Isaac Gym

Isaac Gym is a benchmark that contains a diverse set of simulated robotic environments and tasks used to evaluate the performance of Vision-Language-Action models in cross-embodied settings.

Papers using Isaac Gym (12)

X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models2026ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills2025 · 1 citesHierKick: Hierarchical Reinforcement Learning for Vision-Guided Soccer Robot Control2026Entropy-Controlled Intrinsic Motivation Reinforcement Learning for Quadruped Robot Locomotion in Complex Terrains2025A Framework for Deploying Learning-based Quadruped Loco-Manipulation2025Population-coded Spiking Neural Networks For High-dimensional Robotic Control2025MULE: Multi-terrain And Unknown Load Adaptation For Effective Quadrupedal Locomotion2025PROBE: Proprioceptive Obstacle Detection and Estimation while Navigating in Clutter2025Depth Transfer: Learning to See Like a Simulator for Real-World Drone Navigation2025MULE: Multi-terrain and Unknown Load Adaptation for Effective Quadrupedal Locomotion2025H2-COMPACT: Human-Humanoid Co-Manipulation via Adaptive Contact Trajectory Policies2025Multi-Keypoint Affordance Representation for Functional Dexterous Grasping2025