Benchmarks

space robotics bench · AndrejOrsula

Space Robotics Bench provides robot-learning resources for space-oriented tasks.

Manipulation

Video2World · AetherLabsAI

Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos - Rethinking Embodied Real2Sim from a Software Engineering Perspective

Policy evaluation

VLA Grounding Probe · bakhtawar-i

VLA Grounding Probe investigates SmolVLA language grounding using instruction perturbations.

Policy evaluation

vla manipulation ablations · FERBIN12

VLA Manipulation Ablations studies manipulation generalization and OpenVLA under constrained GPU memory.

Policy evaluation

VLMbench · UCSB-AI

NeurIPS 2022 Paper "VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation"

Manipulation

VTDexManip · LQTS

This is a official code for the benchmark of the paper "VTDexManip: A Dataset and Benchmark for Visual-tactile Pretraining and Dexterous Manipulation with Reinforcement Learning" (ICLR 2025)

Manipulation

xrslam · openxrlab

OpenXRLab Visual-inertial SLAM Toolbox and Benchmark

Navigation & embodied interaction

EWMBench · AgibotTech

EWMBench evaluates scene, motion and semantic quality in embodied world models.

MyoSuite

Musculoskeletal simulation tasks for motor-control learning research.

Locomotion & whole-body control