HyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAI

Robot Manipulation On Rlbench

Métriques

Input Image Size
Succ. Rate (18 tasks, 100 demo/task)

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Input Image Size
Succ. Rate (18 tasks, 100 demo/task)
Paper TitleRepository
Image-BC CNN1281.3Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
ARP+-86.0Autoregressive Action Sequence Learning for Robotic Manipulation
C2FARM-BC (Evaluated in PerAct)12820.1Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation
Act3D25665Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation
Auto-λ--Auto-Lambda: Disentangling Dynamic Task Relationships
RVT12862.9RVT: Robotic View Transformer for 3D Object Manipulation
3D-LOTUS25683.1Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy-
PerAct (Evaluated in RVT)12849.4Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
PerAct12842.7Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
Hiveformer-45.3Instruction-driven history-aware policies for robotic manipulations
PolarNet12846.4PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation
SAM2Act12886.8SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
3D Diffuser Actor25681.33D Diffuser Actor: Policy Diffusion with 3D Scene Representations
Image-BC VIT1281.3Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
RVT-212881.4RVT-2: Learning Precise Manipulation from Few Demonstrations
0 of 15 row(s) selected.