본문 바로가기
  • Home

Adaptive Hierarchical Control of Warning and Trajectory for Energy-Efficient Autonomous Driving

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2025, 30(8), pp.1~9
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : July 7, 2025
  • Accepted : August 19, 2025
  • Published : August 29, 2025

Da-Eun Ji 1 Beak-Cheol Jang 1

1연세대학교

Accredited

ABSTRACT

Given the increasing complexity of intelligent transportation systems, the joint optimization of warning mechanisms and vehicle control has emerged as a critical challenge. This paper proposes a hierarchical optimization framework that integrates warning range optimization at the upper level with energy–time balanced vehicle control at the lower level. In the upper level, the warning range, which defines the spatial scope of risk perception, is determined based on road conditions and traffic density, while in the lower level, Second-Order Cone Programming (SOCP) is employed to simultaneously minimize energy consumption and travel time within the selected range. To overcome the limitations of static weight-based approaches, an adaptive weight tuning mechanism is introduced, combining grid search with gradient-norm feedback. The proposed framework demonstrates consistent convergence across diverse simulation settings, and its validity is confirmed through analyses of cost function reduction and weight sensitivity. These findings indicate that the framework can go beyond conventional path planning or single-objective optimization, offering a robust control strategy that ensures stability, efficiency, and adaptability in real-world driving environments.

Citation status

* References for papers published after 2024 are currently being built.