TONAV：面向关节物体四足移动操作的任务导向导航与动作-速度块学习
TONAV: Task-Oriented Navigation and Action-Velocity Chunk Learning for Articulated Object Quadrupedal Mobile Manipulation
浏览论文内容
中文总结 AI 辅助
该研究针对四足移动操作中导航与操作的耦合问题，提出TONAV框架，结合任务导向导航与动作-速度块学习，通过遥操作、视觉语言推理及速度监督实现更优的操作性能。
中文摘要 AI 辅助
四足移动操作需要两种紧密耦合的能力：到达操作就绪配置，并在与关节物体交互过程中保持稳定接触。然而，现有方法常于目标附近终止导航，导致可达性与操作就绪性之间存在差距；同时，跟踪滞后、运动抖动及接触不稳定性限制了连续交互。为应对这些挑战，我们提出TONAV，这一整合任务导向导航与动作-速度块学习的统一框架。首先，我们引入位置-速度耦合遥操作框架，该框架明确捕捉运动动力学，以提升主从一致性并采集平滑、时间一致的演示数据。其次，任务导向导航利用视觉-语言推理将高层指令分解为可执行子目标，并自适应调整机器人基座至操作就绪配置。最后，动作-速度块学习在速度监督下联合建模关节位置及其时间转换，实现平滑且稳定的持续接触操作。针对各类关节物体任务的真实世界实验表明，TONAV在任务导向导航与完整移动操作中均达到更高成功率，缩小了导航-操作差距并改善了连续接触交互。项目页面位于此https URL。
英文摘要
Quadruped mobile manipulation requires two tightly coupled capabilities: reaching manipulation-ready configurations and maintaining stable contact throughout articulated-object interaction. However, existing methods often terminate navigation near the target, leaving a gap between reachability and manipulation readiness, while tracking lag, motion jitter, and contact instability limit continuous interaction. To address these challenges, we present TONAV, a unified framework integrating task-oriented navigation with action-velocity chunk learning. First, we introduce a position-velocity-coupled teleoperation framework that explicitly captures motion dynamics to improve master-follower consistency and collect smooth, temporally consistent demonstrations. Next, task-oriented navigation leverages vision-language reasoning to decompose high-level instructions into executable subgoals and adaptively refine the robot base toward a manipulation-ready configuration. Finally, action-velocity chunk learning jointly models joint positions and their temporal transitions under velocity supervision, enabling smooth and stable sustained-contact manipulation. Real-world experiments across diverse articulated-object tasks demonstrate that TONAV achieves higher success rates in both task-oriented navigation and complete mobile manipulation, mitigating the navigation-manipulation gap and improving continuous-contact interaction. The project page is at https://haochen611.github.io/TONAV.
发表机构
- School of Artificial Intelligence and Robotics, Hunan University（湖南大学人工智能与机器人学院）
- National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University（湖南大学机器人视觉感知与控制技术国家工程研究中心）
- College of Semiconductors (College of Integrated Circuits), Hunan University（湖南大学半导体学院（集成电路学院））
机构由 AI 辅助整理，请以论文原文为准。
