论文arXiv 2611.0889813 天前
FATHOM框架:世界模型引导扩散策略实现稀疏标记AUV鲁棒跟踪
本文由 AI 根据公开内容整理,可能有误,请以原文为准:FATHOM: World-Model-Guided Diffusion Action-Trajectory Selection for Sparse-Marker AUV Tracking(arXiv 2611.08898)
核心内容
针对合作式自主水下机器人(AUV)在非线性动力学及水下视觉退化环境下的相对跟踪难题,论文提出FATHOM框架。该方法旨在解决主动光标记因遮挡、反射及检测噪声导致的稀疏观测与部分观测控制问题,通过世界模型引导的扩散动作-轨迹选择机制,在无需外部动作捕捉反馈的条件下,实现了真实AUV平台上的实时鲁棒自主跟踪。
技术上,FATHOM利用多模态任务监督循环状态空间模型,融合结构化标记、惯性测量及历史动作构建预测信念;采用扩散动作先验生成多推力器专家轨迹,并通过学习的潜空间动力学预测未来跟踪后果。系统基于显式滚动时域目标函数从候选轨迹中择优执行,并根据机载观测持续更新决策。真机实验验证了其在自然部分标记可见及强动态运动下的有效性,且满足实时 onboard 运行要求。
关键看点
- 感知融合:集成结构化标记、IMU及动作历史至多模态循环状态空间模型,构建应对稀疏观测的预测跟踪信念
- 轨迹生成:利用扩散动作先验生成多推力器专家级轨迹,结合潜空间动力学预测未来状态以评估跟踪后果
- 决策优化:采用显式滚动时域目标函数进行轨迹择优,支持基于机载实时观测的在线决策更新与闭环控制
- 实测验证:在无动捕反馈的真机实验中,验证了自然部分标记可见及挑战性运动下的实时自主跟踪鲁棒性
工程与产业观察
该工作为具身智能在极端感知受限环境下的控制提供了新范式。通过将世界模型预测能力与扩散策略生成能力解耦再融合,有效解决了水下非结构化环境中“看不清”与“控不准”的耦合难题。其基于潜空间动力学的轨迹评估机制,对陆地机器人在烟雾、暗光等视觉退化场景下的安全导航与操作具有直接工程参考价值。
英文摘要 (Abstract)
Reliable relative tracking is fundamental to cooperative autonomous underwater vehicles (AUVs), yet remains challenging under nonlinear vehicle dynamics and degraded underwater visual conditions. Active light markers improve robustness to appearance variation, but provide deliberately sparse observations that can become incomplete or corrupted by occlusion, reflections, and detection noise during dynamic motion. To address the resulting partial-observation control problem, this paper proposes FATHOM, a world-model-guided diffusion action-trajectory selection framework for sparse-marker AUV tracking. FATHOM first integrates structured marker observations, inertial measurements, action history, and temporal dynamics into a predictive tracking belief using a multimodal task-supervised recurrent state-space model. A diffusion action prior then generates multiple expert-like multi-thruster trajectories, whose future tracking consequences are predicted through the learned latent dynamics. Rather than directly executing a generated trajectory, FATHOM selects the most favorable candidate under an explicit receding-horizon objective and continually updates the decision from onboard observations. Extensive offline analyses verify the learned predictive belief, multi-step world-model prediction, diffusion trajectory generation, and predictive selection. More importantly, comprehensive real-AUV experiments, including strong pose-based comparisons and component ablations, demonstrate robust autonomous tracking across nominal and challenging motions with naturally occurring partial marker visibility, while maintaining real-time onboard operation without motion-capture feedback.
作者:Xiaorui Wang, Zeyu Sha, Mingyang Yang, David Chen Wang, Feitian Zhang
外部来源
本页事实对应的公开页面,以原文为准。(点击将离开本站)