Predicting a Pedestrian Trajectory Using Seq2Seq for Mobile Robot Navigation

被引：0

作者：

Sakata, Natsuki ^{[1
]}

Kinoshita, Yuka ^{[1
]}

Kato, Yuka ^{[1
]}

机构：

[1] Tokyo Womans Christian Univ, Devis Math Sci, Tokyo, Japan

来源：

IECON 2018 - 44TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY | 2018年

关键词：

seq2seq; pedestrian model; trajectory prediction; mobile robot; path planning;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper proposes a method to predict the future trajectory of a pedestrian as sequence data by using massive trajectory records collected by various sensor devices. We aim to use the method for safely and efficient path planning of autonomous mobile robots in a human-robot coexisting environment. For the prediction, we use a sequence-to-sequence model, which is frequently used in the field of natural language processing and enables to treat long-term sequence data. In order to verify the effectiveness of the proposed method, we conduct experiments using a dataset of tracking pedestrians at a shopping mall. The result shows that our method can predict sequences sufficiently by converting the trajectory data to adequate sequence data.

引用

页码：4300 / 4305

页数：6

共 12 条

[1] Social LSTM: Human Trajectory Prediction in Crowded Spaces [J].

Alahi, Alexandre ;

Goel, Kratarth ;

Ramanathan, Vignesh ;

Robicquet, Alexandre ;

Li Fei-Fei ;

Savarese, Silvio .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :961-971

[2]

[Anonymous], 2014, ADV NEURAL INFORM PR, DOI DOI 10.1007/S10107-014-0839-0

[3] Robot Guided Crowd Evacuation [J].

Boukas, Evangelos ;

Kostavelis, Ioannis ;

Gasteratos, Antonios ;

Sirakoulis, Georgios Ch .

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2015, 12 (02) :739-751

[4] Person Tracking in Large Public Spaces Using 3-D Range Sensors [J].

Brscic, Drazen ;

Kanda, Takayuki ;

Ikeda, Tetsushi ;

Miyashita, Takahiro .

IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS, 2013, 43 (06) :522-534

[5] Predicting Destinations from Partial Trajectories Using Recurrent Neural Network [J].

Endo, Yuki ;

Nishida, Kyosuke ;

Toda, Hiroyuki ;

Sawada, Hiroshi .

ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2017, PT I, 2017, 10234 :160-172

[6] Simulating dynamical features of escape panic [J].

Helbing, D ;

Farkas, I ;

Vicsek, T .

NATURE, 2000, 407 (6803) :487-490

[7] SOCIAL FORCE MODEL FOR PEDESTRIAN DYNAMICS [J].

HELBING, D ;

MOLNAR, P .

PHYSICAL REVIEW E, 1995, 51 (05) :4282-4286

[8]

Kato Y., 2017, P 2017 IEEE SICE INT

[9]

Kato Y, 2011, IEEE IND ELEC, P2158, DOI 10.1109/IECON.2011.6119642

[10]

Noguchi H., 2012, International symposium on uncertainty quantification and stochastic modeling, P1

← 1 2 →