Probabilistic trajectory prediction of heterogeneous traffic agents based on layered spatio-temporal graph

Zhang, Xuexiang; Zhang, Weiwei; Wu, Xuncheng; Cao, Wenguan

doi:10.1177/0954407021997667

Cited by 3 publications

(10 citation statements)

References 25 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the structure of a GNN, each agent is modelled with a node in the graph and there exist two types of edges connecting the nodes: temporal edges and spatial edges. Therefore, these models are also called Spatio-Temporal graphs [42], [48], [50]. The temporal edges model the relation between each agent's individual node attributes over time.…”

Section: B Data-driven Modelsmentioning

confidence: 99%

“…This is done through the use of Generative Adversarial Networks (GAN) in [42], [54]- [58] with different architecture for the generator and the discriminator but all consisting of LSTM layers. The other generative model used in the literature is the Conditional Variational Autoencoders (CVAE) which formulates the future trajectory of each agent conditioned on its past trajectory and a latent variable that can be sampled multiple times [29], [38], [48], [59]- [61]. This latent variable is learned during the training phase by providing both the trajectory history and the future trajectory of an agent.…”

Section: B Data-driven Modelsmentioning

confidence: 99%

“…There are a couple of papers that used directed graph [29], [46], [48], [53], [58] as opposed to undirected ones. Directed graphs are usually used to account for the asymmetry of the interactions [53].…”

Section: B Implicit Interaction Modelingmentioning

confidence: 99%

“…In the later, the attributes of the edge are relative measurements such as relative distance between the two connected traffic agents in the graph [29], [32], [46]- [50], [58], relative velocity [29], [46], [50] or relative heading/yaw angel [46], [50]. These edge features are sent to an RNN (e.g., LSTM [32], [40], [48], GRU [46], [50]) to encode the information of the spatial interactions between the agents and to be used along other embedded information (e.g., the temporal edge) to output the predicted trajectory in subsequent layers.…”

Section: B Implicit Interaction Modelingmentioning

confidence: 99%

See 3 more Smart Citations

Pedestrian Trajectory Prediction in Pedestrian-Vehicle Mixed Environments: A Systematic Review

Golchoubian

Ghafurian

Dautenhahn

et al. 2023

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Planning an autonomous vehicle's (AV) path in a space shared with pedestrians requires reasoning about pedestrians' future trajectories. A practical pedestrian trajectory prediction algorithm for the use of AVs needs to consider the effect of the vehicle's interactions with the pedestrians on pedestrians' future motion behaviours. In this regard, this paper systematically reviews different methods proposed in the literature for modelling pedestrian trajectory prediction in presence of vehicles that can be applied for unstructured environments. This paper also investigates specific considerations for pedestrian-vehicle interaction (compared with pedestrian-pedestrian interaction) and reviews how different variables such as prediction uncertainties and behavioural differences are accounted for in the previously proposed prediction models. PRISMA guidelines were followed. Articles that did not consider vehicle and pedestrian interactions or actual trajectories, and articles that only focused on road crossing were excluded. A total of 1260 unique peer-reviewed articles from ACM Digital Library, IEEE Xplore, and Scopus databases were identified in the search. 64 articles were included in the final review as they met the inclusion and exclusion criteria. An overview of datasets containing trajectory data of both pedestrians and vehicles used by the reviewed papers has been provided. Research gaps and directions for future work, such as having more effective definition of interacting agents in deep learning methods and the need for gathering more datasets of mixed traffic in unstructured environments are discussed.

show abstract

Section: B Data-driven Modelsmentioning

confidence: 99%

Section: B Data-driven Modelsmentioning

confidence: 99%

Section: B Implicit Interaction Modelingmentioning

confidence: 99%

Section: B Implicit Interaction Modelingmentioning

confidence: 99%

See 2 more Smart Citations

Pedestrian Trajectory Prediction in Pedestrian-Vehicle Mixed Environments: A Systematic Review

Golchoubian

Ghafurian

Dautenhahn

et al. 2023

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…With the development of artificial intelligence, more and more researchers are devoted to the research of autonomous vehicles. 1 The key technologies of autonomous vehicles mainly include three parts: motion prediction of surrounding vehicles, 2,3 vehicle decision-making, and autonomous vehicle control. 4 Therefore, we must first have a good understanding of the surrounding traffic and predict the future motion of surrounding vehicles.…”

Section: Introductionmentioning

confidence: 99%

A comprehensive lateral motion prediction method of surrounding vehicles integrating driver intention prediction and vehicle behavior recognition

Luan

Huang

Zhao

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

In order to solve the accuracy problem of the future motion prediction of the surrounding vehicles with different types of drivers, this paper proposes a comprehensive lateral motion prediction method that combines driver intention prediction and vehicle behavior recognition. For different drivers, different driver optimization models are established: personal optimal model and system optimal model. Then, the driver’s intention prediction probability is obtained through the game theory. Different from the traditional game theory, we apply different model for different driver on the premise of getting the type of driver instead of using the Nash equilibrium for all players. According to the results of driver intention prediction and the vehicle behavior recognition, the optimized polynomial trajectory is used to obtain the driver’s intention prediction trajectory and the vehicle behavior recognition trajectory. Next, the Nash-optimization function of the intention prediction trajectory and the behavior recognition trajectory are established respectively according to the trajectory error, and the balance between the two is our comprehensive trajectory. In order to verify the effectiveness of the proposed method, we conducted simulations under mandatory lane changing and discretionary lane changing conditions. The simulation results show that our algorithm can accurately predict the future motion of the vehicle under different drivers, different speeds and different gaps between vehicles. Its prediction performance is much better than other algorithms.

show abstract

Holistic Spatio-Temporal Graph Attention for Trajectory Prediction in Vehicle–Pedestrian Interactions

Alghodhaifi,

Lakshmanan

2023

Sensors

View full text Add to dashboard Cite

Ensuring that intelligent vehicles do not cause fatal collisions remains a persistent challenge due to pedestrians’ unpredictable movements and behavior. The potential for risky situations or collisions arising from even minor misunderstandings in vehicle–pedestrian interactions is a cause for great concern. Considerable research has been dedicated to the advancement of predictive models for pedestrian behavior through trajectory prediction, as well as the exploration of the intricate dynamics of vehicle–pedestrian interactions. However, it is important to note that these studies have certain limitations. In this paper, we propose a novel graph-based trajectory prediction model for vehicle–pedestrian interactions called Holistic Spatio-Temporal Graph Attention (HSTGA) to address these limitations. HSTGA first extracts vehicle–pedestrian interaction spatial features using a multi-layer perceptron (MLP) sub-network and max pooling. Then, the vehicle–pedestrian interaction features are aggregated with the spatial features of pedestrians and vehicles to be fed into the LSTM. The LSTM is modified to learn the vehicle–pedestrian interactions adaptively. Moreover, HSTGA models temporal interactions using an additional LSTM. Then, it models the spatial interactions among pedestrians and between pedestrians and vehicles using graph attention networks (GATs) to combine the hidden states of the LSTMs. We evaluate the performance of HSTGA on three different scenario datasets, including complex unsignalized roundabouts with no crosswalks and unsignalized intersections. The results show that HSTGA outperforms several state-of-the-art methods in predicting linear, curvilinear, and piece-wise linear trajectories of vehicles and pedestrians. Our approach provides a more comprehensive understanding of social interactions, enabling more accurate trajectory prediction for safe vehicle navigation.

show abstract

Probabilistic trajectory prediction of heterogeneous traffic agents based on layered spatio-temporal graph

Cited by 3 publications

References 25 publications

Pedestrian Trajectory Prediction in Pedestrian-Vehicle Mixed Environments: A Systematic Review

Pedestrian Trajectory Prediction in Pedestrian-Vehicle Mixed Environments: A Systematic Review

A comprehensive lateral motion prediction method of surrounding vehicles integrating driver intention prediction and vehicle behavior recognition

Holistic Spatio-Temporal Graph Attention for Trajectory Prediction in Vehicle–Pedestrian Interactions

Contact Info

Product

Resources

About