Repository
Research
Bullet Physics · bulletphysics
A physics SDK for collision detection and multi-physics simulation.
Robot SDKs
Benchmarks / Research
CALVIN
A benchmark for language-conditioned long-horizon manipulation.
Overview
A benchmark for language-conditioned long-horizon manipulation.
Compare task definitions, evaluation splits, metrics and environment versions. Results from different robot configurations or protocols are not directly comparable.
Project information
- Maintainer
- mees
- Primary language
- Python
- Repository code license
- MIT
- Model-weight license
- Not recorded
- Dataset license
- Not recorded
- Hardware design license
- Not recorded
- Maintenance
- Not archived in the last recorded metadata
- Last observed repository push
- 2025-09-08
Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.
Documentation sections
- CALVIN
- :computer: Quick Start
- :framedpicture: Sensory Observations
- :joystick: Action Space
- :muscle: Evaluation: The Calvin Challenge
- Long-horizon Multi-task Language Control (LH-MTLC)
Browse this resource’s categories
Application areas
Education & research ↗Explore related collections
Browse Benchmarks →More in Benchmarks
Repository
Research
Repository
Research
DeeR VLA · yueyang130
DeeR-VLA studies dynamic multimodal-model inference for robot execution.
Vision-language-action
Repository
Open source
CLOVER · OpenDriveLab
CLOVER: Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation
Robot policies