Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Many tasks cannot be completed by one robot alone. But coordinating multiple robots performing complex manipulation tasks is very difficult. Many solutions rely on complicated centralized control, which tends towards bespoke methods that do not scale well with team size. Enter CHORUS by Ria Doshi, Jeannette Bohg, and team....

RoboPapers's profile picture

RoboPapers

6,499 subscribers

26,395 Aufrufe • vor 1 Monat •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

1 Kommentare

Profilbild von KP bhoomika
KP bhoomikavor 1 Monat

@chris_j_paxton Watching multiple robots coordinate to lift a single laundry basket just to realize they still won't fold the clothes afterward 💀

Ähnliche Videos

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!
44:20

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 Aufrufe • vor 4 Monaten

Robots need to be able to apply pressure and make contact with objects as needed in order to accomplish their tasks. From compliance to working safely around humans to whole-body manipulation of heavy objects, combining force and position control can dramatically expand the capabilities of robots. This is especially true for legged robots, which have so much ability to exert forces on the world around them. But how do we train robots which can do this? Baoxiong Jia tells us more in our discussion of his team’s recent, Best Paper Award winning work on learning a unified policy for position and force control, called UniFP. To learn more, watch Episode #49 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton.
50:15

Robots need to be able to apply pressure and make contact with objects as needed in order to accomplish their tasks. From compliance to working safely around humans to whole-body manipulation of heavy objects, combining force and position control can dramatically expand the capabilities of robots. This is especially true for legged robots, which have so much ability to exert forces on the world around them. But how do we train robots which can do this? Baoxiong Jia tells us more in our discussion of his team’s recent, Best Paper Award winning work on learning a unified policy for position and force control, called UniFP. To learn more, watch Episode #49 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton.

RoboPapers

44,822 Aufrufe • vor 9 Monaten

Robots, unfortunately, tend to be expensive. And finding a robot that’s both capable of performing a wide variety of mobile manipulation tasks, and is affordable and “hackable”, is extremely difficult. Many different problems need to be addressed, from arm control to navigation to integrating your data collection strategy into hardware design. This can make it difficult for all but the most well-funded teams to “scale” real-world robotics research. Fortunately, the team behind Build Your Own Robot has a solution. Manan Anjaria, Mahi Shafiullah 🏠🤖,Jeff Cui, and Enes Erciyes joined us to talk about how they build a fully open-source mobile manipulator out of off-the-shelf parts, which has humanlike range of motion, and can perform a wide variety of tasks, all while being only roughly $10,000 to build. Watch Episode 71 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, today to learn more!
1:01:11

Robots, unfortunately, tend to be expensive. And finding a robot that’s both capable of performing a wide variety of mobile manipulation tasks, and is affordable and “hackable”, is extremely difficult. Many different problems need to be addressed, from arm control to navigation to integrating your data collection strategy into hardware design. This can make it difficult for all but the most well-funded teams to “scale” real-world robotics research. Fortunately, the team behind Build Your Own Robot has a solution. Manan Anjaria, Mahi Shafiullah 🏠🤖,Jeff Cui, and Enes Erciyes joined us to talk about how they build a fully open-source mobile manipulator out of off-the-shelf parts, which has humanlike range of motion, and can perform a wide variety of tasks, all while being only roughly $10,000 to build. Watch Episode 71 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, today to learn more!

RoboPapers

34,151 Aufrufe • vor 5 Monaten

How can we build a general-purpose “foundation model” for robot motion? Zhengyi “Zen” Luo joins us to talk about SONIC, which uses motion tracking as a foundational task for humanoid robot control, and scales humanoid control training to 9k GPU hours and 100 million frames worth of data. The result: a model with a generally-useful embedding space that can be controlled by a VLA, or from human video, to perform a wide variety of humanoid whole-body-control tasks, including with zero-shot transfer to previously unseen motions. Watch episode 72 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, now!
59:44

How can we build a general-purpose “foundation model” for robot motion? Zhengyi “Zen” Luo joins us to talk about SONIC, which uses motion tracking as a foundational task for humanoid robot control, and scales humanoid control training to 9k GPU hours and 100 million frames worth of data. The result: a model with a generally-useful embedding space that can be controlled by a VLA, or from human video, to perform a wide variety of humanoid whole-body-control tasks, including with zero-shot transfer to previously unseen motions. Watch episode 72 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, now!

RoboPapers

24,802 Aufrufe • vor 5 Monaten

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
58:42

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 Aufrufe • vor 1 Jahr

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!
54:52

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

27,904 Aufrufe • vor 7 Monaten

Robots has a data problem, in that robotics data is rare. While human video is quite common, it’s not usually directly usable for robots for a variety of reasons, most significantly that it’s missing explicit, accurate robot actions. Instead, Jeremy Collins proposes that we predict keypoint trajectories — basically, how any given point in an object will move as a robot performs a task. This lets us use action-free human video to train robot skills. Learn more by watching Episode #37 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton now.
44:56

Robots has a data problem, in that robotics data is rare. While human video is quite common, it’s not usually directly usable for robots for a variety of reasons, most significantly that it’s missing explicit, accurate robot actions. Instead, Jeremy Collins proposes that we predict keypoint trajectories — basically, how any given point in an object will move as a robot performs a task. This lets us use action-free human video to train robot skills. Learn more by watching Episode #37 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton now.

RoboPapers

89,011 Aufrufe • vor 10 Monaten

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!
47:57

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

13,768 Aufrufe • vor 4 Tagen

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!
50:41

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 Aufrufe • vor 9 Monaten

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!
1:09:10

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

24,677 Aufrufe • vor 4 Monaten

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!
1:08:49

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 Aufrufe • vor 6 Monaten

Pretraining is essential for good performance on a wide variety of robotics tasks, and so most vision-language-action models build off of a vision language model (VLM) trained on a wide variety of image-language data. But how does the choice of VLM translate to downstream robotics performance? Jianke Zhang and @GYanjiang join us to talk about this key part of the robot policy, looking at a wide variety of different VLMs and how they perform. Interestingly, they see that performance on auxiliary tasks like quesiton answering did not lead to downstream improvements in control. To learn more, watch episode 65 of RoboPapers now, with Chris Paxton and Jiafei Duan!
1:03:46

Pretraining is essential for good performance on a wide variety of robotics tasks, and so most vision-language-action models build off of a vision language model (VLM) trained on a wide variety of image-language data. But how does the choice of VLM translate to downstream robotics performance? Jianke Zhang and @GYanjiang join us to talk about this key part of the robot policy, looking at a wide variety of different VLMs and how they perform. Interestingly, they see that performance on auxiliary tasks like quesiton answering did not lead to downstream improvements in control. To learn more, watch episode 65 of RoboPapers now, with Chris Paxton and Jiafei Duan!

RoboPapers

23,905 Aufrufe • vor 6 Monaten

Teaching robots from human video is an important part of overcoming the “data gap” in robotics, but many of the details still need to be worked out. Homanga Bharadhwaj tells us about two recent research papers, Gen2Act and Spider, which go over different aspects of the problem: Gen2Act uses generative video models to create a reference of how a task should be performed given a language prompt; then, it uses a multi-purpose policy that can “translate” from human video to robot motion. However, Gen2Act has its limitations, in particular when it comes to dexterous, contact-rich tasks. That’s where SPIDER comes in: it uses human data together with simulation to train policies across many different humanoid hands and datasets. Also of note is that this is our first episode with our new rotating co-host, Jiafei Duan. To learn more, watch Episode #57 of RoboPapers now, with Chris Paxton and Jiafei Duan!
51:04

Teaching robots from human video is an important part of overcoming the “data gap” in robotics, but many of the details still need to be worked out. Homanga Bharadhwaj tells us about two recent research papers, Gen2Act and Spider, which go over different aspects of the problem: Gen2Act uses generative video models to create a reference of how a task should be performed given a language prompt; then, it uses a multi-purpose policy that can “translate” from human video to robot motion. However, Gen2Act has its limitations, in particular when it comes to dexterous, contact-rich tasks. That’s where SPIDER comes in: it uses human data together with simulation to train policies across many different humanoid hands and datasets. Also of note is that this is our first episode with our new rotating co-host, Jiafei Duan. To learn more, watch Episode #57 of RoboPapers now, with Chris Paxton and Jiafei Duan!

RoboPapers

24,286 Aufrufe • vor 8 Monaten

Reinforcement learning has unlocked tremendous gains in broader AI and humanoid robot whole body control, but still has yet to deliver strong results for robot manipulation due to the difficulty of capturing tasks in an accurate simulation; one way to fix this is to create complex environments with learned world models. But learning fully within world models is often intractable as powerful world models are computationally too expensive. Instead, Joseph Amigo and Rooholla Khorrambakht propose to break the problem down: into a large-scale world model that can generate forward trajectories, and a lightweight, low-dimensional latent-space model which can approximate local dynamics of a problem, without needing to back-propagate through a heavy global model. What this means: you can do reinforcement learning in this coupled local-global world model, and learn contact rich skills for a robot. To learn more, watch Episode #101 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan!
51:25

Reinforcement learning has unlocked tremendous gains in broader AI and humanoid robot whole body control, but still has yet to deliver strong results for robot manipulation due to the difficulty of capturing tasks in an accurate simulation; one way to fix this is to create complex environments with learned world models. But learning fully within world models is often intractable as powerful world models are computationally too expensive. Instead, Joseph Amigo and Rooholla Khorrambakht propose to break the problem down: into a large-scale world model that can generate forward trajectories, and a lightweight, low-dimensional latent-space model which can approximate local dynamics of a problem, without needing to back-propagate through a heavy global model. What this means: you can do reinforcement learning in this coupled local-global world model, and learn contact rich skills for a robot. To learn more, watch Episode #101 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan!

RoboPapers

16,545 Aufrufe • vor 9 Tagen

Benchmarking, evaluating, and developing robotics code is difficult, and part of this is because no simulator really reflects the diversity and scale of real embodiments. Enter MolmoSpaces from AI2: a massive open ecosystem with a range of 230,000 handcrafted and procedurally-generated home environments, including 48,000 manipulable objects. Crucially, MolmoSpaces provides simulation environments which work for both navigation and manipulation. We talked to the team: Yejin Kim @ RSS2026, Omar Rayyan, and Max Argus, to tell us more. Watch Episode 69 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, now!
1:11:00

Benchmarking, evaluating, and developing robotics code is difficult, and part of this is because no simulator really reflects the diversity and scale of real embodiments. Enter MolmoSpaces from AI2: a massive open ecosystem with a range of 230,000 handcrafted and procedurally-generated home environments, including 48,000 manipulable objects. Crucially, MolmoSpaces provides simulation environments which work for both navigation and manipulation. We talked to the team: Yejin Kim @ RSS2026, Omar Rayyan, and Max Argus, to tell us more. Watch Episode 69 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, now!

RoboPapers

21,116 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 8 Monaten

Robotics has a data problem, and egocentric data is a compelling way to solve it because egocentric data is (1) scalable — it’s cheap to collect — and (2) easily captures the breadth and diversity of real human tasks, while (3) being true to real physics. Lightwheel recently released a hundred thousand hours of high-quality egocentric video data, spread across a wide range of human tasks from cleaning and tidying to assembly and construction to retail tasks. Here to tell us about this tremendous effort is Steve Xie, CEO and co-founder of Lightwheel. The data is also available on HuggingFace right now. Watch Episode 102 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, to learn more!
1:09:08

Robotics has a data problem, and egocentric data is a compelling way to solve it because egocentric data is (1) scalable — it’s cheap to collect — and (2) easily captures the breadth and diversity of real human tasks, while (3) being true to real physics. Lightwheel recently released a hundred thousand hours of high-quality egocentric video data, spread across a wide range of human tasks from cleaning and tidying to assembly and construction to retail tasks. Here to tell us about this tremendous effort is Steve Xie, CEO and co-founder of Lightwheel. The data is also available on HuggingFace right now. Watch Episode 102 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, to learn more!

RoboPapers

32,717 Aufrufe • vor 5 Tagen

Sports like tennis are great examples of the sort of dynamic whole-body interaction that’s possible with humanoid robots. But capturing examples of fast, dynamic interactions from humans is really difficult. Enter LATENT, which uses lower-quality human data plus reinforcement learning to teach a robot to play tennis, able to complete back-and-forth volleys at a human level. LATENT has three steps: (1) collecting imperfect human data like a backswing, (2) using these to learn a latent action space, and (3) they train a high-level policy in simulation which can compose these actions and execute tennis skills on a robot. Haofei Lu and Yunrui Lian ✈️ IROS join us to tell us about their method. Watch Episode #80 of RoboPapers, with Chris Paxton and Jiafei Duan, now to learn more!
55:30

Sports like tennis are great examples of the sort of dynamic whole-body interaction that’s possible with humanoid robots. But capturing examples of fast, dynamic interactions from humans is really difficult. Enter LATENT, which uses lower-quality human data plus reinforcement learning to teach a robot to play tennis, able to complete back-and-forth volleys at a human level. LATENT has three steps: (1) collecting imperfect human data like a backswing, (2) using these to learn a latent action space, and (3) they train a high-level policy in simulation which can compose these actions and execute tennis skills on a robot. Haofei Lu and Yunrui Lian ✈️ IROS join us to tell us about their method. Watch Episode #80 of RoboPapers, with Chris Paxton and Jiafei Duan, now to learn more!

RoboPapers

30,078 Aufrufe • vor 4 Monaten

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!
1:05:20

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

19,727 Aufrufe • vor 9 Monaten