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

TL;DR

This work tackles safety assurance for autonomous driving across diverse conditions by enabling information sharing through a Dynamic Map (DM) generated from distributed simulations. The authors introduce D-AWSIM, a multi-machine simulator that partitions computation across hosts and clients and integrates with Netcode for GameObjects to scale AWSIM-based simulations. A three-layer DM framework processes data in real time via edge-cloud streaming and in-memory DSMS, enabling DM generation without real-world testbeds and supporting external applications like Autoware. Evaluation shows improved data throughput and scalability up to about 240 vehicles, with a practical demonstration of DM integration boosting proactive obstacle avoidance, highlighting the DM’s potential to advance cooperative driving research and safety analyses.

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.

Figures (9)

• Figure 1: Overview diagram illustrating D-AWSIM interconnection flow.
• Figure 2: Handled data in the Dynamic Map.
• Figure 3: Overview of generation of Dynamic Map.
• Figure 4: Overview diagram illustrating D-AWSIM interconnection flow.
• Figure 5: Overview of the local list.