Probabilistic Generative Modeling for Procedural Roundabout Generation for Developing Countries

TL;DR

This paper introduces a probabilistic generative model using GFlowNets to create diverse and valid roundabout designs for developing countries, addressing resource constraints and the need for robust transportation network planning.

Contribution

The work formulates roundabout generation as a Markov decision process and applies GFlowNets to improve diversity and validity in road network design.

Findings

Achieves higher diversity in generated roundabouts

Maintains high validity scores in generated designs

Outperforms related methods in empirical tests

Abstract

Due to limited resources and fast economic growth, designing optimal transportation road networks with traffic simulation and validation in a cost-effective manner is vital for developing countries, where extensive manual testing is expensive and often infeasible. Current rule-based road design generators lack diversity, a key feature for design robustness. Generative Flow Networks (GFlowNets) learn stochastic policies to sample from an unnormalized reward distribution, thus generating high-quality solutions while preserving their diversity. In this work, we formulate the problem of linking incident roads to the circular junction of a roundabout by a Markov decision process, and we leverage GFlowNets as the Junction-Art road generator. We compare our method with related methods and our empirical results show that our method achieves better diversity while preserving a high validity score.