SLEDGE: Synthesizing Simulation Environments for Driving Agents with Generative Models

arXiv:2403.17933v1 Announce Type: cross
Abstract: SLEDGE is the first generative simulator for vehicle motion planning trained on real-world driving logs. Its core component is a learned model that is able to generate agent bounding boxes and lane graphs. The model's outputs serve as an initial state for traffic simulation. The unique properties of the entities to be generated for SLEDGE, such as their connectivity and variable count per scene, render the naive application of most modern generative models to this …

abstract agent agents arxiv core cs.ai cs.cv cs.lg cs.ro driving environments generate generative generative models graphs logs motion planning planning serve simulation simulator state traffic type world