AeroManip-VLA: Scalable Vision-Language-Action Learning for Aerial Manipulation with RL-Generated Demonstrations

arXiv:2609.36915 · cs.RO, cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Project page: https://ruihuangnus.github.io/AeroManip-VLA-page/ABSTRACT

Terminology

• Benchmark — 29× in this paper · explained in 2 episodes
• Reinforcement Learning — 10× in this paper · explained in 4 episodes
• VLA Models — 8× in this paper · explained in 3 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Failure Modes — 5× in this paper · explained in 3 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Provenance — 3× in this paper · explained in 3 episodes
• Diffusion Policy — 2× in this paper
• Embodied AI — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Synthetic Data Generation — 2× in this paper · explained in 5 episodes
• Vision-Language-Action (VLA) Models — 2× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Diffusion Policy (DP) — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Flow Matching — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Imitation Learning (IL) — 1× in this paper · explained in 2 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Sim-to-Real Transfer — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
• SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment
• RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
• UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
• Lodestar: Supporting Independent Learning and Rapid Experimentation Through Data-Driven Analysis Recommendations
• AIR-VLA: Vision-Language-Action Systems for Aerial Manipulation
• AIR-VLA+: Decoupling Movement and Manipulation via Cascaded Dual-Action Decoders with Asymmetric MoE for Aerial Robots
• ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI
• $\pi$, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation
• DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning
• Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

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