Pedestrian Trajectory Prediction Combining Probabilistic Reasoning and Sequence Learning

Autonomous vehicles are expected to predict the near future trajectories of the pedestrian who might wait or continue crossing the road at the un-signalized intersection. This study presents a new framework for pedestrian trajectory predictions, which integrates Dynamic Bayesian Networks (DBN) and sequence to sequence (Seq2Seq) learning through an adaptive weighting strategy. DBN anticipates the pedestrian’s future trajectories using a probabilistic graphical model that combines environmental clues and kinematic information. Seq2Seq predicts the future trajectories with a well-trained learning model based on the observed trajectories up to the current instant. The adaptive weighting strategy can allocate weights online for DBN and Seq2Seq using the stopping probability and prediction errors. A real-world pedestrian dataset is employed for evaluations and results show that the proposed model outperforms DBN and Seq2Seq. The mean errors and final destination errors of the proposed model when predicting one second ahead are 0.04m, 0.10m in crossing scenarios, and 0.06m, 0.17m in stopping scenarios. This study expects to provide active pedestrian protections for autonomous vehicles on urban roads.

Pedestrian trajectory prediction is fundamental to a wide range of scientific research work and industrial applications. Most of the current advanced trajectory prediction methods incorporate context information such as pedestrian neighbourhood, labelled static obstacles, and the background scene into the trajectory prediction process. In contrast to these methods which require rich contexts, the method in our paper focuses on predicting a pedestrian's future trajectory using his/her observed part of the trajectory only. Our method, which we refer to as LVTA, is a Location-Velocity-Temporal Attention LSTM model where two temporal attention mechanisms are applied to the hidden state vectors from the location and velocity LSTM layers. In addition, a location-velocity attention layer embedded inside a tweak module is used to improve the predicted location and velocity coordinates before they are passed to the next time step. Extensive experiments conducted on three large benchmark datasets and comparison with eleven existing trajectory prediction methods demonstrate that LVTA achieves competitive prediction performance. Specifically, LVTA attains 9.19 pixels Average Displacement Error (ADE) and 17.28 pixels Final Displacement Error (FDE) for the Central Station dataset, and 0.46 metres ADE and 0.92 metres FDE for the ETH&UCY datasets. Furthermore, evaluation on using LVTA to generate trajectories of different prediction lengths and on new scenes without the need of retraining confirms that it has good generalizability.

Pedestrian trajectory prediction is a critical research area with numerous domains, e.g., blind navigation, autonomous driving systems, and service robots. There exist two challenges in this research field: spatio-temporal interaction modeling among pedestrians and the uncertainty of pedestrian trajectories. To tackle these challenges, we propose a spatio-temporal interaction aware and trajectory distribution aware graph convolution network. First, we propose a spatio-temporal interaction aware module that integrates a graph convolutional network and self-attention mechanism to model spatio-temporal interactions among pedestrians. Second, we design a trajectory distribution aware module to learn latent trajectory distribution information from the measured trajectories at observed and future times. This can provide knowledge-rich trajectory distribution information for the multimodality of the predicted trajectories. Finally, to address the problem of the propagation and accumulation of prediction errors, we design a trajectory decoder to generate the multimodal future trajectories. The proposed model is evaluated utilizing videos recorded by a camera sensor in crowded areas and can be applied to predict multiple pedestrians’ future trajectories from in-vehicle cameras. Experimental results demonstrate that the proposed approach can achieve superior results on the average displacement error (ADE) and final displacement error (FDE) metrics to state-of-the-art approaches and can predict socially acceptable future trajectories.

We propose a dynamic differential Bayesian networks (DDBNs) and nonparametric regression model. This model is an extended model of traditional dynamic Bayesian networks (DBNs), which can incorporate temporal information in a natural way and directly handle real-valued data obtained from microarrays without any transformation. In addition, it can cope with differential information between gene expression levels, without any loss to the traditional advantage, i.e., the capability of estimating non-linear relationships between genes. We apply DDBNs to analyze simulated data and real data, i.e., Saccharomyces cerevisiae cell cycle gene expression data. We have confirmed the effectiveness of our approach in the sense that some edges have been successfully detected only by DDBNs, not by DBNs.

Pedestrian behavior anticipation is a key challenge in the design of assistive and autonomous driving systems suitable for urban environments. An intelligent system should be able to understand the intentions or underlying motives of pedestrians and to predict their forthcoming actions. To date, only a few public datasets were proposed for the purpose of studying pedestrian behavior prediction in the context of intelligent driving. To this end, we propose a novel large-scale dataset designed for pedestrian intention estimation (PIE). We conducted a large-scale human experiment to establish human reference data for pedestrian intention in traffic scenes. We propose models for estimating pedestrian crossing intention and predicting their future trajectory. Our intention estimation model achieves 79% accuracy and our trajectory prediction algorithm outperforms state-of-the-art by 26% on the proposed dataset. We further show that combining pedestrian intention with observed motion improves trajectory prediction. The dataset and models are available at http://data.nvision2.eecs.yorku.ca/PIE_dataset/.

Non-probability sampling network based on anomaly pedestrian trajectory discrimination for pedestrian trajectory prediction

Pedestrian trajectory prediction via physical-guided position association learning

Pedestrian trajectory prediction in urban environments has emerged as a critical research area with extensive applications across various domains. Accurate prediction of pedestrian trajectories is essential for the safe navigation of autonomous vehicles and robots in pedestrian-populated environments. Effective prediction models must capture both the spatial interactions among pedestrians and the temporal dependencies governing their movements. Existing research primarily focuses on forecasting a single trajectory per pedestrian, limiting its applicability in real-world scenarios characterised by diverse and unpredictable pedestrian behaviours. To address these challenges, this paper introduces the Graph Convolutional Network, Spatial–Temporal Attention, and Generative Model (GSTGM) for pedestrian trajectory prediction. GSTGM employs a spatiotemporal graph convolutional network to effectively capture complex interactions between pedestrians and their environment. Additionally, it integrates a spatial–temporal attention mechanism to prioritise relevant information during the prediction process. By incorporating a time-dependent prior within the latent space and utilising a computationally efficient generative model, GSTGM facilitates the generation of diverse and realistic future trajectories. The effectiveness of GSTGM is validated through experiments on real-world scenario datasets. Compared to the state-of-the-art models on benchmark datasets such as ETH/UCY, GSTGM demonstrates superior performance in accurately predicting multiple potential trajectories for individual pedestrians. This superiority is measured using metrics such as Final Displacement Error (FDE) and Average Displacement Error (ADE). Moreover, GSTGM achieves these results with significantly faster processing speeds.

Pedestrian trajectory prediction can provide decision support for self-driving cars and robots to avoid potential collision risks. Modelling of social relationships and multimodal prediction are core challenges in pedestrian trajectory prediction. However, there are two problems with existing methods: (1) these methods usually focus on modelling pairwise or group interactions, ignoring the importance of high-order interactions; and (2) existing methods struggle to balance the performance between deterministic and multimodal predictions. To address these issues, we propose a higher-order graph attention network for pedestrian trajectory prediction. Specifically, we first construct spatial and temporal graphs to model social interactions and temporal dependencies. To achieve high-order interaction modelling, we design a higher-order graph attention module to capture pedestrian social and temporal interactions of different orders by stacking multiple layers of graph attention. Subsequently, we design a deformable spatial-temporal sparse module to adaptively eliminate social and temporal redundant interactions. To balance deterministic and multimodal prediction performance, we design a two-stage prediction strategy. The first stage predicts pedestrian deterministic trajectories, and the second stage refines pedestrian deterministic trajectories to complete both deterministic and multimodal predictions. Quantitative analysis on the ETH, UCY, and SDD datasets demonstrates that our method outperforms existing methods in both deterministic and multimodal predictions. Qualitative analysis shows that our method can effectively describe complex social relationships and accomplish reliable trajectory prediction.

The supply chain is the central organizing unit in today's global industries and has gained significance as one of the 21st century manufacturing paradigms for improving organizational competitiveness. In this paper, we propose a dynamic Bayesian network to represent the cause-and-effect relationships in an industrial supply chain. Based on the Quick Scan, a systematic data analysis and synthesis methodology, a dynamic Bayesian network is employed as a more descriptive mechanism to model the causal relationships in the supply chain. Dynamic Bayesian networks can be utilized as a knowledge base of the reasoning systems where the diagnostic tasks are conducted. We finally solve this reasoning problem with stochastic simulation.

Forecasting pedestrian trajectories in dynamic scenes remains a critical problem in various applications, such as autonomous driving and socially aware robots. Such forecasting is challenging due to human-human and human-object interactions and future uncertainties caused by human randomness. Generative model-based methods handle future uncertainties by sampling a latent variable. However, few studies explored the generation of the latent variable. In this work, we propose the trajectory predictor with pseudo Oracle (TPPO), which is a generative model-based trajectory predictor. The first pseudo oracle is pedestrians’ moving directions, and the second one is the latent variable estimated from ground truth trajectories. A social attention module is used to aggregate neighbors’ interactions based on the correlation between pedestrians’ moving directions and future trajectories. This correlation is inspired by the fact that pedestrians’ future trajectories are often influenced by pedestrians in front. A latent variable predictor is proposed to estimate latent variable distributions from observed and ground-truth trajectories. Moreover, the gap between these two distributions is minimized during training. Therefore, the latent variable predictor can estimate the latent variable from observed trajectories to approximate that estimated from ground-truth trajectories. We compare the performance of TPPO with related methods on several public datasets. Results demonstrate that TPPO outperforms state-of-the-art methods with low average and final displacement errors. The ablation study shows that the prediction performance will not dramatically decrease as sampling times decline during tests.

One of the major restrictions of dynamic Bayesian networks (DBNs) is their inability to account for topological features such as shape descriptors, homeomorphy, homotopy, and invariance. The main reason for this shortcoming is explained by the fact that even if dynamic Bayesian networks encode statistical relationships; they are not embedded in a Euclidean space where mathematical structures abound. The goal is to embed DBNs into a Euclidean space such that these topological features can be exploited. This extension of DBNs to topological DBNs (TDBNs) leapfrogs the task of pattern recognition and machine learning by not only classifying objects but revealing how they are related topologically. We have applied the TDBN formalism to facial aging for person identification. Preliminary results reveal that the TDBNs outperform the traditional DBN with an accuracy margin of 8% in average.

Nowadays, several components and systems are designed and produced based on reliability. Since the reliability criterion has an important role in purchasing and implementation of these systems. In the design of a reliable system, fault and failure analysis must be carried out in order to reduce fault probability of the system. When dependency and the relation between components of a complex system are important and should be mentioned, determination of system reliability is very difficult. In this paper, dynamic fault tree is used to evaluate the systems reliability that their behavior is varied with time. Dynamic fault tree is constructed and then it converted to dynamic bayesian network. In this paper, the principle of dynamic fault tree gates and their mapping into dynamic bayesian are explained and some new relations between events and gates for this mapping are proposed. GeNIe package is used to determine dynamic bayesian network based on stochastic sampling algorithms. Four systems (cardiac assist system, hypothetical cascaded priority-and system, inertial navigation system/ global positioning system integrated, and emergency detection system) are investigated; reliability and fault probability of these systems are calculated. Comparison of the results with those obtained by other researches shows the proposed method effectiveness for systems reliability modeling and assessment via dynamic bayesian network.

In order to find out the problems of students' learning in the online learning process in time and ensure that students can successfully complete the online learning course, the dynamic Bayesian network is used to predict students' online learning scores. First, the online course Bayesian network is established, and then the dynamic Bayesian network is established by combining the Bayesian network and hidden Markov according to the time slice. The maximum expectation algorithm is used for Bayesian parameter learning, and the scores are predicted according to video learning, chapter test and other influencing factors. The results show that the dynamic Bayesian network can effectively predict the online learning results, the prediction results provide teachers with decision-making, and students can carry out targeted reinforcement learning according to the prediction results in the learning process.

Understanding crowd motion dynamics and forecasting the future pedestrian trajectories are critical to various applications, e.g. autonomous driving and surveillance system. This task is challenging because when pedestrians plan the future paths in real crowd scenes, they will distinguish the priorities of following their predetermined destinations and responding to the motion behaviors of neighboring pedestrians. However, most of the existing methods ignore the problem of intention-interaction trade-off. In this paper, we tackle this problem by a hierarchical network, which achieves dynamically reasoning predetermined destinations and future trajectories. A novel graph structure called Intention-Interaction Graph (IIG) is designed to jointly model the self intentions and social interactions. To aggregate information in IIG, Interaction Gated Graph Attention Networks (IGGAN) consisting of a gate mechanism and an attention mechanism is proposed, thus achieving reasoning the influence degree of neighboring pedestrians and destinations. Experimental results on multiple widely used pedestrian trajectory prediction datasets, including two datasets in ETH and three datasets in UCY, demonstrate the effectiveness of the proposed model.