T N1.5 - a foundation model for general purpose robotics. Here’s how it works: → A human demos the task once → Cosmos (their physics AI model) generates 1,000s of variations → Omniverse simulates the motions in high fidelity → The robot trains entirely in simulation → Then fine-tunes itself in the real world Robots can now learn general skills across tasks, tools, even body types with just one human demo. AI isn’t just thinking in text anymore. It’s perceiving. Reasoning. Moving. Physical AI is here and it’s training itself.

Shruti

70,359 просмотров • 1 год назад

A robot that works with 1 to 6 legs? This reconfigurable robot adapts like a spider, switching between different movement styles on the fly. SnapBot isn’t just a legged robot: it’s a shape-shifting machine. With up to 700 configurations, it can walk, crawl, or row its way through any terrain. Why this is exciting: ✅ Changes its setup from one to six legs for different tasks ✅ Moves in multiple ways, including walking, rowing, and crawling ✅ Adapts to its environment like nature’s best climbers and crawlers ✅ A step toward robots that adjust to real-world challenges instantly Nature-inspired robotics is unlocking new ways to move. SnapBot proves that flexibility is key to the future of locomotion.
0:25

A robot that works with 1 to 6 legs? This reconfigurable robot adapts like a spider, switching between different movement styles on the fly. SnapBot isn’t just a legged robot: it’s a shape-shifting machine. With up to 700 configurations, it can walk, crawl, or row its way through any terrain. Why this is exciting: ✅ Changes its setup from one to six legs for different tasks ✅ Moves in multiple ways, including walking, rowing, and crawling ✅ Adapts to its environment like nature’s best climbers and crawlers ✅ A step toward robots that adjust to real-world challenges instantly Nature-inspired robotics is unlocking new ways to move. SnapBot proves that flexibility is key to the future of locomotion.

Ilir Aliu

78,006 просмотров • 1 год назад

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!
1:11:51

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 просмотров • 6 месяцев назад

Excited to finally share Generative Value Learning (GVL), my Google DeepMind project on extracting universal value functions from long-context VLMs via in-context learning! We discovered a simple method to generate zero-shot and few-shot values for 300+ robot tasks and 50+ datasets using SOTA VLMs like Gemini (Try out the demo on our website on your robot video today!) I worked a lot on leveraging foundation models as guidance for robots in my PhD, and to me, this result forges a new frontier in how we can use foundation models for robot learning, given its broad applicability independent of embodiment and task types. Quite excited about how we can build on this work as a community!
0:32

Excited to finally share Generative Value Learning (GVL), my Google DeepMind project on extracting universal value functions from long-context VLMs via in-context learning! We discovered a simple method to generate zero-shot and few-shot values for 300+ robot tasks and 50+ datasets using SOTA VLMs like Gemini (Try out the demo on our website on your robot video today!) I worked a lot on leveraging foundation models as guidance for robots in my PhD, and to me, this result forges a new frontier in how we can use foundation models for robot learning, given its broad applicability independent of embodiment and task types. Quite excited about how we can build on this work as a community!

Jason Ma

98,090 просмотров • 1 год назад

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.
1:05

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Khurram Javed

52,110 просмотров • 7 месяцев назад

GitHub Copilot coding agent just got a major upgrade. ✨ What's new: • It tests its own UI changes with Playwright and adds screenshots to PRs. • It can connect to more context and tools with remote MCP support. • You can trigger and track tasks from a new dashboard. • It only uses one Copilot premium request per session. Plus, it's now available for Copilot Pro and Business users. ✅ Here are all the updates in action. ▶️
1:52

GitHub Copilot coding agent just got a major upgrade. ✨ What's new: • It tests its own UI changes with Playwright and adds screenshots to PRs. • It can connect to more context and tools with remote MCP support. • You can trigger and track tasks from a new dashboard. • It only uses one Copilot premium request per session. Plus, it's now available for Copilot Pro and Business users. ✅ Here are all the updates in action. ▶️

GitHub

126,899 просмотров • 1 год назад

Legged Locomotion… meets Skateboarding [Paper ⬇️] Most robot movement models either rely on fixed patterns or struggle to handle complex changes. DHAL (Discrete-time Hybrid Automata Learning) takes a different approach: using reinforcement learning to teach robots when and how to switch movements in real-time: ✅ Learns when to switch between different motions without pre-labeled data ✅ Handles complex, high-dimensional movements like a quadrupedal robot on a skateboard ✅ Uses a multi-critic architecture to improve contact-based motion control ✅ Works in both simulation and real-world environments with strong results It proves that robots can learn movement transitions on their own, without predefined rules. Paper: Thanks to Hang Liu for bringing this to my attention!
0:22

Legged Locomotion… meets Skateboarding [Paper ⬇️] Most robot movement models either rely on fixed patterns or struggle to handle complex changes. DHAL (Discrete-time Hybrid Automata Learning) takes a different approach: using reinforcement learning to teach robots when and how to switch movements in real-time: ✅ Learns when to switch between different motions without pre-labeled data ✅ Handles complex, high-dimensional movements like a quadrupedal robot on a skateboard ✅ Uses a multi-critic architecture to improve contact-based motion control ✅ Works in both simulation and real-world environments with strong results It proves that robots can learn movement transitions on their own, without predefined rules. Paper: Thanks to Hang Liu for bringing this to my attention!

Ilir Aliu - eu/acc

41,894 просмотров • 1 год назад

Quadrupeds are fast. Agile. Great at locomotion. But can they manipulate? A new approach from Carnegie Mellon University, Google DeepMind, and Bosch is teaching quadrupedal robots to do more than walk, they’re learning to interact. It’s called Human2LocoMan: a system that uses human data to pretrain robot policies before finetuning on real hardware. The result? A four-legged robot that can walk, carry, organize, scoop, and sort with both single and dual-arm control. By pretraining on human motion, they cut the amount of robot data in half—while improving success rates by over 80% in unfamiliar environments. Their Modularized Cross-Embodiment Transformer (MXT) learns from both human and robot demonstrations, then generalizes those skills to physical tasks—no hardcoded behaviors required. It’s locomotion and manipulation. A quadruped that can walk and clean up after itself?
1:21

Quadrupeds are fast. Agile. Great at locomotion. But can they manipulate? A new approach from Carnegie Mellon University, Google DeepMind, and Bosch is teaching quadrupedal robots to do more than walk, they’re learning to interact. It’s called Human2LocoMan: a system that uses human data to pretrain robot policies before finetuning on real hardware. The result? A four-legged robot that can walk, carry, organize, scoop, and sort with both single and dual-arm control. By pretraining on human motion, they cut the amount of robot data in half—while improving success rates by over 80% in unfamiliar environments. Their Modularized Cross-Embodiment Transformer (MXT) learns from both human and robot demonstrations, then generalizes those skills to physical tasks—no hardcoded behaviors required. It’s locomotion and manipulation. A quadruped that can walk and clean up after itself?

Lukas Ziegler

60,546 просмотров • 1 год назад