Human Trajectory Prediction via Neural Social Physics

Yue, Jiangbei; Manocha, Dinesh; Wang, He

doi:10.1007/978-3-031-19830-4_22

Cited by 30 publications

(27 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To capture this influence, Sadeghian et al 26 introduced a social attention mechanism, which captures the interaction between pedestrians by computing the LSTM hidden state attention of nearby neighbors. To combine physical modeling and data-driven learning, 18 neural social physics (NSP) is a deep neural network that incorporates learnable physical models with explicit and deterministic parameters to model social interaction mechanism for human trajectory forecasting tasks.…”

Section: Social Interaction and Scene Based Methods For Crowd Trajectorymentioning

confidence: 99%

“…Although various recent works 14 – 16 explore the pedestrian-to-pedestrian and pedestrian-to-environment interaction mechanisms, most of them are time series models, which gradually predict future trajectories based on historical information, prompting them to have shortcomings in forecasting over long spans and capturing interactive global information. Recent works 17 , 18 use social interaction modules and context feature extraction methods to represent person–environment relationships. Despite their promising prediction performance, these methods have shortcomings in exploring influential factors affecting pedestrian interaction and the hypergraph structure’s superiority in dividing and modeling groups (shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pedestrian trajectory prediction with high-order interactions

Xiang,

Tian,

Wang

2024

J. Electron. Imag.

View full text Add to dashboard Cite

To tackle the problem of human trajectory prediction in complex scenes, we propose a model using hypergraph convolutional neural networks for social interaction (HGCNSI). Our model leverages a hypergraph structure to capture both high-order interactions and complex social dynamics among pedestrians (who often influence each other in a nonlinear and structured manner). First, we propose a social interaction module that improves the accuracy of interaction modeling by distinguishing between interacting and non-interacting pedestrians. Then, the hypergraph structure that can capture the complex and nonlinear relations among multiple pedestrians from the social interaction module is constructed. Furthermore, we exploit an improved attention mechanism called scene-coordinates attention that fuses the spatial and temporal features and models the unique historical movement information of each person. Finally, we introduce the SIRF module that filters the trajectories within one iteration to reduce the computational complexity and improve the prediction performance. We evaluate the proposed HGCNSI model on five publicly available datasets and demonstrate that it achieves state-of-the-art results. Specifically, the experiments show that our model outperforms existing methods in terms of prediction accuracy, using evaluation metrics, such as the average displacement error and the final displacement error.

show abstract

Section: Social Interaction and Scene Based Methods For Crowd Trajectorymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Pedestrian trajectory prediction with high-order interactions

Xiang,

Tian,

Wang

2024

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…With the success of Transformers [61] in sequence processing such as natural language processing, researchers like [28], [29], [31], [44], [62] have designed different Transformers to obtain better trajectory representations. In addition, several factors, such as social/scene interactions [22], [23], [63], [64], [65], [66] and stochastic trajectory prediction [18], [19], [20], [32], [67], [68], [69], have been widely investigated. In the remainder of this section, we introduce existing methods related to the approach proposed in this manuscript.…”

Section: Related Workmentioning

confidence: 99%

View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums

Wong

Xia

Hong

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

With the fast development of AI-related techniques, the applications of trajectory prediction are no longer limited to easier scenes and trajectories. More and more heterogeneous trajectories with different representation forms, such as 2D or 3D coordinates, 2D or 3D bounding boxes, and even high-dimensional human skeletons, need to be analyzed and forecasted. Among these heterogeneous trajectories, interactions between different elements within a frame of trajectory, which we call the "Dimension-Wise Interactions", would be more complex and challenging. However, most previous approaches focus mainly on a specific form of trajectories, which means these methods could not be used to forecast heterogeneous trajectories, not to mention the dimension-wise interaction. Besides, previous methods mostly treat trajectory prediction as a normal time sequence generation task, indicating that these methods may require more work to directly analyze agents' behaviors and social interactions at different temporal scales. In this paper, we bring a new "view" for trajectory prediction to model and forecast trajectories hierarchically according to different frequency portions from the spectral domain to learn to forecast trajectories by considering their frequency responses. Moreover, we try to expand the current trajectory prediction task by introducing the dimension M from "another view", thus extending its application scenarios to heterogeneous trajectories vertically. Finally, we adopt the bilinear structure to fuse two factors, including the frequency response and the dimension-wise interaction, to forecast heterogeneous trajectories via spectrums hierarchically in a generic way. Experiments show that the proposed model outperforms most state-of-the-art methods on ETH-UCY benchmark, Stanford Drone Dataset and nuScenes with heterogeneous trajectories, including 2D coordinates, 2D and 3D bounding boxes. ! * Equal contribution. Codes are available at https://github.com/cocoon2wong/E-Vertical.

show abstract

“…A VOIDING accidents involving vulnerable road users (VRU), such as pedestrians, is one of the paramount objectives and ongoing challenges for autonomous vehicles. Consequently, the prediction of pedestrian behavior remains an active area of research, as evidenced by recently published methods [1], [2], [3] and review papers [4], [5]. One of the many reasons for the ongoing research effort are conditions encountered in real-world scenarios, which are characterized by imperfect observations and the stochastic nature of human behavior [6], [5].…”

Section: Introductionmentioning

confidence: 99%

“…Most commonly, only the last eight timesteps are provided (equivalent to 3.2 s) and based on that, 12 timesteps are predicted [8], [9], [10], [1], [11]. Initially modeled through simple rule-based methods [12], various architectures based on neural networks Nico Uhlemann, Felix Fent and Markus Lienkamp are with the Technical University of Munich, Germany; School of Engineering & Design, Institute of Automotive Technology and Munich Institute of Robotics and Machine Intelligence (MIRMI) as well as hybrid approaches [2], [3] have emerged in recent years, trying to improve the overall accuracy of the predicted paths on widely-used benchmarks like ETH/UCY [13], [14] and SSD [15]. While this focus has undoubtedly resulted in significant advancements in the precision of the overall predictions, there remain unexplored aspects that are crucial for assessing the applicability of these methods in autonomous systems.…”

Section: Introductionmentioning

confidence: 99%

A Review of Tracking and Trajectory Prediction Methods for Autonomous Driving

Leon

Gavrilescu

2021

Mathematics

View full text Add to dashboard Cite

This paper provides a literature review of some of the most important concepts, techniques, and methodologies used within autonomous car systems. Specifically, we focus on two aspects extensively explored in the related literature: tracking, i.e., identifying pedestrians, cars or obstacles from images, observations or sensor data, and prediction, i.e., anticipating the future trajectories and motion of other vehicles in order to facilitate navigating through various traffic conditions. Approaches based on deep neural networks and others, especially stochastic techniques, are reported.

show abstract

Human Trajectory Prediction via Neural Social Physics

Cited by 30 publications

References 56 publications

Pedestrian trajectory prediction with high-order interactions

Pedestrian trajectory prediction with high-order interactions

View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums

A Review of Tracking and Trajectory Prediction Methods for Autonomous Driving

Contact Info

Product

Resources

About