OpenRobotLab

All

11 repositories

VLM-Grounder
Public
[CoRL 2024] VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
agent robotics vlm vision-and-language visual-grounding 3d-scene-understanding large-language-models gpt-4o vlm-grounder
Python
•0•71•1•0•Updated Nov 26, 2024Nov 26, 2024
EmbodiedScan
Public
[CVPR 2024 & NeurIPS 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI
computer-vision robotics 3d-vision multi-modal-learning
Python
•
Apache License 2.0
•37•497•5•2•Updated Nov 15, 2024Nov 15, 2024
UniHSI
Public
[ICLR 2024 Spotlight] Unified Human-Scene Interaction via Prompted Chain-of-Contacts
unified physics-simulation human-scene-interaction llm
Python
•8•167•2•0•Updated Nov 7, 2024Nov 7, 2024
PointLLM
Public
[ECCV 2024 Best Paper Candidate] PointLLM: Empowering Large Language Models to Understand Point Clouds
chatbot point-cloud llama representation-learning 3d multimodal vision-and-language gpt-4 foundation-models large-language-models
Python
•32•660•3•0•Updated Oct 29, 2024Oct 29, 2024
Grounded_3D-LLM
Public
Code&Data for Grounded 3D-LLM with Referent Tokens
3d scene-understanding llm
Python
•2•91•1•0•Updated Sep 30, 2024Sep 30, 2024
GRUtopia
Public
GRUtopia: Dream General Robots in a City at Scale
Python
•
MIT License
•27•523•6•0•Updated Sep 5, 2024Sep 5, 2024
OVExp
Public
OVExp: Open Vocabulary Exploration for Object-Oriented Navigation
0•30•1•0•Updated Jul 15, 2024Jul 15, 2024
OV_PARTS
Public
[NeurIPS 2023] OV-PARTS: Towards Open-Vocabulary Part Segmentation
Python
•6•72•6•0•Updated Jun 24, 2024Jun 24, 2024
HIMLoco
Public
Learning-based locomotion control from OpenRobotLab, including Hybrid Internal Model & H-Infinity Locomotion Control
Python
•
Other
•33•308•7•0•Updated May 14, 2024May 14, 2024
P3Former
Public
[IJCV 2024] P3Former: Position-Guided Point Cloud Panoptic Segmentation Transformer
point-cloud panoptic-segmentation transformer-decoder lidar-based
Python
•7•77•3•0•Updated Apr 2, 2024Apr 2, 2024
DORT
Public
[CoRL 2023] DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking
structure-from-motion 3d-detection 3d-tracking vision-based-perception
Python
•1•64•5•0•Updated Jan 21, 2024Jan 21, 2024