TIC-VLA：一种适用于动态环境机器人导航的思维控制视觉语言动作模型

摘要

在动态且以人为中心的环境中工作的机器人，必须遵循语言指令同时保持实时反应控制。视觉-语言-动作模型为此提供了前景广阔的框架，但这些模型假设推理与控制具有时间对齐性，而实际上语义推理相对于实时动作存在固有延迟。我们提出延迟感知框架TIC-VLA，该框架在动作生成过程中显式建模延迟语义推理。TIC-VLA定义了延迟语义控制接口，除了当前观测值外，还将动作生成条件设定于延迟的视觉语言语义状态和显式延迟元数据，使策略能够补偿异步推理。我们进一步提出延迟一致性训练流程，在模仿学习和在线强化学习中注入推理延迟，实现训练与异步部署的对齐。为支持真实评估，我们开发了DynaNav——一个物理精确、照片级真实的仿真套件，用于动态环境中的语言引导导航。大量仿真和实体机器人实验表明，TIC-VLA在保持数秒推理延迟下鲁棒实时控制的同时，持续优于现有VLA模型。项目网站：https://ucla-mobility.github.io/TIC-VLA/

English

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/

TIC-VLA：一种适用于动态环境机器人导航的思维控制视觉语言动作模型

TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments

摘要

Support