Hostname: page-component-7b7567c8c-wxvwp Total loading time: 0 Render date: 2026-11-17T11:33:44.983Z Has data issue: false hasContentIssue false

Imitation of human motion for humanoid robot in lift and carry event

Published online by Cambridge University Press:  03 December 2019

Shu-Yin Chiang
Affiliation:
Department of Information and Telecommunications Engineering, Ming Chuan University, 5 De Ming Road, Gui Shan District, Taoyuan City 333, Taiwan; e-mail: sychiang@mail.mcu.edu.tw
Hao-Ge Jiang
Affiliation:
School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, 639798, Singapore; e-mail: haoge001@ntu.edu.sg
Rights & Permissions [Opens in a new window]

Abstract

This study proposed a method to enable a humanoid robot to step up onto a stair by imitating the step-up motion of a human and to accomplish a lift and carry event in HuroCup of Federation of International RoboSports Association. The step-up motion, divided into five states, was captured by a Kinect sensor, and the human joints corresponded to the humanoid robot joints. Selected servomotors and their angle variation were matched with that of human joint numbers by a designed fuzzy inference system on the basis between the human and the humanoid robot joints. Then, the rest of the robot motors were adjusted by the zero moment point obtained from force-sensing registers to maintain stability. Next, two intermediate transition states were added between each state of the humanoid robot step-up to maintain its balance and reduce motor damage. Finally, to be applied in a real lift and carry event, a vision system was integrated to recognize the edge of a color board and determine a suitable site for the step-up. With these functions integrated, the robot under the proposed method was verified to successfully achieve the task of the lift and carry event without losing its balance or falling.

Information

Type
Robot Athletes and Entertainers
Copyright
© Cambridge University Press, 2019 
Figure 0

Figure 1Schematic of the DARwIn-OP servomotor numerically assigned positions

Figure 1

Table 1DWRwIn-OP servomotor ID position and angle.

Figure 2

Figure 2Photograph of the robot performing the lift and carry event

Figure 3

Figure 3Twenty human skeletal joints captured by the Kinect. (a) Skeletal joints. (b) Kinect image

Figure 4

Figure 4Five states of the human step-up motion from the side view

Figure 5

Figure 5Five states of the human step-up motion from the front view

Figure 6

Figure 6Five states of the human step-up motion from the top view

Figure 7

Figure 7Schematic showing the angle calculation

Figure 8

Table 2Angles of human step-up motion for the five stages.

Figure 9

Figure 8Membership functions for each input Xi

Figure 10

Figure 9Membership functions for each output Yi

Figure 11

Figure 10Designed ID angle variation for the human and robot step-up motion

Figure 12

Figure 11Definition of FSR values and the stable region for the DARwIn-OP humanoid

Figure 13

Figure 12Flowchart showing how to adjust the robot position to be stable according to the ZMP

Figure 14

Table 3ZMP adjustment for Figure 12

Figure 15

Figure 13Adding transition steps in the robot’s motion to maintain balance

Figure 16

Figure 14The relationship between pixels versus dimension

Figure 17

Figure 15The robot tries to find the edge of the color board

Figure 18

Figure 16Experimental result of the proposed algorithm from imitation of human motion. (a) State S1. (b) State Sa1→2. (c) State Sb1→2. (d) State S2. (e) State Sa2→3. (f) State Sb2→3. (g) State S3. (h) State Sa3→4. (i) State Sb3→4. (j) State S4. (k) State Sa4→5. (l) State Sb4→5. (m) State S5

Figure 19

Figure 17FSR results of the proposed algorithm from imitation. (a) State S1. (b) State Sa1→2. (c) State Sb1→2. (d) State S2. (e) State Sa2→3. (f) State Sb2→3. (g) State S3. (h) State Sa3→4. (i) State Sb3→4. (j) State S4. (k) State Sa4→5. (l) State Sb4→5. (m) State S5

Figure 20

Figure 18FSR and ZMP for all states

Figure 21

Figure 19Experimental result of the proposed algorithm with the vision system