VP-EVT:用于具身视觉跟踪的主动可见性保持
VP-EVT: Active Visibility Preservation for Embodied Visual Tracking
AI总结:
针对具身视觉跟踪中动态场景行人遮挡导致目标丢失的问题,提出VP-EVT框架,结合语言引导感知与循环控制器保持目标可见性,在OccEVT-Bench上大幅提升跟踪性能。
摘要:
具身视觉跟踪(Embodied Visual Tracking, EVT)是人机协作中智能机器人的核心能力,要求智能体仅依靠自我中心视觉感知在动态环境中跟随指定目标行人。然而,动态场景中持续的行人遮挡对现有EVT方法构成关键挑战:缺乏主动可见性保持的反应式跟踪方法在严重遮挡下常出现长时间目标丢失。因此,本文提出VP-EVT框架,将目标可见性视为运动控制的显式目标而非跟随的副产物。实现该目标需同时理解遮挡目标的物体以及机器人运动如何改变遮挡状态,故VP-EVT采用语言引导感知提取独立的目标与行人观测;当遮挡导致当前观测不完整时,VP-EVT结合视觉历史与自我运动维持对目标和行人相对位置及运动的估计;利用这些估计与当前跟随路径点,VP-EVT预测持续跟随是否会维持遮挡,若预测风险低则保留原跟随运动,否则循环控制器结合更新后的估计与先前决策的机动上下文,协调视角调整与返回稳定跟随的动作。此外,本文引入用于持续遮挡闭环评估的OccEVT-Bench,并收集专家演示用于训练;在其Risk划分上,VP-EVT相较竞争基线将成功率提升121.4%,可见性 deficit 降低78.8%,最长目标丢失时长缩短74.4%。
英文摘要:
Embodied Visual Tracking (EVT) is an essential capability for intelligent robots in human-robot collaboration, requiring an agent to follow a designated target person in dynamic environments relying solely on egocentric visual perception. However, persistent pedestrian occlusions in dynamic scenes pose critical challenges to existing EVT methods. Lacking proactive visibility preservation, reactive tracking methods frequently experience prolonged target loss under severe occlusions. Therefore, we propose VP-EVT, a framework that treats target visibility as an explicit objective of motion control rather than a by-product of following. Acting on this objective requires understanding both what obstructs the target and how robot motion can change that obstruction. VP-EVT therefore uses language-guided perception to extract separate target and pedestrian observations. When occlusion makes current observations incomplete, VP-EVT combines visual history with ego-motion to maintain estimates of their relative positions and motion. Using these estimates and the current following waypoints, VP-EVT predicts whether continued following will sustain the obstruction. When the predicted risk is low, the original following motion is retained; otherwise, a recurrent controller combines updated estimates with maneuver context from preceding decisions to coordinate viewpoint adjustment and the return to stable following. Moreover, we introduce OccEVT-Bench for closed-loop evaluation of persistent occlusion and collect expert demonstrations for training. On its Risk split, VP-EVT improves success rate by 121.4% relative to a competitive baseline and reduces visibility deficit and longest target-loss duration by 78.8% and 74.4%, respectively.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。