Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.03998 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915916729548800 |
|---|---|
| author | Zhang, Yang Jing, Shengxi Wang, Fengxiang Feng, Yuan Wang, Hong |
| author_facet | Zhang, Yang Jing, Shengxi Wang, Fengxiang Feng, Yuan Wang, Hong |
| contents | Interpreting dynamic, heterogeneous multimedia commands with real-time responsiveness is critical for Human-Robot Interaction. We present VA-FastNavi-MARL, a framework that aligns asynchronous audio-visual inputs into a unified latent representation. By treating diverse instructions as a distribution of navigable goals via Meta-Reinforcement Learning, our method enables rapid adaptation to unseen directives with negligible inference overhead. Unlike approaches bottlenecked by heavy sensory processing, our modality-agnostic stream ensures seamless, low-latency control. Validation on a multi-arm workspace confirms that VA-FastNavi-MARL significantly outperforms baselines in sample efficiency and maintains robust, real-time execution even under noisy multimedia streams. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03998 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VA-FastNavi-MARL: Real-Time Robot Control with Multimedia-Driven Meta-Reinforcement Learning Zhang, Yang Jing, Shengxi Wang, Fengxiang Feng, Yuan Wang, Hong Robotics Interpreting dynamic, heterogeneous multimedia commands with real-time responsiveness is critical for Human-Robot Interaction. We present VA-FastNavi-MARL, a framework that aligns asynchronous audio-visual inputs into a unified latent representation. By treating diverse instructions as a distribution of navigable goals via Meta-Reinforcement Learning, our method enables rapid adaptation to unseen directives with negligible inference overhead. Unlike approaches bottlenecked by heavy sensory processing, our modality-agnostic stream ensures seamless, low-latency control. Validation on a multi-arm workspace confirms that VA-FastNavi-MARL significantly outperforms baselines in sample efficiency and maintains robust, real-time execution even under noisy multimedia streams. |
| title | VA-FastNavi-MARL: Real-Time Robot Control with Multimedia-Driven Meta-Reinforcement Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2604.03998 |