United States Department of Transportation
i
Deep-Learning Based Trajectory Forecast for Safety of Intersections with Multimodal Traffic (Phase II)
-
2020-08-01
[PDF-1.13 MB]
Details:
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
Resource Type:
-
Geographical Coverage:
-
Edition:Final Report
-
Corporate Publisher:
-
Abstract:Predicting pedestrian trajectories is of major importance for several applications including autonomous driving and surveillance systems. In autonomous driving, an accurate prediction of pedestrians trajectories enables the controller to plan ahead the motion of the vehicle in an adversarial environment. For example, it is a critical component for collision avoidance systems or emergency braking systems. In general traffic collision avoidance systems, such component would be very important in the synthesis of controller actions, preventing a collision. The objective of this report is to introduce a novel computational method for solving the trajectory prediction problem, using a combination of artificial neural networks (convolutional neural networks) and graph theory.
-
Format:
-
Funding:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type:
