Deep reinforcement learning could be used to learn dexterous robotic policies but it is challenging to transfer them to new robots with vastly different hardware properties. It is also prohibitively expensive to learn a new policy from scratch for each robot hardware due to the high sample complexity of modern state-of-the-art algorithms. We propose a novel approach called Hardware Conditioned Policies where we train a universal policy conditioned on a vector representation of robot hardware. We considered robots in simulation with varied dynamics, kinematic structure, kinematic lengths and degrees-of-freedom. First, we use the kinematic structure directly as the hardware encoding and show great zero-shot transfer to completely novel robots not seen during training. For robots with lower zero-shot success rate, we also demonstrate that fine-tuning the policy network is significantly more sample-efficient than training a model from scratch. In tasks where knowing the agent dynamics is important for success, we learn an embedding for robot hardware and show that policies conditioned on the encoding of hardware tend to generalize and transfer well. Videos of experiments are available at: https://sites.google.com/view/robot-transfer-hcp.

Deep reinforcement learning could be used to learn dexterous robotic policies but it is challenging to transfer them to new robots with vastly different hardware properties. It is also prohibitively expensive to learn a new policy from scratch for each robot hardware due to the high sample complexity of modern state-of-the-art algorithms. We propose a novel approach called Hardware Conditioned Policies where we train a universal policy conditioned on a vector representation of robot hardware. We considered robots in simulation with varied dynamics, kinematic structure, kinematic lengths and degrees-of-freedom. First, we use the kinematic structure directly as the hardware encoding and show great zero-shot transfer to completely novel robots not seen during training. For robots with lower zero-shot success rate, we also demonstrate that fine-tuning the policy network is significantly more sample-efficient than training a model from scratch. In tasks where knowing the agent dynamics is important for success, we learn an embedding for robot hardware and show that policies conditioned on the encoding of hardware tend to generalize and transfer well. Videos of experiments are available at: https://sites.google.com/view/robot-transfer-hcp.

It is also prohibitively expensive to learn a new policy from scratch for each robot hardware due to the high sample complexity of modern state-of-the-art algorithms.

Teleoperation for robot imitation learning is bottlenecked by hardware availability. Can high-quality robot data be collected without a physical robot? We present a system for augmenting Apple Vision Pro with real-time virtual robot feedback. By providing users with an intuitive understanding of how their actions translate to robot motions, we enable the collection of natural barehanded human data that is compatible with the limitations of physical robot hardware. We conducted a user study with 15 participants demonstrating 3 different tasks each under 3 different feedback conditions and directly replayed the collected trajectories on physical robot hardware. Results suggest live robot feedback dramatically improves the quality of the collected data, suggesting a new avenue for scalable human data collection without access to robot hardware. Videos and more are available at https://nataliya.dev/armada.

The researchers taught the robot, called Mobile ALOHA (an acronym for "a low-cost open-source hardware teleoperation system for bimanual operation"), seven different tasks requiring a variety of mobility and dexterity skills, such as rinsing a pan or giving someone a high five. To teach the robot how to cook shrimp, for example, the researchers remotely operated it 20 times to get the shrimp into the plan, flip it, and then serve it. They did it slightly differently each time so the robot learned different ways to do the same task, says Zipeng Fu, a PhD Student at Stanford, who was project co-lead. The robot was then trained on these demonstrations, as well as other human-operated demonstrations for different types of tasks that have nothing to do with shrimp cooking, such as tearing off a paper towel or tape collected by an earlier ALOHA robot without wheels, says Chelsea Finn, an assistant professor at Stanford University, who was an advisor for the project. This "co-training" approach, in which new and old data are combined, helped Mobile ALOHA learn new jobs relatively quickly, compared with the usual approach of training AI systems on thousands if not millions of examples.

We present SLoMo: a first-of-its-kind framework for transferring skilled motions from casually captured "in the wild" video footage of humans and animals to legged robots. SLoMo works in three stages: 1) synthesize a physically plausible reconstructed key-point trajectory from monocular videos; 2) optimize a dynamically feasible reference trajectory for the robot offline that includes body and foot motion, as well as contact sequences that closely tracks the key points; 3) track the reference trajectory online using a general-purpose model-predictive controller on robot hardware. Traditional motion imitation for legged motor skills often requires expert animators, collaborative demonstrations, and/or expensive motion capture equipment, all of which limits scalability. Instead, SLoMo only relies on easy-to-obtain monocular video footage, readily available in online repositories such as YouTube. It converts videos into motion primitives that can be executed reliably by real-world robots. We demonstrate our approach by transferring the motions of cats, dogs, and humans to example robots including a quadruped (on hardware) and a humanoid (in simulation). To the best knowledge of the authors, this is the first attempt at a general-purpose motion transfer framework that imitates animal and human motions on legged robots directly from casual videos without artificial markers or labels.

Accessibility is one of the most important features in the design of robots and their interfaces. This thesis proposes methods that improve the accessibility of robots for three different target audiences: consumers, researchers, and learners. In order for humans and robots to work together effectively, they both must be able to communicate with each other. We tackle the problem of generating route instructions that are readily understandable by novice humans for the navigation of a priori unknown indoor environments. We then move on to the related problem of enabling robots to understand natural language utterances in the context of learning to operate articulated objects (e.g., fridges, drawers) by leveraging kinematic models. Next, we turn our focus to the development of accessible and reproducible robotic platforms for scientific research. We propose a new concept for reproducible robotics research that integrates development and benchmarking, so that reproducibility is obtained "by design" from the beginning of the research and development process. We then propose a framework called SHARC (SHared Autonomy for Remote Collaboration), to improve accessibility for underwater robotic intervention operations. SHARC allows multiple remote scientists to efficiently plan and execute high-level sampling procedures using an underwater manipulator while deferring low-level control to the robot. Lastly, we developed the first hardware-based MOOC in AI and robotics. This course allows learners to study autonomy hands-on by making real robots make their own decisions and accomplish broadly defined tasks. We design a new robotic platform from the ground up to support this new learning experience. A fully browser-based interface, based on leading tools and technologies for code development, testing, validation, and deployment serves to maximize the accessibility of these educational resources.

Deep reinforcement learning could be used to learn dexterous robotic policies but it is challenging to transfer them to new robots with vastly different hardware properties. It is also prohibitively expensive to learn a new policy from scratch for each robot hardware due to the high sample complexity of modern state-of-the-art algorithms. We propose a novel approach called Hardware Conditioned Policies where we train a universal policy conditioned on a vector representation of robot hardware. We considered robots in simulation with varied dynamics, kinematic structure, kinematic lengths and degrees-of-freedom. First, we use the kinematic structure directly as the hardware encoding and show great zero-shot transfer to completely novel robots not seen during training.

Deep reinforcement learning could be used to learn dexterous robotic policies but it is challenging to transfer them to new robots with vastly different hardware properties. It is also prohibitively expensive to learn a new policy from scratch for each robot hardware due to the high sample complexity of modern state-of-the-art algorithms. We propose a novel approach called Hardware Conditioned Policies where we train a universal policy conditioned on a vector representation of robot hardware. We considered robots in simulation with varied dynamics, kinematic structure, kinematic lengths and degrees-of-freedom. First, we use the kinematic structure directly as the hardware encoding and show great zero-shot transfer to completely novel robots not seen during training. For robots with lower zero-shot success rate, we also demonstrate that fine-tuning the policy network is significantly more sample-efficient than training a model from scratch. In tasks where knowing the agent dynamics is important for success, we learn an embedding for robot hardware and show that policies conditioned on the encoding of hardware tend to generalize and transfer well. Videos of experiments are available at: https://sites.google.com/view/robot-transfer-hcp.