Prediction of Human Trajectory following a Haptic Robotic Guide Using Recurrent Neural Networks

Hee Seung Moon, Jiwon Seo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Social intelligence is an important requirement for enabling robots to collaborate with people. In particular, human path prediction is an essential capability for robots in that it prevents potential collision with a human and allows the robot to safely make larger movements. In this paper, we present a method for predicting the trajectory of a human who follows a haptic robotic guide without using sight, which is valuable for assistive robots that aid the visually impaired. We apply a deep learning method based on recurrent neural networks using multimodal data: (1) human trajectory, (2) movement of the robotic guide, (3) haptic input data measured from the physical interaction between the human and the robot, (4) human depth data. We collected actual human trajectory and multimodal response data through indoor experiments. Our model outperformed the baseline result while using only the robot data with the observed human trajectory, and it shows even better results when using additional haptic and depth data.

Original languageEnglish
Title of host publication2019 IEEE World Haptics Conference, WHC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages157-162
Number of pages6
ISBN (Electronic)9781538694619
DOIs
Publication statusPublished - 2019 Jul
Event2019 IEEE World Haptics Conference, WHC 2019 - Tokyo, Japan
Duration: 2019 Jul 92019 Jul 12

Publication series

Name2019 IEEE World Haptics Conference, WHC 2019

Conference

Conference2019 IEEE World Haptics Conference, WHC 2019
CountryJapan
CityTokyo
Period19/7/919/7/12

Fingerprint

Recurrent neural networks
Robotics
robot
neural network
Trajectories
Robots
learning method
Emotional Intelligence
intelligence
experiment
Learning
interaction
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Human-Computer Interaction
  • Biomedical Engineering
  • Sensory Systems
  • Human Factors and Ergonomics

Cite this

Moon, H. S., & Seo, J. (2019). Prediction of Human Trajectory following a Haptic Robotic Guide Using Recurrent Neural Networks. In 2019 IEEE World Haptics Conference, WHC 2019 (pp. 157-162). [8816157] (2019 IEEE World Haptics Conference, WHC 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WHC.2019.8816157
Moon, Hee Seung ; Seo, Jiwon. / Prediction of Human Trajectory following a Haptic Robotic Guide Using Recurrent Neural Networks. 2019 IEEE World Haptics Conference, WHC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 157-162 (2019 IEEE World Haptics Conference, WHC 2019).
@inproceedings{3227f4b0fd014f75a6ae1ab678fb4efd,
title = "Prediction of Human Trajectory following a Haptic Robotic Guide Using Recurrent Neural Networks",
abstract = "Social intelligence is an important requirement for enabling robots to collaborate with people. In particular, human path prediction is an essential capability for robots in that it prevents potential collision with a human and allows the robot to safely make larger movements. In this paper, we present a method for predicting the trajectory of a human who follows a haptic robotic guide without using sight, which is valuable for assistive robots that aid the visually impaired. We apply a deep learning method based on recurrent neural networks using multimodal data: (1) human trajectory, (2) movement of the robotic guide, (3) haptic input data measured from the physical interaction between the human and the robot, (4) human depth data. We collected actual human trajectory and multimodal response data through indoor experiments. Our model outperformed the baseline result while using only the robot data with the observed human trajectory, and it shows even better results when using additional haptic and depth data.",
author = "Moon, {Hee Seung} and Jiwon Seo",
year = "2019",
month = "7",
doi = "10.1109/WHC.2019.8816157",
language = "English",
series = "2019 IEEE World Haptics Conference, WHC 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "157--162",
booktitle = "2019 IEEE World Haptics Conference, WHC 2019",
address = "United States",

}

Moon, HS & Seo, J 2019, Prediction of Human Trajectory following a Haptic Robotic Guide Using Recurrent Neural Networks. in 2019 IEEE World Haptics Conference, WHC 2019., 8816157, 2019 IEEE World Haptics Conference, WHC 2019, Institute of Electrical and Electronics Engineers Inc., pp. 157-162, 2019 IEEE World Haptics Conference, WHC 2019, Tokyo, Japan, 19/7/9. https://doi.org/10.1109/WHC.2019.8816157

Prediction of Human Trajectory following a Haptic Robotic Guide Using Recurrent Neural Networks. / Moon, Hee Seung; Seo, Jiwon.

2019 IEEE World Haptics Conference, WHC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 157-162 8816157 (2019 IEEE World Haptics Conference, WHC 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Prediction of Human Trajectory following a Haptic Robotic Guide Using Recurrent Neural Networks

AU - Moon, Hee Seung

AU - Seo, Jiwon

PY - 2019/7

Y1 - 2019/7

N2 - Social intelligence is an important requirement for enabling robots to collaborate with people. In particular, human path prediction is an essential capability for robots in that it prevents potential collision with a human and allows the robot to safely make larger movements. In this paper, we present a method for predicting the trajectory of a human who follows a haptic robotic guide without using sight, which is valuable for assistive robots that aid the visually impaired. We apply a deep learning method based on recurrent neural networks using multimodal data: (1) human trajectory, (2) movement of the robotic guide, (3) haptic input data measured from the physical interaction between the human and the robot, (4) human depth data. We collected actual human trajectory and multimodal response data through indoor experiments. Our model outperformed the baseline result while using only the robot data with the observed human trajectory, and it shows even better results when using additional haptic and depth data.

AB - Social intelligence is an important requirement for enabling robots to collaborate with people. In particular, human path prediction is an essential capability for robots in that it prevents potential collision with a human and allows the robot to safely make larger movements. In this paper, we present a method for predicting the trajectory of a human who follows a haptic robotic guide without using sight, which is valuable for assistive robots that aid the visually impaired. We apply a deep learning method based on recurrent neural networks using multimodal data: (1) human trajectory, (2) movement of the robotic guide, (3) haptic input data measured from the physical interaction between the human and the robot, (4) human depth data. We collected actual human trajectory and multimodal response data through indoor experiments. Our model outperformed the baseline result while using only the robot data with the observed human trajectory, and it shows even better results when using additional haptic and depth data.

UR - http://www.scopus.com/inward/record.url?scp=85072771019&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072771019&partnerID=8YFLogxK

U2 - 10.1109/WHC.2019.8816157

DO - 10.1109/WHC.2019.8816157

M3 - Conference contribution

AN - SCOPUS:85072771019

T3 - 2019 IEEE World Haptics Conference, WHC 2019

SP - 157

EP - 162

BT - 2019 IEEE World Haptics Conference, WHC 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Moon HS, Seo J. Prediction of Human Trajectory following a Haptic Robotic Guide Using Recurrent Neural Networks. In 2019 IEEE World Haptics Conference, WHC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 157-162. 8816157. (2019 IEEE World Haptics Conference, WHC 2019). https://doi.org/10.1109/WHC.2019.8816157