Fast Plans, Faithful Actions: Closing the Planning-Execution Gap in Hierarchical Vision-Language-Action Models

arXiv:2609.30833 · cs.RO · Submitted 2026-09-25 · Read on arXiv

cs.RO

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/Physical-Intelligence/openpi

Terminology

• Consistency — 4× in this paper · explained in 3 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Flow Matching — 3× in this paper · explained in 7 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Vision-Language Model (VLM) — 2× in this paper · explained in 3 episodes
• Action Chunking — 1× in this paper · explained in 1 episode
• Automatic Waypoint Extraction — 1× in this paper
• Benchmarking — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Exponential Moving Average (EMA) — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Granularity Mismatch — 1× in this paper · explained in 2 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes

Sources

• PaliGemma: A versatile 3B VLM for transfer
• Classifier-Free Diffusion Guidance
• LoRA: Low-Rank Adaptation of Large Language Models
• NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces
• 3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance
• LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
• Flow Matching for Generative Modeling
• GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding
• Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models
• Guided Flows for Generative Modeling and Decision Making

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
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving