Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Zhiyu, Zhang, Yun, Liu, Johnson, Song, Rui, Tang, Chen, Ma, Jiaqi
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2602.02459
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910272281640960
author Huang, Zhiyu
Zhang, Yun
Liu, Johnson
Song, Rui
Tang, Chen
Ma, Jiaqi
author_facet Huang, Zhiyu
Zhang, Yun
Liu, Johnson
Song, Rui
Tang, Chen
Ma, Jiaqi
contents Robots in dynamic, human-centric environments must follow language instructions while maintaining real-time reactive control. Vision-language-action (VLA) models offer a promising framework, but they assume temporally aligned reasoning and control, despite semantic inference being inherently delayed relative to real-time action. We introduce Think-in-Control (TIC)-VLA, a latency-aware framework that explicitly models delayed semantic reasoning during action generation. TIC-VLA defines a delayed semantic-control interface that conditions action generation on delayed vision-language semantic states and explicit latency metadata, in addition to current observations, enabling policies to compensate for asynchronous reasoning. We further propose a latency-consistent training pipeline that injects reasoning inference delays during imitation learning and online reinforcement learning, aligning training with asynchronous deployment. To support realistic evaluation, we present DynaNav, a physics-accurate, photo-realistic simulation suite for language-guided navigation in dynamic environments. Extensive experiments in simulation and on a real robot show that TIC-VLA consistently outperforms prior VLA models while maintaining robust real-time control under multi-second reasoning latency. Project website: https://ucla-mobility.github.io/TIC-VLA/
format Preprint
id arxiv_https___arxiv_org_abs_2602_02459
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments
Huang, Zhiyu
Zhang, Yun
Liu, Johnson
Song, Rui
Tang, Chen
Ma, Jiaqi
Robotics
Robots in dynamic, human-centric environments must follow language instructions while maintaining real-time reactive control. Vision-language-action (VLA) models offer a promising framework, but they assume temporally aligned reasoning and control, despite semantic inference being inherently delayed relative to real-time action. We introduce Think-in-Control (TIC)-VLA, a latency-aware framework that explicitly models delayed semantic reasoning during action generation. TIC-VLA defines a delayed semantic-control interface that conditions action generation on delayed vision-language semantic states and explicit latency metadata, in addition to current observations, enabling policies to compensate for asynchronous reasoning. We further propose a latency-consistent training pipeline that injects reasoning inference delays during imitation learning and online reinforcement learning, aligning training with asynchronous deployment. To support realistic evaluation, we present DynaNav, a physics-accurate, photo-realistic simulation suite for language-guided navigation in dynamic environments. Extensive experiments in simulation and on a real robot show that TIC-VLA consistently outperforms prior VLA models while maintaining robust real-time control under multi-second reasoning latency. Project website: https://ucla-mobility.github.io/TIC-VLA/
title TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments
topic Robotics
url https://arxiv.org/abs/2602.02459