让机器人听懂人话追目标：先指认再跟踪
现在的机器人视觉跟踪，要么靠人预先指定目标，要么只能跟固定物体。这篇让机器人先听懂自然语言描述（比如“追那个穿红衣服的人”），从画面中框出目标，再持续跟踪。关键是把“指认”和“跟踪”拆成两步：先选框，再基于框的位置规划路径，而不是像之前那样在抽象空间里瞎猜。在测试中，单摄像头就能达到89.4%的成功率，甚至超过一些多摄像头方案。它不是你明天就能用的产品，但指明了让机器人更听话、更可靠的方向——先确认“你指的是谁”，再行动。
📄 原文摘要(英文)
Embodied visual tracking (EVT) requires a mobile agent to continuously follow a specific target described in natural language using only onboard vision. While recent vision-language-action (VLA) policies unify target identification and trajectory planning, their chain-of-thought (CoT) reasoning often operates in abstract spatial latents that are difficult to supervise and weakly aligned with explicit image-space detections. To address this, we introduce ReferTrack, a referring-then-tracking paradigm that grounds EVT using a single forward-facing camera. Our model first selects the target from an indexed set of bounding boxes, then decodes tracking waypoints conditioned on this image-grounded decision. To preserve target motion cues over time, ReferTrack maintains a sliding-window queue of previously selected bounding boxes, injecting their geometric features into the visual history via temporal-viewpoint-bbox indicator (TVBI) tokens. We further enhance target identification by co-training on a custom Refer-QA dataset. On EVT-Bench, ReferTrack achieves state-of-the-art single-view performance with success rates of 89.4%, 73.3%, and 74.1% on the single-target, distracted, and ambiguity tracking splits, respectively -- matching or even surpassing several multi-camera baselines on identification-heavy tasks. Finally, real-world deployments on legged and humanoid robots validate its robust sim-to-real transfer capabilities. Code is available at https://github.com/MedlarTea/referTrack.