Human Trajectory Forecasting in Crowds: A Deep Learning Perspective

Abstract

Since the past few decades, human trajectory forecasting has been a field of active research owing to its numerous real-world applications: evacuation situation analysis, deployment of intelligent transport systems, traffic operations, to name a few. In this work, we cast the problem of human trajectory forecasting as learning a representation of human social interactions. Early works handcrafted this representation based on domain knowledge. However, social interactions in crowded environments are not only diverse but often subtle. Recently, deep learning methods have outperformed their handcrafted counterparts, as they learn about human-human interactions in a more generic data-driven fashion. In this work, we present an in-depth analysis of existing deep learning-based methods for modelling social interactions. We propose two domainknowledge inspired data-driven methods to effectively capture these social interactions. To objectively compare the performance of these interaction-based forecasting models, we develop a large scale interaction-centric benchmark TrajNet++, a significant yet missing component in the field of human trajectory forecasting. We propose novel performance metrics that evaluate the ability of a model to output socially acceptable trajectories. Experiments on TrajNet++ validate the need for our proposed metrics, and our method outperforms competitive baselines on both real-world and synthetic datasets.

Asymmetrical Bi-RNN for pedestrian trajectory encoding

“…We based our experiments on the Trajnet++ LSTM baseline [3] with respect to a variety of interaction modules: directional, occupancy and social pooling. All hyper-parameters except for the encoder remained unchanged.…”

“…2) An interaction module for taking into account the neighbors trajectories. The most common way to take into account the effect of interactions between agents in their trajectories is to decode the past positions while pooling on a spatial grid with either the neighbors' positions, their relative velocities [3], or their RNN hidden states [1]. This last approach is very popular and is known under the name of social pooling.…”

“…Using the recent Trajnet++ benchmark [3] and with respect to various available learning architectures that forecast pedestrians trajectories, we evaluate the effectiveness of U-RNNs for efficient pedestrian trajectories encoding. We then provide insight into designing improved motion encoders prior to the application of interaction modules for the task of pedestrian trajectory prediction.…”

DeepPTP: A Deep Pedestrian Trajectory Prediction Model for Traffic Intersection

“…It fully simulates the interaction among groups in social activities. Kothari et al [7] proposed a knowledge-based data method (TrajNet++) for large-scale interaction between pedestrian trajectories. The TrajNet++ is composed of motion encoding-decoding module and interactive module.…”

“…However, this kind of influence among nodes will gradually decrease or even disappear are transferred in the recursive unit in the traditional recurrent neural network as the features. The equation of the dilation convolution is shown in (7). The d is the dilation factor, which changes by an exponent of 2 according to the depth of the network.…”