# AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge

arXiv: https://arxiv.org/abs/2602.13476 · HTML: https://mlsanity.com/paper/2602.13476/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 54 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Builds on (most cited first, 30 of 37)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [One Step Diffusion via Shortcut Models](https://mlsanity.com/paper/2410.12557/) (2024)
- [TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2409.12514/) (2024)
- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [GNM: A General Navigation Model to Drive Any Robot](https://mlsanity.com/paper/2210.03370/) (2022)
- [Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation](https://mlsanity.com/paper/2203.15041/) (2022)
- [Rapid Exploration for Open-World Navigation with Latent Goal Models](https://mlsanity.com/paper/2104.05859/) (2021)
- [OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning](https://mlsanity.com/paper/2505.11917/) (2025)
- [OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation](https://mlsanity.com/paper/2505.03912/) (2025)
- [Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation](https://mlsanity.com/paper/1709.10489/) (2017)
- [HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers](https://mlsanity.com/paper/2410.05273/) (2024)
- [CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification](https://mlsanity.com/paper/2508.21046/) (2025)
- [Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation](https://mlsanity.com/paper/2410.08001/) (2024)
- [Training-Time Action Conditioning for Efficient Real-Time Chunking](https://mlsanity.com/paper/2512.05964/) (2025)
- [SACSoN: Scalable Autonomous Control for Social Navigation](https://mlsanity.com/paper/2306.01874/) (2023)
- [VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference](https://mlsanity.com/paper/2512.01031/) (2025)
- [Deep Visual MPC-Policy Learning for Navigation](https://mlsanity.com/paper/1903.02749/) (2019)
- [TartanDrive: A Large-Scale Dataset for Learning Off-Road Dynamics Models](https://mlsanity.com/paper/2205.01791/) (2022)
- [Leave No Observation Behind: Real-time Correction for VLA Action Chunks](https://mlsanity.com/paper/2509.23224/) (2025)
- [A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM](https://mlsanity.com/paper/2410.15549/) (2024)
- [Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment](https://mlsanity.com/paper/2511.04555/) (2025)
- [OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation](https://mlsanity.com/paper/2509.19480/) (2025)
- [From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control](https://mlsanity.com/paper/2405.04798/) (2024)
- [LeLaN: Learning A Language-Conditioned Navigation Policy from In-the-Wild Videos](https://mlsanity.com/paper/2410.03603/) (2024)
- [CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models](https://mlsanity.com/paper/2508.13446/) (2025)
- [ExAug: Robot-Conditioned Navigation Policies via Geometric Experience Augmentation](https://mlsanity.com/paper/2210.07450/) (2022)

## Built on by (most cited first, 10 of 10)

- [AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing](https://mlsanity.com/paper/2606.09811/) (2026)
- [RAPID: Redundancy-Aware and Compatibility-Optimal Edge-Cloud Partitioned Inference for Diverse VLA Models](https://mlsanity.com/paper/2603.07949/) (2026)
- [Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference](https://mlsanity.com/paper/2607.12659/) (2026)
- [AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation](https://mlsanity.com/paper/2604.24086/) (2026)
- [Towards General Language-Conditioned Latent Safety Filters](https://mlsanity.com/paper/2608.00315/) (2026)
- [TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model](https://mlsanity.com/paper/2609.09158/) (2026)
- [Efficient Vision-Language-Action Management and Serving for Robot Factories](https://mlsanity.com/paper/2609.12075/) (2026)
- [RealtimeWAM: One-Step Asynchronous World Action Models](https://mlsanity.com/paper/2610.06617/) (2026)
- [RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment](https://mlsanity.com/paper/2610.09294/) (2026)
- [ADAPT: Audio-Depth Action Planning with Transition-Aware Rewards for Lights-Out Industrial Navigation](https://mlsanity.com/paper/2610.15956/) (2026)

## Abstract (arXiv)

Robotic foundation models achieve strong generalization by leveraging internet-scale vision-language representations, but their massive computational cost creates a fundamental bottleneck: high inference latency. In dynamic environments, this latency breaks the control loop, rendering powerful models unsafe for real-time deployment. We propose AsyncVLA, an asynchronous control framework that decouples semantic reasoning from reactive execution. Inspired by hierarchical control, AsyncVLA runs a large foundation model on a remote workstation to provide high-level guidance, while a lightweight, onboard Edge Adapter continuously refines actions at high frequency. To bridge the domain gap between these asynchronous streams, we introduce an end-to-end finetuning protocol and a trajectory re-weighting strategy that prioritizes dynamic interactions. We evaluate our approach on real-world vision-based navigation tasks with communication delays up to 6 seconds. AsyncVLA achieves a 40% higher success rate than state-of-the-art baselines, effectively bridging the gap between the semantic intelligence of large models and the reactivity required for edge robotics.