AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding

arXiv:2606.06155 · cs.RO, cs.CV, cs.MM · Submitted 2026-06-04 · Read on arXiv

cs.RO, cs.CV, cs.MM

Submitted: 2026-06-04

Updated: 2026-10-18

Comments: Preprint. Code and project page are available. Code: https://github.com/Skywalker-yqz/AffordanceVLA Project page: https://skywalker-yqz.github.io/AffordanceVLA/

Code: https://github.com/Skywalker-yqz/AffordanceVLA

Project page: https://skywalker-yqz.github.io/AffordanceVLA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Data Augmentation — 1× in this paper · explained in 7 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 5 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• Affordances from Human Videos as a Versatile Representation for Robotics
• Motus: A Unified Latent Action World Model
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation
• UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
• WorldVLA: Towards Autoregressive Action World Model
• GR-3 Technical Report
• RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design
• EqvAfford: SE(3) Equivariance for Point-Level Affordance Learning
• Learning Part-Aware Dense 3D Feature Field for Generalizable Articulated Object Manipulation
• Reducing the Barrier to Entry of Complex Robotic Software: a MoveIt! Case Study
• OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation
• GraspMolmo: Generalizable Task-Oriented Grasping via Large-Scale Synthetic Data Generation
• Learning Universal Policies via Text-Guided Video Generation
• AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains
• End-to-End Affordance Learning for Robotic Manipulation
• Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
• ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• ${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities

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