Improving Multi-Agent Trajectory Prediction Using Traffic States on Interactive Driving Scenarios

Mohan, C. Krishna and Babu, Sobhan (2023) Improving Multi-Agent Trajectory Prediction Using Traffic States on Interactive Driving Scenarios. IEEE Robotics and Automation Letters, 8 (5). pp. 2708-2715. ISSN 2377-3766

Text
ieee_rob_aut_let_8-5.pdf - Published Version
Download (1MB)

Abstract

Predicting trajectories of multiple agents in interactive driving scenarios such as intersections, and roundabouts are challenging due to the high density of agents, varying speeds, and environmental obstacles. Existing approaches use relative distance and semantic maps of intersections to improve trajectory prediction. However, drivers base their driving decision on the overall traffic state of the intersection and the surrounding vehicles. So, we propose to use traffic states that denote changing spatio-temporal interaction between neighboring vehicles, to improve trajectory prediction. An example of a traffic state is a clump state which denotes that the vehicles are moving close to each other, i.e., congestion is forming. We develop three prediction models with different architectures, namely, Transformer-based (TS-Transformer), Generative Adversarial Network-based (TS-GAN), and Conditional Variational Autoencoder-based (TS-CVAE). We show that traffic state-based models consistently predict better future trajectories than the vanilla models. TS-Transformer produces state-of-the-art results on two challenging interactive trajectory prediction datasets, namely, Eye-on-Traffic (EOT), and INTERACTION. Our qualitative analysis shows that traffic state-based models have better aligned trajectories to the ground truth.

[error in script]

IITH Creators:

IITH Creators	ORCiD
Mohan, C. Krishna	https://orcid.org/0000-0002-7316-0836
Babu, Sobhan	UNSPECIFIED

Item Type:

Article

Uncontrolled Keywords:

conditional variational autoencoder; generative adversarial networks; Trajectory prediction; transformers; Hidden Markov models; Auto encoders; Conditional variational autoencoder; Decoding; Hidden-Markov models; Predictive models; Road; Traffic state; Trajectory prediction; Transformer; Decoding; Forecasting; Generative adversarial networks; Learning systems; Multi agent systems; Semantics; Traffic congestion; Trajectories; Vehicles

Subjects:

Computer science
Computer science > Computer programming, programs, data

Divisions:

Department of Computer Science & Engineering

Depositing User:

Mr Nigam Prasad Bisoyi

Date Deposited:

28 Sep 2023 10:44

Last Modified:

28 Sep 2023 10:44

URI:

http://raiithold.iith.ac.in/id/eprint/11710