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。

Everyone is scaling VLAs with more robot data. TiPToP shows another path. No robot training, no policy learning. Just RGB + language → 3D scene → GPU TAMP planner → trajectory. Foundation models + planning alone can run real manipulation tasks.

Robots Digest 🤖

5,055 subscribers

10,362 次观看 • 4 个月前 •via X (Twitter)

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

State-of-the-art robot policies often need hundreds of hours of data. What if we needed none? Introducing TiPToP: a manipulation system that zero-shots open-world tasks from pixels and language using vision foundation models and GPU-parallelized Task and Motion Planning (TAMP).

State-of-the-art robot policies often need hundreds of hours of data. What if we needed none? Introducing TiPToP: a manipulation system that zero-shots open-world tasks from pixels and language using vision foundation models and GPU-parallelized Task and Motion Planning (TAMP).

Nishanth Kumar

78,298 次观看 • 4 个月前

So I heard we need more data for robot learning :) Purely real world teleop is expensive and slow, making large scale data collection challenging. I’ve been excited about getting more data into robot learning, going beyond just real-world teleop data. To this end, we’ve been scaling up data generation with RL in realistic simulations generated on the fly from crowdsourced videos. Enables realistic data collection, much more cheaply than purely real world teleop. Importantly, data collection becomes even*cheaper* with more environments, allowing training with over 100x more data. Transfers to real robots for generalizable manipulation. A 🧵 (1/N)

So I heard we need more data for robot learning :) Purely real world teleop is expensive and slow, making large scale data collection challenging. I’ve been excited about getting more data into robot learning, going beyond just real-world teleop data. To this end, we’ve been scaling up data generation with RL in realistic simulations generated on the fly from crowdsourced videos. Enables realistic data collection, much more cheaply than purely real world teleop. Importantly, data collection becomes evencheaper with more environments, allowing training with over 100x more data. Transfers to real robots for generalizable manipulation. A 🧵 (1/N)

Abhishek Gupta

13,350 次观看 • 1 年前

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

42,804 次观看 • 5 个月前

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 pick up a new task and start performing it right away. Why this is a big deal: ✅ Learns tasks instantly with just one or a few demonstrations ✅ Improves over time as more demonstrations are given ✅ Uses simulation-based training with “pseudo-demonstrations” for scalability ✅ Can transfer skills across different robots and even follow language-defined tasks It brings in-context learning to robotics, opening up new possibilities for flexible, real-world automation. You can try it yourself: code and weights are available at • • • • Thank you to Edward Johns, Director of the Robot Learning Lab at Imperial College for sharing their work! 🙏

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 pick up a new task and start performing it right away. Why this is a big deal: ✅ Learns tasks instantly with just one or a few demonstrations ✅ Improves over time as more demonstrations are given ✅ Uses simulation-based training with “pseudo-demonstrations” for scalability ✅ Can transfer skills across different robots and even follow language-defined tasks It brings in-context learning to robotics, opening up new possibilities for flexible, real-world automation. You can try it yourself: code and weights are available at • • • • Thank you to Edward Johns, Director of the Robot Learning Lab at Imperial College for sharing their work! 🙏

Ilir Aliu

46,285 次观看 • 1 年前

A big part of scaling robot learning to solve real-world problems is that we somehow need to get enough diverse, high-quality data to train our robots to perform useful things. GPT and its fellow large language models were bootstrapped and proved out on a massive dataset of real-world language data. Unfortunately, despite our best efforts, similarly massive datasets don’t really exist for robotics — so, in our unending pursuit of high-quality, useful data, we turn to simulation. I compared a couple recent works on sim-to-real robot manipulation, which discuss how to train perception-driven manipulation policies in simulation, in such a way that they’re useful in the real world. - DextraH-RGB, from NVIDIA - Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation, also from NVIDIA — specifically the GEAR lab - Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids, another GEAR lab paper - Local Policies Enable Zero-shot Long-Horizon Manipulation, from CMU (video from DextrAH-RGB)

A big part of scaling robot learning to solve real-world problems is that we somehow need to get enough diverse, high-quality data to train our robots to perform useful things. GPT and its fellow large language models were bootstrapped and proved out on a massive dataset of real-world language data. Unfortunately, despite our best efforts, similarly massive datasets don’t really exist for robotics — so, in our unending pursuit of high-quality, useful data, we turn to simulation. I compared a couple recent works on sim-to-real robot manipulation, which discuss how to train perception-driven manipulation policies in simulation, in such a way that they’re useful in the real world. - DextraH-RGB, from NVIDIA - Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation, also from NVIDIA — specifically the GEAR lab - Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids, another GEAR lab paper - Local Policies Enable Zero-shot Long-Horizon Manipulation, from CMU (video from DextrAH-RGB)

Chris Paxton

20,486 次观看 • 1 年前

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

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 次观看 • 1 年前

Training robot foundation models faces two key hurdles: how to get enough data to train an effective model, and how to make sure that new skills can be acquired quickly. The team at Rhoda AI believes that the answer is training Direct Video Action models from web data. Web data is plentiful, to the point where Rhoda can train their base model on hundreds of years of video data. And then, with the addition of robot data, they can quickly adapt it to new tasks with as little as 20 hours of in-domain data, performing complex, multi-step manipulation tasks with their purpose-built video foundation model. Tongzhou Mu 🤖🦾🦿 Eric Chan and Changan Chen joined us to talk more about their approach. Watch Episode #79 of RoboPapers, with Michael Cho - Rbt/Acc, Chris Paxton, and Jiafei Duan, to learn more!

Training robot foundation models faces two key hurdles: how to get enough data to train an effective model, and how to make sure that new skills can be acquired quickly. The team at Rhoda AI believes that the answer is training Direct Video Action models from web data. Web data is plentiful, to the point where Rhoda can train their base model on hundreds of years of video data. And then, with the addition of robot data, they can quickly adapt it to new tasks with as little as 20 hours of in-domain data, performing complex, multi-step manipulation tasks with their purpose-built video foundation model. Tongzhou Mu 🤖🦾🦿 Eric Chan and Changan Chen joined us to talk more about their approach. Watch Episode #79 of RoboPapers, with Michael Cho - Rbt/Acc, Chris Paxton, and Jiafei Duan, to learn more!

RoboPapers

24,475 次观看 • 2 个月前

This is a demonstration video of in-hand object rotation with new Torobo Hand. By leveraging large-scale parallel reinforcement learning in NVIDIA Isaac Sim, the learned policy can perform object manipulation in MuJoCo and on the real robot without any additional training.

This is a demonstration video of in-hand object rotation with new Torobo Hand. By leveraging large-scale parallel reinforcement learning in NVIDIA Isaac Sim, the learned policy can perform object manipulation in MuJoCo and on the real robot without any additional training.

東京ロボティクス株式会社

10,860 次观看 • 1 年前

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:

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 次观看 • 1 年前

Egocentric Videos for Robot Training 🧵 Researchers at NYU and UC Berkeley published research where they developed a system called EgoZero that trains robots using human demonstration videos recorded with smart glasses. 👓 The system converts first-person human actions into 3D point-based state-action representations. The policies executed on a gripper-equipped robot, achieved a 70% zero-shot success rate across seven manipulation tasks, with only 20 minutes of human data per task. EgoZero stands as one of the solid empirical proofs that egocentric smart-glass video collected from everyday human behavior can serve as powerful, scalable training data for real robot learning. Vincent Liu Ademi Adeniji

Egocentric Videos for Robot Training 🧵 Researchers at NYU and UC Berkeley published research where they developed a system called EgoZero that trains robots using human demonstration videos recorded with smart glasses. 👓 The system converts first-person human actions into 3D point-based state-action representations. The policies executed on a gripper-equipped robot, achieved a 70% zero-shot success rate across seven manipulation tasks, with only 20 minutes of human data per task. EgoZero stands as one of the solid empirical proofs that egocentric smart-glass video collected from everyday human behavior can serve as powerful, scalable training data for real robot learning. Vincent Liu Ademi Adeniji

VaderResearch

23,055 次观看 • 10 个月前

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

13,456 次观看 • 5 个月前

No wonder they say teleoperation is dead Peking University’s DAGroup released HumanNet, a massive 1 million hour dataset of human-centric videos that turns everyday internet footage into gold for embodied AI. It’s got first-person and third-person views, super detailed actions, object interactions, tool use, and long sequences of real behavior. Everything’s cleaned up and annotated with 3D poses, SLAM tracks, and robot-ready labels. The crazy part is,Training on just 1,000 hours of their first-person videos performs as well as (or even slightly better than) 100 hours of actual robot teleop data on downstream tasks. Basically, human videos can now stand in for expensive robot data. Scaling laws for robotics just got a whole lot more realistic. Human priors + smart curation = the future of world models.

No wonder they say teleoperation is dead Peking University’s DAGroup released HumanNet, a massive 1 million hour dataset of human-centric videos that turns everyday internet footage into gold for embodied AI. It’s got first-person and third-person views, super detailed actions, object interactions, tool use, and long sequences of real behavior. Everything’s cleaned up and annotated with 3D poses, SLAM tracks, and robot-ready labels. The crazy part is,Training on just 1,000 hours of their first-person videos performs as well as (or even slightly better than) 100 hours of actual robot teleop data on downstream tasks. Basically, human videos can now stand in for expensive robot data. Scaling laws for robotics just got a whole lot more realistic. Human priors + smart curation = the future of world models.

CyberRobo

27,048 次观看 • 2 个月前

💥 Think more real data is needed for scene reconstruction? Think again! Meet MegaSynth: scaling up feed-forward 3D scene reconstruction with synthesized scenes. In 3 days, it generates 700K scenes for training—70x larger than real data! ✨ The secret? Reconstruction is mostly non-semantic! No need to rely heavily on real or highly realistic synthetic data. 🌐 Project: (1/4)

💥 Think more real data is needed for scene reconstruction? Think again! Meet MegaSynth: scaling up feed-forward 3D scene reconstruction with synthesized scenes. In 3 days, it generates 700K scenes for training—70x larger than real data! ✨ The secret? Reconstruction is mostly non-semantic! No need to rely heavily on real or highly realistic synthetic data. 🌐 Project: (1/4)

Hanwen Jiang

26,969 次观看 • 1 年前

🧐Applying world models to improve real-world policy on challenging manipulation tasks used to be considered out of reach. 😌After sustained effort, we’re now seeing encouraging progress. 🚀Thrilled to introduce RISE: Self-Improving Robot Policy with Compositional World Model RISE is, to our knowledge, the first work to use a world model as an effective learning environment for challenging real-world manipulation, enabling policy improvement on tasks that demand high dynamics, dexterity, and precision. Incredible teamwork with Kunyang Lin Hongyang Li Yue Xiangyu Hao Zhao Chonghao Sima

🧐Applying world models to improve real-world policy on challenging manipulation tasks used to be considered out of reach. 😌After sustained effort, we’re now seeing encouraging progress. 🚀Thrilled to introduce RISE: Self-Improving Robot Policy with Compositional World Model RISE is, to our knowledge, the first work to use a world model as an effective learning environment for challenging real-world manipulation, enabling policy improvement on tasks that demand high dynamics, dexterity, and precision. Incredible teamwork with Kunyang Lin Hongyang Li Yue Xiangyu Hao Zhao Chonghao Sima

Jiazhi Yang ✈️ RSS2026

76,440 次观看 • 5 个月前

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:

Ilir Aliu

18,210 次观看 • 5 个月前

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.

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 次观看 • 1 年前

We asked Angus about the future of robotics and AI training. “I built an industrial-grade kinematic solver for 6 degrees of freedom motion, with full path planning and joint control." "You can stream AI model outputs into it, or run it like a traditional industrial robot." "The benefit of that is all of that information you can stream and record from those joints… you can use that as the training data." "Frankly, moving a robot with a lever is really crap data for training robots. But this gives you smooth, high-quality motion, without needing two robots.”

We asked Angus about the future of robotics and AI training. “I built an industrial-grade kinematic solver for 6 degrees of freedom motion, with full path planning and joint control." "You can stream AI model outputs into it, or run it like a traditional industrial robot." "The benefit of that is all of that information you can stream and record from those joints… you can use that as the training data." "Frankly, moving a robot with a lever is really crap data for training robots. But this gives you smooth, high-quality motion, without needing two robots.”

TBPN

18,811 次观看 • 1 年前

We might be solving the wrong problem in robotics. That’s what this makes clear. UMI → Universal Manipulation Interface A simple $400 gripper that lets you teach robots by demonstration. You hold it like a tool. Show the task. The robot learns. No teleoperation. No expensive hardware. No robot-specific data. Stanford open-sourced everything → hardware, code, datasets. What stands out to me is the bottleneck. Not algorithms. Data. Teleoperation → ~35 demos/hour UMI → ~111 demos/hour And the data transfers across robots → UR5, Franka, others. The design is surprisingly practical: → GoPro fisheye lens (155° FOV) + mirrors for depth → SLAM + IMU for precise 6DoF tracking → latency matching for dynamic tasks → diffusion policies for multimodal actions Then it scales. Cheng Chi takes this further with Sunday Robotics (with Tony Zhao). A $200 glove → deployed in 500+ homes → ~10 million real-world interactions. Not lab data. Real human behavior. Their robot learns dishes, laundry, espresso → with zero robot-specific data. This is where the shift becomes obvious. From training robots in controlled environments → to learning directly from humans at scale So here’s the real question: Will robotics be unlocked by better models… or by unlocking data? #ArtificialIntelligence #Robotics #AI #Innovation #FutureOfWork

We might be solving the wrong problem in robotics. That’s what this makes clear. UMI → Universal Manipulation Interface A simple $400 gripper that lets you teach robots by demonstration. You hold it like a tool. Show the task. The robot learns. No teleoperation. No expensive hardware. No robot-specific data. Stanford open-sourced everything → hardware, code, datasets. What stands out to me is the bottleneck. Not algorithms. Data. Teleoperation → ~35 demos/hour UMI → ~111 demos/hour And the data transfers across robots → UR5, Franka, others. The design is surprisingly practical: → GoPro fisheye lens (155° FOV) + mirrors for depth → SLAM + IMU for precise 6DoF tracking → latency matching for dynamic tasks → diffusion policies for multimodal actions Then it scales. Cheng Chi takes this further with Sunday Robotics (with Tony Zhao). A $200 glove → deployed in 500+ homes → ~10 million real-world interactions. Not lab data. Real human behavior. Their robot learns dishes, laundry, espresso → with zero robot-specific data. This is where the shift becomes obvious. From training robots in controlled environments → to learning directly from humans at scale So here’s the real question: Will robotics be unlocked by better models… or by unlocking data? #ArtificialIntelligence #Robotics #AI #Innovation #FutureOfWork

Pascal Bornet

186,223 次观看 • 3 个月前

Can vision-language-action (VLA) models generalize to diverse OOD tasks and align with customized objectives? 🤔 🚀 We introduce GRAPE, a plug-and-play algorithm to generalize robot policies via preference alignment. GRAPE unfolds three benefits to boost the generalizability of VLAs: 👉1. GRAPE aligns VLAs on a trajectory level and endows the model with the ability for global decision-making, instead of merely cloning behavior; 👉2. GRAPE implicitly models reward from both successful and failed trials to boost generalizability to diverse tasks; 👉3. GRAPE adopts a scalable preference synthesis algorithm to rank trajectories with preferences that align with arbitrary objectives. Our experiments on a diverse array of real-world and simulated robotic tasks reveal: 1⃣GRAPE enhances the performance of state-of-the-art VLA models, increasing success rates on in-domain and unseen manipulation tasks by 51.79% and 60.36%; 2⃣GRAPE is versatile to be aligned with diverse objectives and reduce collision rates by 44.31% or rollout length by 11.15% when aligning towards safer or more efficient manipulation policy, respectively. Check out our full project for more details: 🔥 Paper: 🔥 Project: 🔥 Code:

Can vision-language-action (VLA) models generalize to diverse OOD tasks and align with customized objectives? 🤔 🚀 We introduce GRAPE, a plug-and-play algorithm to generalize robot policies via preference alignment. GRAPE unfolds three benefits to boost the generalizability of VLAs: 👉1. GRAPE aligns VLAs on a trajectory level and endows the model with the ability for global decision-making, instead of merely cloning behavior; 👉2. GRAPE implicitly models reward from both successful and failed trials to boost generalizability to diverse tasks; 👉3. GRAPE adopts a scalable preference synthesis algorithm to rank trajectories with preferences that align with arbitrary objectives. Our experiments on a diverse array of real-world and simulated robotic tasks reveal: 1⃣GRAPE enhances the performance of state-of-the-art VLA models, increasing success rates on in-domain and unseen manipulation tasks by 51.79% and 60.36%; 2⃣GRAPE is versatile to be aligned with diverse objectives and reduce collision rates by 44.31% or rollout length by 11.15% when aligning towards safer or more efficient manipulation policy, respectively. Check out our full project for more details: 🔥 Paper: 🔥 Project: 🔥 Code:

Huaxiu Yao

19,988 次观看 • 1 年前