From Simulation to the Real-World: An In-Field 6D Pose Dataset and Baseline for Robotic Strawberry Harvesting
从仿真到现实:面向机器人草莓采摘的实地6D位姿数据集与基线
Woojung Son (1), Won Suk Lee (1), Zijing Huang (1), Daeun Choi (1), Catia Silva (2), Yu She (3), Yan Gu (4) ((1) Department of Agricultural and Biological Engineering, University of Florida, (2) Department of Electrical and Computer Engineering, University of Florida, (3) Edwardson School of Industrial Engineering, Purdue University, (4) School of Mechanical Engineering, Purdue University)
机构
*
Department of Agricultural and Biological Engineering, University of Florida(佛罗里达大学农业与生物工程系)
;
Department of Electrical and Computer Engineering, University of Florida(佛罗里达大学电气与计算机工程系)
;
Edwardson School of Industrial Engineering, Purdue University(普渡大学爱德华森工业工程学院)
;
School of Mechanical Engineering, Purdue University(普渡大学机械工程学院)
专题命中
机器人数据与评测
:robotic(title,abstract);分类 cs.CV
AI总结
针对机器人草莓采摘中6D位姿估计的仿真到现实差距问题,首次构建了实地草莓6D位姿真值数据集(12,040张图像),并基于NVIDIA Isaac Sim生成具有场景级真实感的合成数据集,通过基线实验量化了差距。