Attentional-GCNN: Adaptive Pedestrian Trajectory Prediction towards Generic Autonomous Vehicle Use Cases

TL;DR

The paper introduces Attentional-GCNN, a novel graph neural network model for pedestrian trajectory prediction that accounts for uncertainty and is suitable for real-world autonomous vehicle scenarios, outperforming existing methods.

Contribution

It proposes a new GCNN-based model with attention mechanisms for probabilistic pedestrian trajectory prediction, trained on a novel real-world dataset, improving accuracy and inference speed.

Findings

Achieves 10% improvement in Average Displacement Error

Achieves 12% improvement in Final Displacement Error

Provides fast inference suitable for real-time autonomous vehicle use

Abstract

Autonomous vehicle navigation in shared pedestrian environments requires the ability to predict future crowd motion both accurately and with minimal delay. Understanding the uncertainty of the prediction is also crucial. Most existing approaches however can only estimate uncertainty through repeated sampling of generative models. Additionally, most current predictive models are trained on datasets that assume complete observability of the crowd using an aerial view. These are generally not representative of real-world usage from a vehicle perspective, and can lead to the underestimation of uncertainty bounds when the on-board sensors are occluded. Inspired by prior work in motion prediction using spatio-temporal graphs, we propose a novel Graph Convolutional Neural Network (GCNN)-based approach, Attentional-GCNN, which aggregates information of implicit interaction between pedestrians in a crowd by assigning attention weight in edges of the graph. Our model can be trained to either output a probabilistic distribution or faster deterministic prediction, demonstrating applicability to autonomous vehicle use cases where either speed or accuracy with uncertainty bounds are required. To further improve the training of predictive models, we propose an automatically labelled pedestrian dataset collected from an intelligent vehicle platform representative of real-world use. Through experiments on a number of datasets, we show our proposed method achieves an improvement over the state of art by 10% Average Displacement Error (ADE) and 12% Final Displacement Error (FDE) with fast inference speeds.