Next Article in Journal
High-Resolution Remote Sensing Image Change Detection Based on Cross-Mixing Attention Network
Next Article in Special Issue
Pedestrian Trajectory Prediction Based on Motion Pattern De-Perturbation Strategy
Previous Article in Journal
Traffic Classification and Packet Scheduling Strategy with Deadline Constraints for Input-Queued Switches in Time-Sensitive Networking
Previous Article in Special Issue
Channel Switching Algorithms for a Robust Networked Control System with a Delay and Packet Errors
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Electronics
Volume 13
Issue 3
10.3390/electronics13030628
electronics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

A Pedestrian Trajectory Prediction Method for Generative Adversarial Networks Based on Scene Constraints

by
Zhongli Ma
1,
Ruojin An
1,
Jiajia Liu
1,*,
Yuyong Cui
2,
Jun Qi
3,
Yunlong Teng
4,
Zhijun Sun
5,
Juguang Li
6 and
Guoliang Zhang
1
1
College of Automation, Chengdu University of Information Technology, Chengdu 610103, China
2
Southwest Institute of Technical Physics, Chengdu 610041, China
3
College of Communication Engineering, Chengdu University of Information Technology, Chengdu 610225, China
4
College of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
5
Nuclear Power Institute of China, Chengdu 610005, China
6
Chengdu Emfuture Technology Co., Ltd., Chengdu 611731, China
*
Author to whom correspondence should be addressed.
Electronics 2024, 13(3), 628; https://doi.org/10.3390/electronics13030628
Submission received: 28 December 2023 / Revised: 22 January 2024 / Accepted: 30 January 2024 / Published: 2 February 2024
(This article belongs to the Special Issue Intelligent Mobile Robotic Systems: Decision, Planning and Control)
Browse Figures
Versions Notes

Abstract

Pedestrian trajectory prediction is one of the most important topics to be researched for unmanned driving and intelligent mobile robots to perform perceptual interaction with the environment. To solve the problem of the SGAN (social generative adversarial networks) model lacking an understanding of pedestrian interaction and scene constraints, this paper proposes a trajectory prediction method based on a scenario-constrained generative adversarial network. Firstly, a self-attention mechanism is added, which can integrate information at every moment. Secondly, mutual information is introduced to enhance the influence of latent code on the predicted trajectory. Finally, a new social pool is introduced into the original trajectory prediction model, and a scene edge extraction module is added to ensure the final output path of the model is within the passable area in line with the physical scene, which greatly improves the accuracy of trajectory prediction. Based on the CARLA (CAR Learning to Act) simulation platform, the improved model was tested on the public dataset and the self-built dataset. The experimental results showed that the average moving deviation was reduced by 26.4% and the final offset was reduced by 23.8%, which proved that the improved model could better solve the uncertainty of pedestrian turning decisions. The accuracy and stability of pedestrian trajectory prediction are improved while maintaining multiple modes.
Keywords: scene constraint; pedestrian trajectory prediction; generative adversarial networks; self-attention mechanism; CARLA simulation scene constraint; pedestrian trajectory prediction; generative adversarial networks; self-attention mechanism; CARLA simulation

Share and Cite

MDPI and ACS Style

Ma, Z.; An, R.; Liu, J.; Cui, Y.; Qi, J.; Teng, Y.; Sun, Z.; Li, J.; Zhang, G. A Pedestrian Trajectory Prediction Method for Generative Adversarial Networks Based on Scene Constraints. Electronics 2024, 13, 628. https://doi.org/10.3390/electronics13030628

AMA Style

Ma Z, An R, Liu J, Cui Y, Qi J, Teng Y, Sun Z, Li J, Zhang G. A Pedestrian Trajectory Prediction Method for Generative Adversarial Networks Based on Scene Constraints. Electronics. 2024; 13(3):628. https://doi.org/10.3390/electronics13030628

Chicago/Turabian Style

Ma, Zhongli, Ruojin An, Jiajia Liu, Yuyong Cui, Jun Qi, Yunlong Teng, Zhijun Sun, Juguang Li, and Guoliang Zhang. 2024. "A Pedestrian Trajectory Prediction Method for Generative Adversarial Networks Based on Scene Constraints" Electronics 13, no. 3: 628. https://doi.org/10.3390/electronics13030628

APA Style

Ma, Z., An, R., Liu, J., Cui, Y., Qi, J., Teng, Y., Sun, Z., Li, J., & Zhang, G. (2024). A Pedestrian Trajectory Prediction Method for Generative Adversarial Networks Based on Scene Constraints. Electronics, 13(3), 628. https://doi.org/10.3390/electronics13030628

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop