Optimal Collision-Free Robot Trajectory Generation Based on Time Series Prediction of Human Motion

Yiwei Wang, Yixuan Sheng, Ji Wang, Wenlong Zhang

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In this letter, we propose that the joint motion of a human worker doing repetitive work could be predicted using a time series model. With a motion capture system, the elbow joint rotation data are collected and used to fit an autoregressive model. An online parameter adaptation algorithm is employed to update model parameters in real time. A safety index with a distance factor is defined to describe the level of safety during physical human-robot interaction. An optimization problem is formulated to generate a collision-free trajectory for the manipulator based on human motion prediction to make the generated trajectory smoother. Planar and three-dimensional simulations are conducted to validate the efficacy of the algorithm by comparing the trajectories with and without real-Time human motion prediction. Experiments are conducted on a 6-DOF manipulator Universal Robots UR5 with a Microsoft Kinect sensor (ver. 1). The optimization problem can be solved within the sampling time of the system, which suggests this algorithm can be applied in real-Time trajectory generation. The trajectories generated with different control horizons are compared, and the results show that the manipulator can achieve the goal faster via a smoother trajectory with the help of human motion prediction.

Original languageEnglish (US)
Article number8004480
Pages (from-to)226-233
Number of pages8
JournalIEEE Robotics and Automation Letters
Volume3
Issue number1
DOIs
StatePublished - Jan 1 2018

Fingerprint

Trajectory Generation
Time Series Prediction
Time series
Collision
Robot
Trajectories
Robots
Trajectory
Manipulator
Motion
Manipulators
Prediction
Safety
Parameter Adaptation
Optimization Problem
Real-time
Human-robot Interaction
Motion Capture
Time Series Models
Autoregressive Model

Keywords

  • Collision avoidance
  • motion and path planning
  • optimization and optimal control
  • physical human-robot interaction
  • robot safety

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Human-Computer Interaction
  • Biomedical Engineering
  • Mechanical Engineering
  • Control and Optimization
  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Optimal Collision-Free Robot Trajectory Generation Based on Time Series Prediction of Human Motion. / Wang, Yiwei; Sheng, Yixuan; Wang, Ji; Zhang, Wenlong.

In: IEEE Robotics and Automation Letters, Vol. 3, No. 1, 8004480, 01.01.2018, p. 226-233.

Research output: Contribution to journalArticle

@article{c6ab4be48c3044c7b92d80cf60184c79,
title = "Optimal Collision-Free Robot Trajectory Generation Based on Time Series Prediction of Human Motion",
abstract = "In this letter, we propose that the joint motion of a human worker doing repetitive work could be predicted using a time series model. With a motion capture system, the elbow joint rotation data are collected and used to fit an autoregressive model. An online parameter adaptation algorithm is employed to update model parameters in real time. A safety index with a distance factor is defined to describe the level of safety during physical human-robot interaction. An optimization problem is formulated to generate a collision-free trajectory for the manipulator based on human motion prediction to make the generated trajectory smoother. Planar and three-dimensional simulations are conducted to validate the efficacy of the algorithm by comparing the trajectories with and without real-Time human motion prediction. Experiments are conducted on a 6-DOF manipulator Universal Robots UR5 with a Microsoft Kinect sensor (ver. 1). The optimization problem can be solved within the sampling time of the system, which suggests this algorithm can be applied in real-Time trajectory generation. The trajectories generated with different control horizons are compared, and the results show that the manipulator can achieve the goal faster via a smoother trajectory with the help of human motion prediction.",
keywords = "Collision avoidance, motion and path planning, optimization and optimal control, physical human-robot interaction, robot safety",
author = "Yiwei Wang and Yixuan Sheng and Ji Wang and Wenlong Zhang",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/LRA.2017.2737486",
language = "English (US)",
volume = "3",
pages = "226--233",
journal = "IEEE Robotics and Automation Letters",
issn = "2377-3766",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Optimal Collision-Free Robot Trajectory Generation Based on Time Series Prediction of Human Motion

AU - Wang, Yiwei

AU - Sheng, Yixuan

AU - Wang, Ji

AU - Zhang, Wenlong

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In this letter, we propose that the joint motion of a human worker doing repetitive work could be predicted using a time series model. With a motion capture system, the elbow joint rotation data are collected and used to fit an autoregressive model. An online parameter adaptation algorithm is employed to update model parameters in real time. A safety index with a distance factor is defined to describe the level of safety during physical human-robot interaction. An optimization problem is formulated to generate a collision-free trajectory for the manipulator based on human motion prediction to make the generated trajectory smoother. Planar and three-dimensional simulations are conducted to validate the efficacy of the algorithm by comparing the trajectories with and without real-Time human motion prediction. Experiments are conducted on a 6-DOF manipulator Universal Robots UR5 with a Microsoft Kinect sensor (ver. 1). The optimization problem can be solved within the sampling time of the system, which suggests this algorithm can be applied in real-Time trajectory generation. The trajectories generated with different control horizons are compared, and the results show that the manipulator can achieve the goal faster via a smoother trajectory with the help of human motion prediction.

AB - In this letter, we propose that the joint motion of a human worker doing repetitive work could be predicted using a time series model. With a motion capture system, the elbow joint rotation data are collected and used to fit an autoregressive model. An online parameter adaptation algorithm is employed to update model parameters in real time. A safety index with a distance factor is defined to describe the level of safety during physical human-robot interaction. An optimization problem is formulated to generate a collision-free trajectory for the manipulator based on human motion prediction to make the generated trajectory smoother. Planar and three-dimensional simulations are conducted to validate the efficacy of the algorithm by comparing the trajectories with and without real-Time human motion prediction. Experiments are conducted on a 6-DOF manipulator Universal Robots UR5 with a Microsoft Kinect sensor (ver. 1). The optimization problem can be solved within the sampling time of the system, which suggests this algorithm can be applied in real-Time trajectory generation. The trajectories generated with different control horizons are compared, and the results show that the manipulator can achieve the goal faster via a smoother trajectory with the help of human motion prediction.

KW - Collision avoidance

KW - motion and path planning

KW - optimization and optimal control

KW - physical human-robot interaction

KW - robot safety

UR - http://www.scopus.com/inward/record.url?scp=85042928681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042928681&partnerID=8YFLogxK

U2 - 10.1109/LRA.2017.2737486

DO - 10.1109/LRA.2017.2737486

M3 - Article

AN - SCOPUS:85042928681

VL - 3

SP - 226

EP - 233

JO - IEEE Robotics and Automation Letters

JF - IEEE Robotics and Automation Letters

SN - 2377-3766

IS - 1

M1 - 8004480

ER -