D-AWSIM: Distributed Autonomous Driving Simulator for Dynamic Map Generation Framework

TL;DR

D-AWSIM is a distributed simulation platform that enables large-scale urban traffic and dynamic map generation for autonomous driving research, reducing costs and regulatory hurdles.

Contribution

The paper introduces D-AWSIM, a novel distributed simulator that scales up urban traffic scenarios and dynamic map generation for autonomous driving systems.

Findings

D-AWSIM significantly increases throughput for vehicle and sensor data processing.

The framework supports large-scale urban traffic scenario simulation.

Integration with Autoware demonstrates practical applicability.

Abstract

Autonomous driving systems have achieved significant advances, and full autonomy within defined operational design domains near practical deployment. Expanding these domains requires addressing safety assurance under diverse conditions. Information sharing through vehicle-to-vehicle and vehicle-to-infrastructure communication, enabled by a Dynamic Map platform built from vehicle and roadside sensor data, offers a promising solution. Real-world experiments with numerous infrastructure sensors incur high costs and regulatory challenges. Conventional single-host simulators lack the capacity for large-scale urban traffic scenarios. This paper proposes D-AWSIM, a distributed simulator that partitions its workload across multiple machines to support the simulation of extensive sensor deployment and dense traffic environments. A Dynamic Map generation framework on D-AWSIM enables researchers to explore information-sharing strategies without relying on physical testbeds. The evaluation shows that D-AWSIM increases throughput for vehicle count and LiDAR sensor processing substantially compared to a single-machine setup. Integration with Autoware demonstrates applicability for autonomous driving research.