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

by   Kunming Li, et al.

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 (ADE) and 12


page 1

page 3

page 4

page 5


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

Understanding and predicting the intention of pedestrians is essential t...

Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction

Understanding crowd motion dynamics is critical to real-world applicatio...

Socially Aware Crowd Navigation with Multimodal Pedestrian Trajectory Prediction for Autonomous Vehicles

Seamlessly operating an autonomous vehicle in a crowded pedestrian envir...

Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction

Better machine understanding of pedestrian behaviors enables faster prog...

Autonomous Vehicle Speed Control for Safe Navigation of Occluded Pedestrian Crosswalk

Both humans and the sensors on an autonomous vehicle have limited sensin...

AVGCN: Trajectory Prediction using Graph Convolutional Networks Guided by Human Attention

Pedestrian trajectory prediction is a critical yet challenging task, esp...

A Follow-the-Leader Strategy using Hierarchical Deep Neural Networks with Grouped Convolutions

The task of following-the-leader is implemented using a hierarchical Dee...

Please sign up or login with your details

Forgot password? Click here to reset