Learning-powered Prediction and Decision-making for Autonomous Driving (LPAD)

About the Special Session

News

Motivation and Scope

One of the key challenges for autonomous driving is to enable vehicles to operate safely and socially alongside human traffic participants. Central to this task is to effectively predict the intents of other road users, forecast their trajectories within a scene, and utilize these predictions to make informed decisions. The prediction task is incredibly challenging since the future motion of road users is affected by various factors, such as dynamics, road conditions, and surrounding agents, and can often exhibit multi-modal behavior. Moreover, how to leverage the prediction models to enable real-time and interaction-aware decision-making is also a challenging task to assure safety, adhere to traffic rules, interact with diverse traffic participants, and meet the needs of passengers. Machine learning-based methods show promise in addressing these challenges and can greatly enhance the performance, scalability, and intelligence of the system, allowing autonomous vehicles to operate in complex driving environments. The use of machine learning-based methods for prediction and decision-making in autonomous driving is a rapidly growing area of research, with a scope that extends from learning decision-making policies to predicting the multi-modal movements of heterogeneous road users for better decision-making. 

This special session aims to present the latest research and invite submissions for new works on cutting-edge learning-based methods for prediction and decision-making problems. We are soliciting original contributions that are not published or currently under consideration by any other journals/conferences.

Topics of interest (not limited to)

• Deep learning for trajectory prediction.

• Behavior/intention prediction for heterogeneous traffic participants.

• Prediction for model-based decision-making, planning, and control.

• Reinforcement learning, imitation learning, and inverse reinforcement learning.

• Decision-making under uncertainty.

• Interaction-aware and personalized decision-making.

• Human-in-the-loop learning and learning from human feedback.

• Human-machine collaboration for autonomous driving.

• Verification and validation of learning-based systems.

• System safety and cyber security of autonomous vehicles.

• Driving scene representation, understanding, and simulation.

• Driving dataset collection in highly interactive scenarios.

 Call For Papers

Authors are invited to submit full-length papers of up to 6 pages for technical content including figures and references. A maximum of 2 additional pages is allowed, but at an extra cost per page. The maximum number of pages is 6 + 2 (with additional cost) = 8. Each paper will undergo a peer-reviewing process by at least two independent reviewers. All the accepted papers, if they are presented at ITSC 2023, will be published in IEEE Xplore and eligible for the journal special issues.

 Submission

1. The submission portal (https://its.papercept.net/conferences/scripts/start.pl) is now open and authors can submit special session papers through the link.

2. Select Submit a contribution to ITSC 2023.

3. Submit as a Special Session Paper with code kaf7g.

Important Dates

•  May 28, 2023: Submission deadline for special session papers 

• July 12, 2023: Notification of paper acceptance 

• August 16, 2023: Final paper submission deadline 

 Program