ManiSkill

ManiSkill Data ManiSkill is a unified benchmark for learning generalizable robotic manipulation skills powered by SAPIEN. It features 20 out-of-box task families with 2000+ diverse object models and 4M+ demonstration frames. Moreover, it empowers fast visual input learning algorithms so that a CNN-based policy can coll

Papers using ManiSkill (16)

Colosseum V2: Benchmarking Generalization for Vision Language Action Models2026Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation2026GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks2026DockAnywhere: Data-Efficient Visuomotor Policy Learning for Mobile Manipulation via Novel Demonstration Generation2026Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation2026Non-Markovian Long-Horizon Robot Manipulation via Keyframe Chaining2026$\pi$-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs2026VolumeDP: Modeling Volumetric Representation for Manipulation Policy Learning2026ManiDreams: An Open-Source Library for Robust Object Manipulation via Uncertainty-aware Task-specific Intuitive Physics2026FODMP: Fast One-Step Diffusion of Movement Primitives Generation for Time-Dependent Robot Actions2026Generalizable Geometric Prior and Recurrent Spiking Feature Learning for Humanoid Robot Manipulation2026Bridging Simulation and Reality: Cross-Domain Transfer with Semantic 2D Gaussian Splatting2025E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion2025GeoVLA: Empowering 3D Representations in Vision-Language-Action Models2025Physical Autoregressive Model for Robotic Manipulation without Action Pretraining2025Coupled Distributional Random Expert Distillation For World Model Online Imitation Learning2025