Intent Prediction of Pedestrians via Motion Trajectories Using Stacked Recurrent Neural Networks
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
The problem of intent understanding between highly and fully automated vehicles and vulnerable road users (VRUs) such as pedestrians in urban traffic environment has got some momentum over the past few years. Previous work has been tackling the problem using two common approaches, namely dynamical motion modeling and motion planning. In this paper, a novel radical end-to-end data-driven approach is proposed for long-term intent prediction of VRUs in urban traffic environment based solely on their motion trajectories. In the proposed approach, we utilized the widely adopted architecture of recurrent neural networks with Long-Short Term Memory (LSTM) modules to form a deep stacked LSTM network. Three common approaches used in the literature were compared against our proposed approach over two different real-world datasets involving pedestrians collected from vehicle-based stereo cameras. The results over the testing datasets showed that the proposed approach achieved higher accuracies over most of the scenarios of the testing datasets with a small mean lateral position error of 0.48 m. Moreover, the proposed approach showed also a significant generalization capability over totally unobserved testing scenes during the training phase with only 0.58 m in mean lateral position error.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“| RNN | Process sequential data via recurrent structures | Simple temporal analysis, low latency | Basic motion recognition (e.g., arm |”
From Recent advances in intelligent wearable systems: from multiscale biomechanical features towards human motion intent prediction (2026) · cites this paper as [147]
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 11×
“They have also introduced two data-driven approaches for the pedestrian intent recognition task based on CNNs and RNNs respectively.”
MethodInfluentialAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We utilized the Adam optimizer [32], to minimize the”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 1×
“have witnessed a huge success in a number of different spatial and sequential tasks [12], [17]–[19].”
BackgroundFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · cited 1×
“have witnessed a huge success in a number of different spatial and sequential tasks [12], [17]–[19].”
BackgroundRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 2×
“Recurrent Neural Networks (RNN) have been commonly used in many sequence-based prediction tasks such as handwriting imitation [24], driver behavior modeling [25], human gait”
BackgroundMethodUnscented Filtering and Nonlinear Estimation
Julier, S. J., & Uhlmann, J. K. (2004) · Proceedings of the IEEE · doi:10.1109/jproc.2003.823141 · Cited by 6,588 · cited 7×
“In [6], a dynamical motion model based on Extended Kalman filter (EKF) [14] with different motion models was proposed for short time prediction (i.e. less than 2 seconds) of pedestrians’ motion trajectories.”
MethodInfluentialOn the difficulty of training recurrent neural networks
Pascanu, R., Mikolov, T., & Bengio, Y. (2012) · arXiv · doi:10.48550/arxiv.1211.5063 · Cited by 4,310 · cited 1×
“Since traditional RNNs have difficult times in giving an accurate prediction when it comes to memorizing past long sequences [28].”
Background
Research works printed but not linked: 1
- lee, 2007, Loss functions in time series forecasting, International Encyclopedia of the Social Sciences
Cited by
Items 101–103 of 103
Digital Manufacturing and the Fifth Industrial Revolution
Kumar, A., & Rai, R. S. (2025) · Wiley eBooks · doi:10.1002/9781394365371.ch17
FMI-PTP: Pedestrian trajectory prediction based on field of view and motion intent
Cong, P., Zhu, Y., Deng, M., Xiao, Y., Tang, A., & Zhang, X. (2026) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2026.131457
Wang, Z., Zhou, Z., Zhou, W., Chu, X., & Xie, S. (2026) · Transportmetrica A Transport Science · doi:10.1080/23249935.2026.2702488
Metadata
- Authors
- Saleh, K., Hossny, M., & Nahavandi, S.
- Affiliations
- Deakin University (AU)
- Venue
- IEEE Transactions on Intelligent Vehicles
- Published
- 2018-12
- Volume
- 3
- Issue
- 4
- Pages
- 414-424
- ISSN
- 2379-8858 (ISSN-L)
- 2379-8904
- OpenAlex
- W2895763020
- Cited by
- 103
- References
- 32
- Citations by year
- 2026: 4 · 2025: 16 · 2024: 13 · 2023: 22 · 2022: 11 · 2021: 17 · 2020: 12 · 2019: 7 · 2018: 1
- FWCI
- 4.92
- Type
- journal article
- Language
- en
- Open access
- green
- figshare.com
- Locations
- IEEE Transactions on Intelligent Vehicles (publishedVersion)
- Deakin Research Online (Deakin University) (submittedVersion)
- Figshare (submittedVersion, cc-by)
- Funders
- Institute for Intelligent Systems Research and Innovation (IISRI)
- Topics
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Traffic and Road Safety
- Social Sciences › Safety Research › Evacuation and Crowd Dynamics
- Keywords
- vulnerable road users, movement trajectories, stacked LSTM, long short-term memory, end-to-end learning, autonomous vehicles, urban traffic
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.