ITSC 2025 Paper Abstract

Paper FR-LM-T41.2

Kim, Dohee (Hyundai Motor Company), Seo, Youngwon (Kookmin University), Choi, Yongkeun (Eric) (University of California, Berkeley), Joa, Eunhyek (Zoox), Lee, Sang Ho (Hyundai Motor Company), Jeong, Gu-Min (Kookmin University), Borrelli, Francesco (University of California, Berkeley)

Energy-Optimal Multi-Modal Speed Planning and Following System for Connected Electrified Vehicles: Realistic V2X Communication-Based Experimental Analyses

Scheduled for presentation during the Regular Session "S41a-Motion Planning, Trajectory Optimization, and Control for Autonomous Vehicles" (FR-LM-T41), Friday, November 21, 2025, 10:50−11:10, Broadbeach 1&2

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Keywords Real-time Motion Planning and Control for Autonomous Vehicles in ITS Networks, Real-world ITS Pilot Projects and Field Tests, Driver Behavior Monitoring and Feedback Systems for Semi-autonomous Vehicles

Abstract

In this paper, we discuss a service-oriented, energy-optimal deceleration planning and following system (EDPS) for electrified vehicles. This system maximizes regenerative energy by using preview information and is integrated with realistic vehicle-to-everything (V2X) communication. We explore the subsequent processes and issues associated with this integration. Also, the multi-modal attention algorithm is proposed to ensure that EDPS can explicitly hold multi-modality satisfying target deceleration distance and speed at the destination, while achieving energy-optimal performance by learning feasible deceleration sets. To verify the performance of the service-oriented EDPS in conjunction with actual V2X communication environments and a real vehicle, an experimental environment has been set up. Through experiments that closely resemble real-world conditions, the EDPS received continuous traffic light information while performing multi-modal energy-optimal speed planning, demonstrating practical ecological approach (Eco-Approach) performance while tracking the planned profile. Additionally, the comparative results showed that the EDPS has an energy recovery effect that is more than 30 % greater compared to the deceleration of typical human drivers.