-
Behavior-1k
The Behavior-1k dataset contains 1,000 everyday activities and realistic simulation. -
NOIR: Neural Signal Operated Intelligent Robots for Everyday Activities
NOIR is a general-purpose, intelligent brain-robot interface system that enables humans to command robots to perform everyday activities through brain signals. -
Breakout and Robot Pushing
The dataset used in the paper is an adapted version of the Atari baseline Breakout, and a simulated Robot pushing domain. -
Relay Policy Learning
Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning. -
Open X-Embodiment Collaboration
The Open X-Embodiment Collaboration dataset is a collection of robotic learning datasets and RT-X models. -
Fleet-Tools Benchmark
The Fleet-Tools benchmark is a dataset for robotic tool-use tasks. -
PoCo: Policy Composition from and for Heterogeneous Robot Learning
Training general robotic policies from heterogeneous data for different tasks is a significant challenge. Existing robotic datasets vary in different modalities such as color,... -
Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sour...
Learning language-conditioned robot behavior from offline data and crowd-sourced annotation. -
Scaling robot learning with semantically imagined experience
Scaling robot learning with semantically imagined experience. -
Neural Contractive Dynamical Systems
Stability guarantees are crucial when ensuring a fully autonomous robot does not take undesirable or potentially harmful actions. We propose a novel methodology to learn neural... -
Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Le...
The Sparse Diffusion Policy (SDP) framework, which integrates Mixture of Experts (MoE) layers into the diffusion policy.