Related papers: Octo: An Open-Source Generalist Robot Policy
General-purpose robotic systems must master a large repertoire of diverse skills to be useful in a range of daily tasks. While reinforcement learning provides a powerful framework for acquiring individual behaviors, the time needed to…
Autoregressive policies offer a compelling foundation for scalable robot learning by enabling discrete abstraction, token-level reasoning, and flexible inference. However, applying autoregressive modeling to continuous robot actions…
Acquiring large-scale, high-fidelity robot demonstration data remains a critical bottleneck for scaling Vision-Language-Action (VLA) models in dexterous manipulation. We propose a Real-Sim-Real data collection and data editing pipeline that…
As robotic agents increasingly assist humans in reality, quadruped robots offer unique opportunities for interaction in complex scenarios due to their agile movement. However, building agents that can autonomously navigate, adapt, and…
Deep Reinforcement Learning (RL) has shown great success in learning complex control policies for a variety of applications in robotics. However, in most such cases, the hardware of the robot has been considered immutable, modeled as part…
The ability to transfer a policy from one environment to another is a promising avenue for efficient robot learning in realistic settings where task supervision is not available. This can allow us to take advantage of environments well…
Can we enable humanoid robots to generate rich, diverse, and expressive motions in the real world? We propose to learn a whole-body control policy on a human-sized robot to mimic human motions as realistic as possible. To train such a…
Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without requiring extensive manual engineering. However, robotic skill learning methods typically make one of several trade-offs to…
Despite strong multi-task pretraining, existing policies often exhibit poor task steerability. For example, a robot may fail to respond to a new instruction ``put the bowl in the sink" when moving towards the oven, executing ``close the…
For a robot to learn a good policy, it often requires expensive equipment (such as sophisticated sensors) and a prepared training environment conducive to learning. However, it is seldom possible to perfectly equip robots for economic…
Deep reinforcement learning has been shown to solve challenging tasks where large amounts of training experience is available, usually obtained online while learning the task. Robotics is a significant potential application domain for many…
Robot learning holds the promise of learning policies that generalize broadly. However, such generalization requires sufficiently diverse datasets of the task of interest, which can be prohibitively expensive to collect. In other fields,…
While recent advances have demonstrated strong performance in individual humanoid skills such as upright locomotion, fall recovery and whole-body coordination, learning a single policy that masters all these skills remains challenging due…
The dominant paradigm for end-to-end robot learning focuses on optimizing task-specific objectives that solve a single robotic problem such as picking up an object or reaching a target position. However, recent work on high-capacity models…
We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data. In recent years, policy gradient methods have emerged as a promising paradigm for training control policies in simulation.…
Egocentric human experience data presents a vast resource for scaling up end-to-end imitation learning for robotic manipulation. However, significant domain gaps in visual appearance, sensor modalities, and kinematics between human and…
Current vision-based robotics simulation benchmarks have significantly advanced robotic manipulation research. However, robotics is fundamentally a real-world problem, and evaluation for real-world applications has lagged behind in…
Data scaling has driven remarkable success in foundation models for Natural Language Processing (NLP) and Computer Vision (CV), yet the principles of effective data scaling in robotic manipulation remain insufficiently understood. In this…
The ability to specify robot commands by a non-expert user is critical for building generalist agents capable of solving a large variety of tasks. One convenient way to specify the intended robot goal is by a video of a person demonstrating…
Data-driven simulators promise high data-efficiency for driving policy learning. When used for modelling interactions, this data-efficiency becomes a bottleneck: Small underlying datasets often lack interesting and challenging edge cases…