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 policies via imitation is extremely potent, but making sure those policies will generalize to out of distribution settings is still very hard. SAILOR proposes a solution in learning to search via a learned world model, which outperforms existing imitation approaches. Gokul Swamy, Arnav Jain , and Vibhakar Mohta... show more

RoboPapers

6,496 subscribers

21,507 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

7 Comments

Chris Paxton1 year ago

For links and more + email updates you can check out the substack post for this episode:

Ipsita Praharaj2 months ago

Pretty cool!!

Saksham Jindal1 year ago

@arnavkj95 came a looooong way. Great work!

Chetan1 year ago

I really liked this paper!

VinayK2 months ago

Thanks for sharing

Yash Butala2 months ago

Wow!

Vaibhav Maheshwari2 months ago

Brilliant stuff

Related Videos

Full episode dropping soon! Geeking out with Gokul Swamy Arnav Jain Vibhakar Mohta on 𝚂𝙰𝙸𝙻𝙾𝚁: Robust Imitation via Learning to Search Co-hosted by Michael Cho - Rbt/Acc Chris Paxton

Full episode dropping soon! Geeking out with Gokul Swamy Arnav Jain Vibhakar Mohta on 𝚂𝙰𝙸𝙻𝙾𝚁: Robust Imitation via Learning to Search Co-hosted by Michael Cho - Rbt/Acc Chris Paxton

RoboPapers

10,458 views • 1 year ago

Full episode dropping soon! Geeking out with Nishanth Kumar on From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models Co-hosted by Michael Cho - Rbt/Acc Chris Paxton

Full episode dropping soon! Geeking out with Nishanth Kumar on From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models Co-hosted by Michael Cho - Rbt/Acc Chris Paxton

RoboPapers

12,621 views • 10 months ago

Full episode dropping soon! Geeking out with Daniel Ho on 1X World Model Co-hosted by Michael Cho - Rbt/Acc Chris Paxton

Full episode dropping soon! Geeking out with Daniel Ho on 1X World Model Co-hosted by Michael Cho - Rbt/Acc Chris Paxton

RoboPapers

13,782 views • 8 months ago

Full episode dropping soon! Geeking out with Vincent Liu Ademi Adeniji on EgoZero: Robot Learning from Smart Glasses Co-hosted by Chris Paxton Michael Cho - Rbt/Acc

Full episode dropping soon! Geeking out with Vincent Liu Ademi Adeniji on EgoZero: Robot Learning from Smart Glasses Co-hosted by Chris Paxton Michael Cho - Rbt/Acc

RoboPapers

10,984 views • 1 year ago

Evaluating robot policies is hard. Every lab has a different robot; reproducible evaluations are really challenging. This makes it hard for us to know which methods for learning robot policies are likely to perform the best in real-world scenarios. Taking a page from LLM evaluations like Chatbot Arena, RoboArena aims to address this problem through crowdsourcing evaluations with a network of different evaluators. Watch Episode #34 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton , now to learn more from authors Pranav Atreya and Karl Pertsch!

Evaluating robot policies is hard. Every lab has a different robot; reproducible evaluations are really challenging. This makes it hard for us to know which methods for learning robot policies are likely to perform the best in real-world scenarios. Taking a page from LLM evaluations like Chatbot Arena, RoboArena aims to address this problem through crowdsourcing evaluations with a network of different evaluators. Watch Episode #34 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton , now to learn more from authors Pranav Atreya and Karl Pertsch!

RoboPapers

15,056 views • 1 year ago

Most robot policies today still largely lack memory: they make all their decisions based on what they can see right now. MemER aims to change that by learning which frames are important; this lets it deal with tasks like object search. Ajay Sridhar, Jenny Pan, and @satviks107Sharma tell us about how to achieve this fundamental capability for long-horizon task execution. Watch Episode #54 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton to learn more!

Most robot policies today still largely lack memory: they make all their decisions based on what they can see right now. MemER aims to change that by learning which frames are important; this lets it deal with tasks like object search. Ajay Sridhar, Jenny Pan, and @satviks107Sharma tell us about how to achieve this fundamental capability for long-horizon task execution. Watch Episode #54 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton to learn more!

RoboPapers

17,875 views • 9 months ago

Reasoning over long horizons would allow robots to generalize better to unseen environments and settings zero-shot. One mechanism for this kind of reasoning would be world models, but traditional video world models still tend to struggle with long horizons, and are very data intensive to train. But what if instead of predicting images about the future, we predicted just the symbolic information necessary for reasoning? Nishanth Kumar tells us about Pixels to Predicates, a method for symbol grounding which allows a VLM to plan sequences of robot skills to achieve unseen goals in previously unseen settings. To find out more, watch episode #44 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton now!

Reasoning over long horizons would allow robots to generalize better to unseen environments and settings zero-shot. One mechanism for this kind of reasoning would be world models, but traditional video world models still tend to struggle with long horizons, and are very data intensive to train. But what if instead of predicting images about the future, we predicted just the symbolic information necessary for reasoning? Nishanth Kumar tells us about Pixels to Predicates, a method for symbol grounding which allows a VLM to plan sequences of robot skills to achieve unseen goals in previously unseen settings. To find out more, watch episode #44 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton now!

RoboPapers

19,749 views • 10 months 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

27,945 views • 7 months ago

Collecting dexterous humanoid robot data is difficult to scale. That's why Mengda Xu and Han Zhang built DexUMI: a tool for demonstrating how to control a dexterous robot hand, which allows you to quickly collect task data. Co-hosted by Michael Cho - Rbt/Acc and Chris Paxton

Collecting dexterous humanoid robot data is difficult to scale. That's why Mengda Xu and Han Zhang built DexUMI: a tool for demonstrating how to control a dexterous robot hand, which allows you to quickly collect task data. Co-hosted by Michael Cho - Rbt/Acc and Chris Paxton

RoboPapers

26,344 views • 1 year ago

Full episode dropping soon! Geeking out with Jason Ma Tianyu Li Anh-Quan Pham Chet Bhateja on Dyna-2: A 1-Million-Hour Scaling Law for World-Action Models Co-hosted by Michael Cho - Rbt/Acc Chris Paxton Jiafei Duan

Full episode dropping soon! Geeking out with Jason Ma Tianyu Li Anh-Quan Pham Chet Bhateja on Dyna-2: A 1-Million-Hour Scaling Law for World-Action Models Co-hosted by Michael Cho - Rbt/Acc Chris Paxton Jiafei Duan

RoboPapers

10,912 views • 1 month 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 • 8 months ago

Teaching robots to perform dexterous manipulation tasks currently requires teleoperation, which limits demonstration quality, speed, and scalability. Instead, why not use human videos? The problem is that a human hand isn’t a robot hand, so data must be retargeted using simulation to resolve issues like collisions and interpenetration when controlling the hand. In VideoManip, Hongyi Chen and co-authors built a system to solve this problem, taking in RGB videos of humans performing manipulation tasks and using them to create accurate simulations with which to learn robot policies. Watch episode #73 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton, now to learn more!

Teaching robots to perform dexterous manipulation tasks currently requires teleoperation, which limits demonstration quality, speed, and scalability. Instead, why not use human videos? The problem is that a human hand isn’t a robot hand, so data must be retargeted using simulation to resolve issues like collisions and interpenetration when controlling the hand. In VideoManip, Hongyi Chen and co-authors built a system to solve this problem, taking in RGB videos of humans performing manipulation tasks and using them to create accurate simulations with which to learn robot policies. Watch episode #73 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton, now to learn more!

RoboPapers

27,360 views • 5 months ago

Specifying reward functions for robots is one of the hardest things about reinforcement learning. Robot rewards often need to be very detailed; metrics like progress can be ill-defined and hard to estimate. This leads to most robot learning defaulting to sparse rewards or simple preference learning. But naive preference learning (having human annotators choose one trajectory over another) is an easy solution, but obscures a lot of the signal in complex tasks and can make learning a lot less efficient. Marcel Torné, Anubha Mahajan, and Abhijnya Bhat join us to talk about their solution: freeform preference learning, which lets annotators define natural-language axes to compare trajectories over. This improves real-world performance on long-horizon manipulation tasks over sparse rewards and simple binary preference learning. Watch Epsiode 103 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, today to learn more!

Specifying reward functions for robots is one of the hardest things about reinforcement learning. Robot rewards often need to be very detailed; metrics like progress can be ill-defined and hard to estimate. This leads to most robot learning defaulting to sparse rewards or simple preference learning. But naive preference learning (having human annotators choose one trajectory over another) is an easy solution, but obscures a lot of the signal in complex tasks and can make learning a lot less efficient. Marcel Torné, Anubha Mahajan, and Abhijnya Bhat join us to talk about their solution: freeform preference learning, which lets annotators define natural-language axes to compare trajectories over. This improves real-world performance on long-horizon manipulation tasks over sparse rewards and simple binary preference learning. Watch Epsiode 103 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, today to learn more!

RoboPapers

17,403 views • 22 days ago

For robots to be useful, they can’t just dance — they must be able to physically interact with the world around them. Unfortunately, the sorts of motion tracking policies you see performing dancing or martial arts are not really capable of the kind of precise, forceful interaction needed to perform useful interactions with the world. Siheng Zhao and Yanjie Ze join us to talk about ResMimic, their new paper which takes a general-purpose human motion-tracking policy and improves it with a residual policy to reliably interact with objects To learn more, watch Episode #47 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton, today!

For robots to be useful, they can’t just dance — they must be able to physically interact with the world around them. Unfortunately, the sorts of motion tracking policies you see performing dancing or martial arts are not really capable of the kind of precise, forceful interaction needed to perform useful interactions with the world. Siheng Zhao and Yanjie Ze join us to talk about ResMimic, their new paper which takes a general-purpose human motion-tracking policy and improves it with a residual policy to reliably interact with objects To learn more, watch Episode #47 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton, today!

RoboPapers

11,399 views • 10 months ago

Ep#11 with Soroush Nasiriany Zhenyu Jiang Abhi Maddukuri Lawrence Yunliang Chen on Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation Co-hosted by Chris Paxton & Michael Cho - Rbt/Acc

Ep#11 with Soroush Nasiriany Zhenyu Jiang Abhi Maddukuri Lawrence Yunliang Chen on Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation Co-hosted by Chris Paxton & Michael Cho - Rbt/Acc

RoboPapers

13,873 views • 1 year ago

The holy grail of robotics is to be able to perform previously-unseen, out-of-distribution manipulation tasks “zero shot” in a new environment. NovaFlow proposes an approach which (1) generates a video, (2) computes predicted flow — how points move through the scene — and (3) uses this flow as an objective to generate a motion. Using this procedure, NovaFlow generates motions in unseen scenes, for unseen tasks, and can transfer across embodiments. To learn more, we are joined by Hongyu Li and Jiahui Fu from RAI. Watch Episode #63 of RoboPapers with Chris Paxton and Michael Cho - Rbt/Acc now to learn more!

The holy grail of robotics is to be able to perform previously-unseen, out-of-distribution manipulation tasks “zero shot” in a new environment. NovaFlow proposes an approach which (1) generates a video, (2) computes predicted flow — how points move through the scene — and (3) uses this flow as an objective to generate a motion. Using this procedure, NovaFlow generates motions in unseen scenes, for unseen tasks, and can transfer across embodiments. To learn more, we are joined by Hongyu Li and Jiahui Fu from RAI. Watch Episode #63 of RoboPapers with Chris Paxton and Michael Cho - Rbt/Acc now to learn more!

RoboPapers

21,434 views • 7 months ago

World models — action-conditioned predictive models of the environment — are an exciting are of research for robots that can be useful both for training and for test-time compute. But video-based world models waste a lot of predictive power on reconstructing pixels, which makes model and data requirements much higher and limits how far out into the future their predictions remain viable. Instead, what if we learned a purely semantic world model, one which predicts which properties will be true about the world after a sequence of actions, without reconstructing the whole images? Jacob Berg tells us more. Watch Episode #53 of RoboPapers now, with Michael Cho - Rbt/Acc and Chris Paxton!

World models — action-conditioned predictive models of the environment — are an exciting are of research for robots that can be useful both for training and for test-time compute. But video-based world models waste a lot of predictive power on reconstructing pixels, which makes model and data requirements much higher and limits how far out into the future their predictions remain viable. Instead, what if we learned a purely semantic world model, one which predicts which properties will be true about the world after a sequence of actions, without reconstructing the whole images? Jacob Berg tells us more. Watch Episode #53 of RoboPapers now, with Michael Cho - Rbt/Acc and Chris Paxton!

RoboPapers

39,322 views • 9 months ago