Robot arm pose prediction method based on image gradient vector mapping

Table 1. Robot arm motion parameters for the generation of image set
View table
View in Article
Table 1. Robot arm motion parameters for the generation of image set
关节运动范围/(°) 记录间隔/(°) 记录点位/个转动顺序
底关节 −90～90 5 36 3
肘关节 −90～90 3 60 2
腕关节 −90～90 2 90 1

Table 2. HOG parameters for calculation
View table
View in Article
Table 2. HOG parameters for calculation
参数数值
输入图像分辨率/px $48 \times 48$
Cell/px $1 \times 1$
Stride/px 4
Block/px $4 \times 4$
梯度方向划分数/个 9

Table 3. Overall evaluation of joint angle prediction results of test image set
View table
View in Article
Table 3. Overall evaluation of joint angle prediction results of test image set
关节 ${\theta _{\rm{RMSE}}}$/(°) ${\theta _{\rm{MAE}}}$/(°) ${\theta _{\rm{MAXE}}}$/(°)
底关节 1.49 1.72 5.66
肘关节 2.04 3.47 9.72
腕关节 2.25 3.58 10.87
平均值 1.93 2.92 8.75

Table 4. Comparison of joint angle prediction errors based on test image set
View table
View in Article
Table 4. Comparison of joint angle prediction errors based on test image set
关节关节角度预报误差/(°)
本文算法 DREAM^[5] CRAVES^[7]
底关节 1.72 3.76 4.63
肘关节 3.47 3.95 4.35
腕关节 3.58 4.38 5.13
平均值 2.92 4.03 4.70

Tools

Get Citation

Copy Citation Text

Yuhang DING, Zhen CHEN. Robot arm pose prediction method based on image gradient vector mapping[J]. Chinese Journal of Ship Research, 2023, 18(5): 251

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites