Dataset profile

RoboCasa365

RoboCasa365 is a simulation framework for training and benchmarking generalist robots on kitchen tasks. It offers simulated tasks and demonstrations, making it useful for pretraining and evaluation before real healthcare collection.

Source institutionUT Austin Robot Perception and Learning Lab
Robot ManipulationHousehold Robotics

Overview

RoboCasa365 is a simulation framework for training and benchmarking generalist robots on kitchen tasks. It offers simulated tasks and demonstrations, making it useful for pretraining and evaluation before real healthcare collection.

What's included

  • Simulated kitchen tasks
  • Kitchen scenes and 3D objects
  • Human and robot demonstration datasets

Tasks / activities

kitchen manipulationcountertop tasksobject arrangementsimulated household workflows

Modalities

RGBDepthRobot ActionsLanguageAnnotations

Collection methodology

Tasks are implemented in simulation with assets, automated trajectories, and human demonstration resources for benchmark training.

Potential applications

  • Simulation pretraining
  • Generalist robot benchmarking
  • Kitchen manipulation policies
  • Synthetic-to-real planning

Access & licensing

This is a third-party public/research dataset. We do not own or distribute this dataset. Access and usage are governed by the original publisher's terms.

Access and use are governed by RoboCasa365 project terms and dependency licenses.

Limitations / opportunities for custom data

Teams moving from simulated household tasks to care facilities may need real-world demonstrations, physical constraints, and expert review.

Need data beyond this benchmark?

We design custom healthcare and caregiving collections around the tasks, experts, environments, and modalities your model requires.

Request Similar Data