scholarly journals Pedestrian Trajectory Prediction in Extremely Crowded Scenarios

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1223 ◽  
Author(s):  
Xiaodan Shi ◽  
Xiaowei Shao ◽  
Zhiling Guo ◽  
Guangming Wu ◽  
Haoran Zhang ◽  
...  
Keyword(s):  
Relative Motion ◽  
Short Term Memory ◽  
Back Propagation ◽  
Human Interaction ◽  
Force Model ◽  
Social Force ◽  
Trajectory Data ◽  
Trajectory Prediction ◽  
Anisotropic Neighborhood ◽  
Absolute Coordinates

Pedestrian trajectory prediction under crowded circumstances is a challenging problem owing to human interaction and the complexity of the trajectory pattern. Various methods have been proposed for solving this problem, ranging from traditional Bayesian analysis to Social Force model and deep learning methods. However, most existing models heavily depend on specific scenarios because the trajectory model is constructed in absolute coordinates even though the motion trajectory as well as human interaction are in relative motion. In this study, a novel trajectory prediction model is proposed to capture the relative motion of pedestrians in extremely crowded scenarios. Trajectory sequences and human interaction are first represented with relative motion and then integrated to our model to predict pedestrians’ trajectories. The proposed model is based on Long Short Term Memory (LSTM) structure and consists of an encoder and a decoder which are trained by truncated back propagation. In addition, an anisotropic neighborhood setting is proposed instead of traditional neighborhood analysis. The proposed approach is validated using trajectory data acquired at an extremely crowded train station in Tokyo, Japan. The trajectory prediction experiments demonstrated that the proposed method outperforms existing methods and is stable for predictions of varying length even when the model is trained with a controlled short trajectory sequence.

Long Short-Term Memory-Based Human-Driven Vehicle Longitudinal Trajectory Prediction in a Connected and Autonomous Vehicle Environment

2021 ◽  
pp. 036119812199347
Author(s):  
Lei Lin ◽  
Siyuan Gong ◽  
Srinivas Peeta ◽  
Xia Wu
Keyword(s):  
Traffic Flow ◽  
Short Term Memory ◽  
Road Traffic ◽  
Autonomous Vehicle ◽  
Trajectory Data ◽  
Road Transportation ◽  
Trajectory Prediction ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

The advent of connected and autonomous vehicles (CAVs) will change driving behavior and travel environment, and provide opportunities for safer, smoother, and smarter road transportation. During the transition from the current human-driven vehicles (HDVs) to a fully CAV traffic environment, the road traffic will consist of a “mixed” traffic flow of HDVs and CAVs. Equipped with multiple sensors and vehicle-to-vehicle communications, a CAV can track surrounding HDVs and receive trajectory data of other CAVs in communication range. These trajectory data can be leveraged with recent advances in deep learning methods to potentially predict the trajectories of a target HDV. Based on these predictions, CAVs can react to circumvent or mitigate traffic flow oscillations and accidents. This study develops attention-based long short-term memory (LSTM) models for HDV longitudinal trajectory prediction in a mixed flow environment. The model and a few other LSTM variants are tested on the Next Generation Simulation US 101 dataset with different CAV market penetration rates (MPRs). Results illustrate that LSTM models that utilize historical trajectories from surrounding CAVs perform much better than those that ignore information even when the MPR is as low as 0.2. The attention-based LSTM models can provide more accurate multi-step longitudinal trajectory predictions. Further, grid-level average attention weight analysis is conducted and the CAVs with higher impact on the target HDV’s future trajectories are identified.

scholarly journals Social Force Model-Based Safety Evaluation of Intersections in Arterials Considering the Pedestrian Yield Rule

2021 ◽  
Vol 18 (23) ◽  
pp. 12461
Author(s):  
Jiao Yao ◽  
Yuhang Li ◽  
Jiaping He
Keyword(s):  
Evaluation Model ◽  
Safety Evaluation ◽  
Force Model ◽  
Social Force ◽  
Trajectory Data ◽  
Entropy Weight ◽  
Social Force Model ◽  
Entropy Weight Method ◽  
Safety Models ◽  
Pedestrian Crossing

To enhance the safety of pedestrians crossing the street, a series of new regulations regarding pedestrian yield has been proposed and widely implemented across cities. In this study, we first made some improvements to the social force model, in which pedestrian crossing at the intersection, drivers’ psychology of giving way, vehicle yield to pedestrians, vehicle yield in different directions, the influence of pedestrians crossing boundaries, and signal lamp groups on pedestrian behavior were considered. Furthermore, pedestrian crossing and vehicle yield safety models were established, based on which the comprehensive safety evaluation model of intersections in arterials was established, in which two indices—(1) the safety degree of pedestrian crossings and (2) vehicle acceleration interference—were combined with the entropy weight method. Finally, four types of intersections in arterials were studied using a simulation: the intersections between different levels of arterials, and intersections with one-time and two-times pedestrian crossings. Moreover, safety evaluation and analysis of those intersections, considering the rule of pedestrian yield, were conducted combined with the trajectory data from the VISSIM simulation. The relevant results showed that for pedestrians crossing the street, the pedestrian safety of two-time crossing is significantly higher than that of one-time crossing, and compared with the arterial, the pedestrian crossing distance of the sub-arterial is shorter, and the pedestrian perception is safer. Moreover, due to the herd psychology effect, the increase in pedestrian flow volume improves the safety perception of pedestrians at the intersection.

scholarly journals Trajectory prediction based on long short-term memory network and Kalman filter using hurricanes as an example

2021 ◽  
Vol 25 (3) ◽  
pp. 1005-1023
Author(s):  
Wanting Qin ◽  
Jun Tang ◽  
Cong Lu ◽  
Songyang Lao
Keyword(s):  
Kalman Filter ◽  
Moving Objects ◽  
Short Term Memory ◽  
Effective Means ◽  
Prediction Algorithm ◽  
Trajectory Data ◽  
Trajectory Prediction ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

AbstractTrajectory data can objectively reflect the moving law of moving objects. Therefore, trajectory prediction has high application value. Hurricanes often cause incalculable losses of life and property, trajectory prediction can be an effective means to mitigate damage caused by hurricanes. With the popularization and wide application of artificial intelligence technology, from the perspective of machine learning, this paper trains a trajectory prediction model through historical trajectory data based on a long short-term memory (LSTM) network. An improved LSTM (ILSTM) trajectory prediction algorithm that improves the prediction of the simple LSTM is proposed, and the Kalman filter is used to filter the prediction results of the improved LSTM algorithm, which is called LSTM-KF. Through simulation experiments of Atlantic hurricane data from 1851 to 2016, compared to other LSTM and ILSTM algorithms, it is found that the LSTM-KF trajectory prediction algorithm has the lowest prediction error and the best prediction effect.

scholarly journals Modeling and Simulation of Nonmotorized Vehicles’ Dispersion at Mixed Flow Intersections

2019 ◽  
Vol 2019 ◽  
pp. 1-19 ◽  
Author(s):  
Qiyuan Liu ◽  
Jian Sun ◽  
Ye Tian ◽  
Ying Ni ◽  
Shinan Yu
Keyword(s):  
Electric Field ◽  
Dispersion Model ◽  
Particle Dispersion ◽  
Force Model ◽  
Dispersion Characteristics ◽  
Social Force ◽  
Trajectory Data ◽  
High Definition ◽  
Mixed Flow ◽  
Motorized Vehicles

Interactions between motorized and nonmotorized vehicles have drawn considerable attention from researchers. They are commonly seen at mixed flow intersections where nonmotorized vehicles, without the restriction of lane markers or physical barriers, may disperse into adjacent lanes and thus lead to complex interactions with motorized vehicles. Such a dispersion phenomenon between heterogeneous participants (e-bikes and bicycles as nonmotorized vehicles versus motorized vehicles) is difficult to model. In this paper, we were inspired by the dispersion of charged particles in an electric field and modeled the dispersion phenomenon of go-straight, nonmotorized vehicles at mixed flow intersections accordingly, as it was discovered in this research that these two dispersion phenomena share three underlying commonalities with each other. A novel particle dispersion model (PDM) based on a particle’s movement in an electric field is proposed. The model is calibrated and validated using 1,490 high-definition sets of trajectory data for go-straight, nonmotorized vehicles during 43 cycles at two typical mixed flow intersections. The PDM is compared with the social force model (SFM) on their dispersion characteristics that are used to describe the nonmotorized bicycles’ behavior. The results show that the PDM performs better than the SFM with regard to depicting the dispersion characteristic indices of the nonmotorized vehicles, such as the travel time, the dispersion intensity of heterogeneous nonmotorized vehicles, the sectional dispersion degree, and other dispersion characteristics.

scholarly journals A re-examination of the role of friction in the original Social Force Model

2020 ◽  
Vol 121 ◽  
pp. 42-53 ◽  
Author(s):  
I.M. Sticco ◽  
G.A. Frank ◽  
F.E. Cornes ◽  
C.O. Dorso
Keyword(s):  
Force Model ◽  
Social Force ◽  
Social Force Model

A prediction model of vessel trajectory based on generative adversarial network

2021 ◽  
pp. 1-11
Author(s):  
Senjie Wang ◽  
Zhengwei He
Keyword(s):  
Safety Management ◽  
Route Planning ◽  
Local Area ◽  
Trajectory Data ◽  
Trajectory Prediction ◽  
Generative Adversarial Network ◽  
Ship Traffic ◽  
Adversarial Network ◽  
Historical Trajectory ◽  
Vessel Motion

Abstract Trajectory prediction is an important support for analysing the vessel motion behaviour, judging the vessel traffic risk and collision avoidance route planning of intelligent ships. To improve the accuracy of trajectory prediction in complex situations, a Generative Adversarial Network with Attention Module and Interaction Module (GAN-AI) is proposed to predict the trajectories of multiple vessels. Firstly, GAN-AI can infer all vessels’ future trajectories simultaneously when in the same local area. Secondly, GAN-AI is based on adversarial architecture and trained by competition for better convergence. Thirdly, an interactive module is designed to extract the group motion features of the multiple vessels, to achieve better performance at the ship encounter situations. GAN-AI has been tested on the historical trajectory data of Zhoushan port in China; the experimental results show that the GAN-AI model improves the prediction accuracy by 20%, 24% and 72% compared with sequence to sequence (seq2seq), plain GAN, and the Kalman model. It is of great significance to improve the safety management level of the vessel traffic service system and judge the degree of ship traffic risk.

scholarly journals Crowd Evacuation Guidance Based on Combined Action Reinforcement Learning

Algorithms ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 26
Author(s):  
Yiran Xue ◽  
Rui Wu ◽  
Jiafeng Liu ◽  
Xianglong Tang
Keyword(s):  
Reinforcement Learning ◽  
Guidance System ◽  
Force Model ◽  
Interactive Simulation ◽  
Social Force ◽  
Novel Approach ◽  
Learning Agent ◽  
Network Output ◽  
Combined Action ◽  
Crowd Evacuation

Existing crowd evacuation guidance systems require the manual design of models and input parameters, incurring a significant workload and a potential for errors. This paper proposed an end-to-end intelligent evacuation guidance method based on deep reinforcement learning, and designed an interactive simulation environment based on the social force model. The agent could automatically learn a scene model and path planning strategy with only scene images as input, and directly output dynamic signage information. Aiming to solve the “dimension disaster” phenomenon of the deep Q network (DQN) algorithm in crowd evacuation, this paper proposed a combined action-space DQN (CA-DQN) algorithm that grouped Q network output layer nodes according to action dimensions, which significantly reduced the network complexity and improved system practicality in complex scenes. In this paper, the evacuation guidance system is defined as a reinforcement learning agent and implemented by the CA-DQN method, which provides a novel approach for the evacuation guidance problem. The experiments demonstrate that the proposed method is superior to the static guidance method, and on par with the manually designed model method.

scholarly journals Simulating Interactions between Pedestrians, Segway Riders and Cyclists in Shared Spaces Using Social Force Model

2018 ◽  
Vol 34 ◽  
pp. 91-98 ◽  
Author(s):  
Charitha Dias ◽  
Hiroaki Nishiuchi ◽  
Satoshi Hyoudo ◽  
Tomoyuki Todoroki
Keyword(s):  
Force Model ◽  
Social Force ◽  
Social Force Model ◽  
Shared Spaces
Sign in / Sign up

Export Citation Format

Share Document