ITSC 2024 Paper Abstract

Close

Paper ThAT1.2

Liu, Yupei (Beijing Institute of Technology), Chen, Danni (Beijing Institute of Technology), Lu, Chao (Beijing Institute of Technology), Lu, Hongliang (The Hong Kong University of Science and Technology (Guangzhou)), Meixin Zhu, Meixin (University of Washington)

A Hippocampus-Inspired Dynamic Planning Method for Overtaking Scenes Via Predictive Map

Scheduled for presentation during the Invited Session "Learning-powered and Knowledge-driven Autonomous Driving I" (ThAT1), Thursday, September 26, 2024, 10:50−11:10, Salon 1

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 8, 2024

Keywords Automated Vehicle Operation, Motion Planning, Navigation

Abstract

Motion planning is particularly critical for a reliable autonomous driving system. A dependable motion planning system must prioritize safety, comfort, and efficiency. To adapt to the complex and dynamic traffic environment, motion planning must account for the potential reactions of other traffic participants, anticipating their future movements or actions to ensure the safety and stability of the planning. Recent research on cognitive behavioral science has revealed the crucial role of the human hippocampus in integrating prediction and planning. Based on this, a brand-new synergized planning method based on a Hippocampus-plausible predictive map is proposed in this paper. The effectiveness of the proposed method was demonstrated in the overtaking scenarios with heavy traffic which indicated comprehensive improvement in planning safety, efficiency, and comfort.

 

 

All Content © PaperCept, Inc.


This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2024 PaperCept, Inc.
Page generated 2024-10-08  15:23:47 PST  Terms of use