Probabilistic Crowd GAN: Multimodal Pedestrian Trajectory Prediction Using a Graph Vehicle-Pedestrian Attention Network

Abstract

Understanding and predicting the intention of pedestrians is essential to enable autonomous vehicles and mobile robots to navigate crowds. This problem becomes increasingly complex when we consider the uncertainty and multimodality of pedestrian motion, as well as the implicit interactions between members of a crowd, including any response to a vehicle. Our approach, Probabilistic Crowd GAN, extends recent work in trajectory prediction, combining Recurrent Neural Networks (RNNs) with Mixture Density Networks (MDNs) to output probabilistic multimodal predictions, from which likely modal paths are found and used for adversarial training. We also propose the use of Graph Vehicle-Pedestrian Attention Network (GVAT), which models social interactions and allows input of a shared vehicle feature, showing that inclusion of this module leads to improved trajectory prediction both with and without the presence of a vehicle. Through evaluation on various datasets, we demonstrate improvements on the existing state of the art methods for trajectory prediction and illustrate how the true multimodal and uncertain nature of crowd interactions can be directly modelled.

Vehicle Motion State Prediction Method Integrating Point Cloud Time Series Multiview Features and Multitarget Interactive Information

“…In complex urban scenes, the future movement of targets and cars is affected by the movement of other objects and the spatial environment. To improve the accuracy of trajectory prediction by addressing complexity, researchers have begun to model the social interaction between multiple objects and the constraints of scene context based on object trajectory prediction [31][32][33][34][35]. Alahi et al [36] proposed the social LSTM model, which captured the social interaction of the target by running a maximum pool of the state vector of the nearby target within a predefined distance range.…”

A Survey on Motion Prediction of Pedestrians and Vehicles for Autonomous Driving

“…The work presented here gives an insight into developing and employing the existing motion models for pedestrians and vehicles in autonomous driving applications with the possibility of expanding this study to all road agent classes in future. CNN [36] CNN [37] Scene-aware LSTM+CNN [47] Interaction-aware LSTM [23] Scene+Interactionaware LSTM [24] LSTM+CNN [25] Map+Interactionaware CNN [63] CNN [61] Multimodal Interactionaware LSTM+GAN [29] LSTM+GAN [53] Scene+Interactionaware RNN [54] GAN+LSTM [55] CNN+LSTM+GAN [28] Occupancy Map Map-aware DBN [21] Vehicle Intention Interactionaware CNN [40] CNN [41] CNN [42] GRU [44] Map-aware SVM [43] Unimodal Unaware Clustering [33] Clustering [34] Clustering [35] Interactionaware DBN [22] LSTM [26] LSTM+GAN [30] Map-aware RNN [50] Map+Interactionaware CNN [63] CNN [61] Multimodal Scene+Interactionaware LSTM+CNN [27] CNN+LSTM+GAN [28] Interaction-aware CNN [52] Occupancy CA [17] Map-aware Particle filter [16] Vehicle Unaware CA [14] Kalman filter [15] CTRA [18] CTRV [19] Map-aware IMM [20]…”

A novel method of predictive collision risk area estimation for proactive pedestrian accident prevention system in urban surveillance infrastructure

“…Thus, we designed the prediction networks and trained trajectories by test spots. Much research has been conducted on forecasting object's trajectory using social graph convolutional LSTM [42], spatiotemporal graph transformer networks [43], probabilistic crowd GAN [44] based on deep learning methods. These studies handled only one class's trajectory forecast, but our study aims to predict trajectory in interactive situations between vehicle and pedestrian.…”