Vehicle Trajectory Prediction at Intersections using Interaction based Generative Adversarial Networks

Roy, Debaditya and Ishizaka, Tetsuhiro and krishna Mohan, C and et al, . (2019) Vehicle Trajectory Prediction at Intersections using Interaction based Generative Adversarial Networks. In: IEEE Intelligent Transportation Systems Conference (ITSC), 27-30 October 2019, Auckland, New Zealand.

Full text not available from this repository. (Request a copy)


Vehicle trajectory prediction at intersections is both essential and challenging for autonomous vehicle navigation. This problem is aggravated when the traffic is predominantly composed of smaller vehicles that frequently disobey lane behavior as is the case in many developing countries. Existing macro approaches consider the trajectory prediction problem for lane-based traffic that cannot account when there is a high disparity in vehicle size and driving behavior among different vehicle types. Hence, we propose a vehicle trajectory prediction approach that models the interaction among different types of vehicles with vastly different driving styles. These interactions are encapsulated in the form of a social context embedded in a Generative Adversarial Network (GAN) to predict the trajectory of each vehicle at either a signalized or non-signalized intersection. The GAN model produces the most acceptable future trajectory among many choices that conform to past driving behavior as well as the trajectories of neighboring vehicles. We evaluate the proposed approach on aerial videos of intersections recorded in China where lane discipline is not followed by vehicles. The proposed GAN based approach demonstrates 6.4% relative improvement in predicting trajectories over state-of-the-art.

[error in script]
IITH Creators:
IITH CreatorsORCiD
krishna Mohan, CUNSPECIFIED
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Indexed in Scopus
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: Team Library
Date Deposited: 14 Jan 2020 04:22
Last Modified: 14 Jan 2020 04:22
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 7318 Statistics for this ePrint Item