外观
论文arXiv 2610.1908213 天前
RH-NBV规划器解决严重遮挡感知，UR5e目标信息恢复率达63.8%
针对机器人主动感知中严重遮挡难题，研究提出滚动时域次佳视点（RH-NBV）规划器。该方法评估候选视点序列而非孤立视点，在UR5e机械臂实测中将重度遮挡下ROI覆盖率提升至63.8%，显著优于传统单步NBV基线。
Universal Robots UR5e本文由 AI 根据公开内容整理，可能有误，请以原文为准：Receding-Horizon Next-Best-View Planning for Highly Occluded Target Perception（arXiv 2610.19082）
核心内容
针对机器人获取特定目标信息时面临的严重遮挡问题，研究提出滚动时域次佳视点（RH-NBV）规划器，将局部目标感知建模为短时域顺序视点规划问题。该方法在仿真及物理UR5e机械臂上完成验证，测试对象包括受控遮挡下的咖啡杯、斯坦福兔及自然自遮挡番茄植株。实验数据显示，在最严重遮挡配置下，RH-NBV实现63.8%的ROI覆盖率与85.5%的遮挡表面召回率，而单步NBV基线仅分别为34.2%和7.4%。
技术方案核心在于评估未来视点序列而非基于即时效用的孤立视点，从而避免陷入局部最优。消融实验证实性能提升源于多步推理机制而非单纯计算量增加。系统采用眼在手（eye-in-hand）RGB-D相机架构，对比了梯度NBV规划器与随机搜索算法。研究表明RH-NBV在强遮挡场景优势显著，而在遮挡较少时传统短视NBV仍具成本竞争力，为复杂非结构化环境下的精细操作感知提供了新范式。
关键看点
- 序列规划机制：摒弃单步即时效用评估，采用滚动时域策略评估候选视点序列，通过多步推理解决严重遮挡下的感知盲区问题
- 量化性能突破：在UR5e物理实测最严重遮挡工况下，ROI覆盖率达63.8%，遮挡表面召回率85.5%，较单步NBV基线提升近12倍
- 归因验证结论：控制变量消融实验证实，感知性能提升源自多步时序推理逻辑，而非额外计算资源堆叠，验证了算法有效性
- 场景适用边界：强遮挡场景下RH-NBV优势显著，但在低遮挡环境中传统Myopic NBV仍保持竞争力且计算成本更低
工程与产业观察
该研究揭示了具身智能在非结构化环境中从“反应式感知”向“预测性感知”演进的技术路径。对于农业采摘、工业装配等存在严重自遮挡或环境遮挡的场景，引入短时域序列规划是提升感知完备性的关键工程手段，证明了在不依赖大模型前提下，通过优化传统几何规划逻辑即可大幅增强机器人在复杂物理世界中的自主信息获取能力。
英文摘要 (Abstract)
Robotic systems that must acquire information about a specific target often face severe occlusion from sur- rounding structures or from the target itself, such that a single camera viewpoint provides only partial information. Active perception must therefore select viewpoints that progressively reveal unobserved regions. However, conventional local next- best-view (NBV) methods typically select viewpoints according to their immediate utility, which can overlook views that provide limited information initially but enable more informative obser- vations from subsequent viewpoints. We formulated local target perception as a short-horizon sequential view-planning problem and proposed a Receding-Horizon Next-Best-View (RH-NBV) planner that evaluates candidate sequences of future viewpoints rather than isolated views. RH-NBV is evaluated on a UR5e manipulator with an eye-in-hand RGB-D camera in simulation as well as on physical robot against a gradient-based NBV planner, and random search, using a coffee mug and Stanford bunny under controlled occlusion and a tomato plant with natural self-occlusion. Under heavy occlusion, RH-NBV achieves substantially higher target information recovery, reaching 63.8% ROI coverage versus 34.2% and 85.5% occluded-surface recall versus 7.4% for the single-step NBV baselines on the most occluded mug configuration. A controlled horizon ablation shows that this improvement arises from multi-step reasoning rather than additional computation. RH-NBV provides the greatest benefit for strongly occluded targets, while myopic NBV remains competitive and substantially cheaper when visibility is less constrained.
作者：Ayse Gul Yildiz, Rekha Raja
来源
本页事实对应的公开页面，以原文为准。