ITSC 2024 Paper Abstract

Close

Paper WeAT8.1

Zhang, Zhengming (Purdue University), Ding, Zhengming (Tulane University), Chen, Yaobin (Purdue School of Engineering and Technology, IUPUI), Chien, Stanley (Indiana University-Purdue University Indianapolis), Li, Lingxi (Indiana University-Purdue University Indianapolis), Sherony, rini (Toyota Motor North America), Domeyer, Josh (Toyota Motor North America), Tian, Renran (Indiana Univ.-Purdue Univ. Indianapolis)

Intent-Guided Trajectory Prediction for E-Scooter Riders and Bicyclists

Scheduled for presentation during the Regular Session "Modeling, Simulation, and Control of Pedestrians and Cyclists I" (WeAT8), Wednesday, September 25, 2024, 10:30−10:50, Salon 16

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on December 26, 2024

Keywords Sensing, Vision, and Perception, Modeling, Simulation, and Control of Pedestrians and Cyclists, Sensing and Intervening, Detectors and Actuators

Abstract

The rapidly increasing popularity of micromobility devices, such as e-scooters and bicycles, in urban environments underscores the critical need for advanced trajectory prediction models to enhance road safety and facilitate seamless integration into intelligent transportation systems. This study introduces a novel approach to predicting the movements of bicyclists and e-scooter riders by leveraging a unique dataset that combines bird’s-eye and egocentric views, collected from diverse urban settings across the United States. Employing state-of-the-art deep learning techniques, our model significantly outperforms traditional linear and polynomial regression models in terms of Average Displacement Error (ADE) and Final Displacement Error (FDE), demonstrating superior accuracy in forecasting the trajectories of vulnerable road users. Furthermore, our approach incorporates cognitive annotations to predict crossing intentions, enriching the model’s predictive capabilities. The findings highlight the potential of our method to contribute to the development of proactive safety measures and collision avoidance systems, ultimately fostering safer urban mobility landscapes for all road users.

 

 

All Content © PaperCept, Inc.


This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2024 PaperCept, Inc.
Page generated 2024-12-26  13:37:19 PST  Terms of use