Predicting Pedestrian Trajectories with Deep Adversarial Networks Considering Motion and Spatial Information
-
Published:2023-12-12
Issue:12
Volume:16
Page:566
-
ISSN:1999-4893
-
Container-title:Algorithms
-
language:en
-
Short-container-title:Algorithms
Author:
Lao Liming1ORCID, Du Dangkui2, Chen Pengzhan12ORCID
Affiliation:
1. Institute of Robotics and Intelligent Systems, Taizhou University, Taizhou 318000, China 2. School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330013, China
Abstract
This paper proposes a novel prediction model termed the social and spatial attentive generative adversarial network (SSA-GAN). The SSA-GAN framework utilizes a generative approach, where the generator employs social attention mechanisms to accurately model social interactions among pedestrians. Unlike previous methodologies, our model utilizes comprehensive motion features as query vectors, significantly enhancing predictive performance. Additionally, spatial attention is integrated to encapsulate the interactions between pedestrians and their spatial context through semantic spatial features. Moreover, we present a novel approach for generating simulated multi-trajectory datasets using the CARLA simulator. This method circumvents the limitations inherent in existing public datasets such as UCY and ETH, particularly when evaluating multi-trajectory metrics. Our experimental findings substantiate the efficacy of the proposed SSA-GAN model in capturing the nuances of pedestrian interactions and providing accurate multimodal trajectory predictions.
Funder
National Natural Science Foundation of China
Subject
Computational Mathematics,Computational Theory and Mathematics,Numerical Analysis,Theoretical Computer Science
Reference48 articles.
1. Yang, C.T., Zhang, T., Chen, L.P., and Fu, L.C. (2019, January 6–9). Socially-Aware Navigation of Omnidirectional Mobile Robot with Extended Social Force Model in Multi-Human Environment. Proceedings of the 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), Bari, Italy. 2. Haarslev, F., Juel, W.K., Kollakidou, A., Krüger, N., and Bodenhagen, L. (2021, January 6–8). Context-aware Social Robot Navigation. Proceedings of the 18th International Conference on Informatics in Control, Automation and Robotics, Paris, France. 3. Li, K., Shan, M., Narula, K., Worrall, S., and Nebot, E. (2020, January 20–23). Socially Aware Crowd Navigation with Multimodal Pedestrian Trajectory Prediction for Autonomous Vehicles. Proceedings of the IEEE 23rd International Conference on Intelligent Transportation Systems, Rhodes, Greece. 4. Uhlemann, N., Fent, F., and Lienkamp, M. (2023). Evaluating Pedestrian Trajectory Prediction Methods for the Application in Autonomous Driving. arXiv. 5. Rhinehart, N., Mcallister, R., Kitani, K., and Levine, S. (November, January 27). PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|