KPGrasp: Scalable Keypoint Flow Matching for Dexterous Grasp Generation
cs.RO
Submitted: 2026-06-08
Updated: 2026-10-10
Code: https://github.com/kevinzakka/mink
Terminology
Sources
- SpringGrasp: Synthesizing Compliant, Dexterous Grasps under Shape Uncertainty
- Dexonomy: Synthesizing All Dexterous Grasp Types in a Grasp Taxonomy
- DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation
- Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation
- GenDexGrasp: Generalizable Dexterous Grasping
- Deep Differentiable Grasp Planner for High-DOF Grippers
- Learning Robust Real-World Dexterous Grasping Policies via Implicit Shape Augmentation
- FFHFlow: Diverse and Uncertainty-Aware Dexterous Grasp Generation via Flow Variational Inference
- $\mathcal{D(R,O)}$ Grasp: A Unified Representation of Robot and Object Interaction for Cross-Embodiment Dexterous Grasping
- HOGraspFlow: Taxonomy-Aware Hand-Object Retargeting for Multi-Modal SE(3) Grasp Generation
- SE(3)-Equivariant Diffusion Policy in Spherical Fourier Space
- Point Policy: Unifying Observations and Actions with Key Points for Robot Manipulation
- World Models for Learning Dexterous Hand-Object Interactions from Human Videos
- Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations
- Flow Matching for Generative Modeling
- FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
- Score-Based Generative Modeling through Stochastic Differential Equations
- Muon is Scalable for LLM Training
- RealDex: Towards Human-like Grasping for Robotic Dexterous Hand
- Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies