dgrachevapache-2.0

A2 Environment Assets

Asset collection for the A2 tabletop manipulation environment in PyBullet simulation, including 66 simplified YCB objects, UR5e robot models, and pre-defined test scenarios for grasp, place, and pick-and-place tasks.

Downloads173

Why This Matters for Physical AI

Provides standardized simulation assets and benchmarking test cases for evaluating tabletop manipulation policies on grasping, placing, and pick-and-place tasks with both seen and unseen objects.

Technical Profile

Robot Embodiments
UR5e
Environment
simulation
Task Types
graspingplacepick_and_place
Data Format
URDF
Annotation Types
language_instructions
License
apache-2.0
Part of the LeRobot family

Community Signals

Top 50% by downloads
HuggingFace Discussions1

Access

Need custom physical AI data?

Claru builds purpose-built datasets for simulation applications with dense human annotations and quality assurance.

Request a Sample Pack

Related Datasets