MapsTP: HD Map Images Based Multimodal Trajectory Prediction for Automated Vehicles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sharma, Sushil, Das, Arindam, Sistu, Ganesh, Halton, Mark, Eising, Ciarán
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912052492107776
author Sharma, Sushil
Das, Arindam
Sistu, Ganesh
Halton, Mark
Eising, Ciarán
author_facet Sharma, Sushil
Das, Arindam
Sistu, Ganesh
Halton, Mark
Eising, Ciarán
contents Predicting ego vehicle trajectories remains a critical challenge, especially in urban and dense areas due to the unpredictable behaviours of other vehicles and pedestrians. Multimodal trajectory prediction enhances decision-making by considering multiple possible future trajectories based on diverse sources of environmental data. In this approach, we leverage ResNet-50 to extract image features from high-definition map data and use IMU sensor data to calculate speed, acceleration, and yaw rate. A temporal probabilistic network is employed to compute potential trajectories, selecting the most accurate and highly probable trajectory paths. This method integrates HD map data to improve the robustness and reliability of trajectory predictions for autonomous vehicles.
format Preprint
id arxiv_https___arxiv_org_abs_2407_05811
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MapsTP: HD Map Images Based Multimodal Trajectory Prediction for Automated Vehicles
Sharma, Sushil
Das, Arindam
Sistu, Ganesh
Halton, Mark
Eising, Ciarán
Computer Vision and Pattern Recognition
Predicting ego vehicle trajectories remains a critical challenge, especially in urban and dense areas due to the unpredictable behaviours of other vehicles and pedestrians. Multimodal trajectory prediction enhances decision-making by considering multiple possible future trajectories based on diverse sources of environmental data. In this approach, we leverage ResNet-50 to extract image features from high-definition map data and use IMU sensor data to calculate speed, acceleration, and yaw rate. A temporal probabilistic network is employed to compute potential trajectories, selecting the most accurate and highly probable trajectory paths. This method integrates HD map data to improve the robustness and reliability of trajectory predictions for autonomous vehicles.
title MapsTP: HD Map Images Based Multimodal Trajectory Prediction for Automated Vehicles
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.05811