Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 26, 2025ElectronicsOpen Access

Collision Risk Assessment of Lane-Changing Vehicles Based on Spatio-Temporal Feature Fusion Trajectory Prediction

View Full Paper
Ask AI
Bookmark
Share

Authors

HSHongtao SuXidian UniversityNWNing WangMacau University of Science and TechnologyXWXiangmin WangTongji University

Discussion

Loading...

Member takes

Implication

The framework utilizes spatio-temporal feature fusion to improve collision risk prediction in vehicles, suggesting enhanced safety.

Key Points

  • Collision risk index improved long-horizon accuracy, providing earlier warnings during lane changes.
  • Average RMSE reductions of 0.02 m, 0.12 m, and 0.26 m demonstrate the method's effectiveness over a GAT-Transformer baseline.
  • Assessment utilized probabilistic trajectory forecasts on the HighD dataset to compute collision probability and intensity.
  • Implications include potential for early deceleration and informed decisions in lane-change scenarios.

Cite This Study

Su et al. (2025) studied this question.

synapsesocial.com/papers/68af6210ad7bf08b1eae3388https://doi.org/10.3390/electronics14173388
View Full Paper
Ask AI
Bookmark
Share