Dan Negrut
University of Wisconsin - Madison
Mechanical Engineering
Radu Serban
University of Wisconsin - Madison
Mechanical Engineering

Final Report

View PDF|

Final Report Summary

View PDF|




Developing an Open Source Multi-Agent Simulation Environment for Connected Autonomous Vehicles (CAVs)

This SAFER-SIM project will use simulation technology to address three pressing safety topics: (1) automated vehicles technology; (2) connected vehicles technology; and (3) distributed simulation technology. Specifically, the project seeks to implement and demonstrate components of a comprehensive multi-agent simulation platform for autonomous vehicles. This connected autonomous vehicle simulation framework, called Synchrono, will accelerate and democratize research and development activities in the field of autonomous navigation by creating a software platform that allows rapid, low-cost and risk-free testing of novel designs, methods and software components. Synchrono is : (a) heterogeneous and multi-agent, in that it supports the simulation of heterogeneous traffic scenarios involving conventional, assisted, and autonomous vehicles, as well as pedestrians and cyclists; (b) open platform, as it allows any client that subscribes to a common API to remotely plug in and engage in traffic scenarios that bring together, for instance, Ford, GM, and Toyota AVs in a setup that protects their IP; (c) vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication emulation ready, owing to its ability to simulate the V2V and V2I data exchange as enabled in real-world scenarios by ad-hoc dedicated short range communication (DSRC) protocols; and (d) open-source, as the software will be available under a BSD3 license in a public repository for unrestricted use and redistribution.

Supporting links:
TRID Record
UW Dataset