用3D点云分析环境，实时识别抓握场景并定位可抓物体
Point Cloud Context Analysis for Rehabilitation Grasping Assistance
- 通过3D点云分析环境几何，识别预设的抓握模式
- 分类准确率超85%，处理速度达30帧/秒，抓点误差平均小于1厘米
- 适合康复机器人和日常任务辅助，硬件成本低、响应快
控制外骨骼手助力残障患者完成抓握任务极具挑战性，主要难点在于难以推断用户意图。我们假设大多数日常抓握行为属于有限的几类模式，可通过实时分析3D点云中的环境几何信息进行推断。本文提出一种低成本、实时的家用场景语义标注系统，旨在支持日常生活活动的辅助决策。系统由微型深度相机、惯性测量单元和微处理器组成，能在处理复杂3D场景时实现超过30帧/秒的运行速度，对预定义抓握模式的分类准确率高达85%以上。在每种模式下，系统可检测并定位可抓取物体，对于简单几何物体，抓握点估计平均误差小于1厘米。该系统在机器人辅助康复及手动任务协助方面具有应用潜力。
原文摘要 · Abstract (English)
Controlling hand exoskeletons for assisting impaired patients in grasping tasks is challenging because it is difficult to infer user intent. We hypothesize that majority of daily grasping tasks fall into a small set of categories or modes which can be inferred through real-time analysis of environmental geometry from 3D point clouds. This paper presents a low-cost, real-time system for semantic image labeling of household scenes with the objective to inform and assist activities of daily living. The system consists of a miniature depth camera, an inertial measurement unit and a microprocessor. It is able to achieve 85% or higher accuracy at classification of predefined modes while processing complex 3D scenes at over 30 frames per second. Within each mode it can detect and localize graspable objects. Grasping points can be correctly estimated on average within 1 cm for simple object geometries. The system has potential applications in robotic-assisted rehabilitation as well as manual task assistance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。