Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 17, 2026Journal of Intelligent and Connected VehiclesOpen Access

Prior-knowledge-guided model-based reinforcement learning for integrated longitudinal-lateral control of vehicular platoons

View Full Paper
Ask AI
Bookmark
Share

Authors

XWXia WuHMHaigen MinZMZihao Mao

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improvements in vehicle platoon control, indicating better stability and safety.

Key Points

  • This research aims to improve the control of vehicular platoons using a novel model-based reinforcement learning method that integrates prior knowledge.
  • Proposed a model-based reinforcement learning (MBRL) approach with planning capabilities for vehicle platoon control.
  • Designed a unified state space and joint action space for two-dimensional control along with a multidimensional reward function.
  • Introduced a prior-knowledge-guided exploration strategy to enhance training efficiency and accelerate convergence.
  • The new method significantly enhanced training efficiency compared to traditional approaches.
  • In evaluations, improved longitudinal-lateral control and platoon stability were observed, supporting safer maneuvers in varied scenarios.
  • Demonstrated high computational efficiency alongside enhanced adaptability in real-data scenarios.

Cite This Study

Wu et al. (2026) studied this question.

synapsesocial.com/papers/6a095b5d7880e6d24efe1116https://doi.org/10.26599/jicv.2026.9210083
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Robust Longitudinal Control for Vehicular Platoons Using Deep Reinforcement Learning2024 · 11 citations
  2. 2Knowledge-guided reinforcement learning for robust vehicle platoon control under communication and actuator failures2026
  3. 3Collaborative Control of Vehicle Platoon based on Deep Reinforcement Learning2024 · 24 citations
  4. 4Physics-informed platooning with learning-augmented calibration and compensation: a real-world study2026
  5. 5Model-data-driven control for human-leading vehicle platoon2024 · 2 citations