← Back to the feed
Energy & materialsResearch findings

Development of a Data-Driven Simulation Model for Collision Avoidance Behavior

Original published 2026.05.29 21:15 KSTAdded to Blackdeck 2026.11.22 19:17 KST

What has changed?

A collision mechanism is integrated into the loss function of a data-driven model.

Key points

  1. A data-driven model to reduce collisions in pedestrian movement simulation is proposed.
  2. Collision rates in bidirectional flows are reduced to levels comparable with controlled experiments.
  3. Lane formation and N-curves in bidirectional flows are effectively reproduced using lateral acceleration-based loss function.

Connect it to your work

Collision rates in bidirectional flows are reduced to levels comparable with controlled experiments.

What remains unproven

The abstract reports simulation results; real-world performance is not established by this input.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivSimulation of collision avoidance behavior in crowd movement by data-driven approach