Home Console Docs News Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Robot Manipulation On Rlbench

Metrics

Input Image Size

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

Results

Performance results of various models on this benchmark

			Paper Title	Repository
SAM2Act	128	86.8	SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
ARP+	-	86.0	Autoregressive Action Sequence Learning for Robotic Manipulation
3D-LOTUS	256	83.1	Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy
RVT-2	128	81.4	RVT-2: Learning Precise Manipulation from Few Demonstrations
3D Diffuser Actor	256	81.3	3D Diffuser Actor: Policy Diffusion with 3D Scene Representations	-
Act3D	256	65	Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation
RVT	128	62.9	RVT: Robotic View Transformer for 3D Object Manipulation
PerAct (Evaluated in RVT)	128	49.4	Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
PolarNet	128	46.4	PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation
Hiveformer	-	45.3	Instruction-driven history-aware policies for robotic manipulations
PerAct	128	42.7	Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
C2FARM-BC (Evaluated in PerAct)	128	20.1	Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation
Image-BC CNN	128	1.3	Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
Image-BC VIT	128	1.3	Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
Auto-λ	-	-	Auto-Lambda: Disentangling Dynamic Task Relationships

0 of 15 row(s) selected.