Effectiveness verification of trajectory planning using quantum inspired machine at highway merging

Koji Oya･Kota Matsuura･Kenshin Yamamoto (MIRISE Technologies)

At the JSAE 2025 Autumn Congress, we presented a trajectory planning using a quantum-inspired machine for combinatorial optimization. We conducted trajectory planning simulations based on actual traffic scenario and verified the effectiveness of the proposed method by comparing the simulation results with real-world data.

A data-driven algorithm development framework leveraging multiple interactive simulator

Shohei Kobe･Akira Ito (Aichi Institute of Technology)･Ken Kinjo･Yuki Asada (DENSO)･Fumitake Tsuji･Kohichi Yoshioka･Kazunori Ban (Toyota Technical Development)

While data-driven algorithms enable flexible decision-making where rule-based approaches struggle, achieving the required functionality often requires large volume of training data. This study proposes a development framework that enables data-efficient acquisition of this functionality from a small amount of simulator-generated training data guided by functional requirements.

Road Adaptive Control with Haptic Steer-by-Wire

Yusuke Yamanaka･Hiroaki Kuwahara (Shibaura Institute of Technology)

This study develops a Steer-by-Wire system using bilateral control to precisely feed back road reaction forces to the driver. Furthermore, based on the acquired road information, the system suppresses unstable driving conditions. This approach aims to achieve both realistic steering feel and vehicle stability. The effectiveness of the proposed system was verified through simulations and experiments.

Design of an Autonomous Distributed Four-Wheel Independent Drive and Steering Control System Based on Broadcast Control

Akira Ito (Aichi Institute of Technology)･Shun-ichi Azuma (Kyoto University)

This study addresses the problem of distributing driving force and steering angle for a vehicle equipped with corner modules capable of independent four-wheel drive and steering. As a new approach replacing conventional rule-based methods, we propose an autonomous distributed allocation rule using broadcast control based on multi-agent control theory.

Optimization and Development of a 48V Cooling Fan System with Direct Control Strategy Based on TMD Controller

CHANWOONG JO (Hyundai Motor)

This paper proposes a method to optimize and directly control 48V cooling fan motors in vehicle thermal energy systems, replacing traditional 12V systems. The 48V system reduces power loss and is suitable for high-power loads. Through design optimization, it achieved a 4% efficiency improvement, 300g weight reduction, and 10mm thickness reduction. The Field-Oriented Control (FOC) method was applied for flexible adaptation to various motor specifications. Twenty control parameters were identified, and their effectiveness was validated through testing. This research is planned to be applied to future Software Defined Vehicle (SDV) development.

Driving Risk prediction over a repetitive driving pattern

Michele Guagnano (Politecnico di Torino)･Yecan Wang･Shigenobu Mitsuzawa (Honda Motor R&D Co., Ltd)･Massimo Violante (Politecnico di Torino)･Riccardo Groppo (Sleep Advice Technologies)

Road traffic accidents remain a major global issue, yet professional drivers face a distinct and often underestimated risk: long-term exposure to repetitive routes. To address this, we conducted a longitudinal study with 54 participants over a 12-day protocol, performing 4 consecutive laps during each day on a simulator on a repetitive track to replicate routine shifts. The resulting dataset fuses driving, eye-tracking metrics, and physiological features. An ML model was trained to predict the risk level of a lap with data from the previous one. The model was validated with a K-Fold approach, by achieving a mean accuracy of 91%.