Customized Co-Simulation Environment for Autonomous Driving Algorithm Development and Evaluation
- 6 April 2021
- conference paper
- conference paper
- Published by SAE International in SAE International Journal of Advances and Current Practices in Mobility
Abstract
Deployment of autonomous vehicles requires an extensive evaluation of developed control, perception, and localization algorithms. Therefore, increasing the implemented SAE level of autonomy in road vehicles requires extensive simulations and verifications in a realistic simulation environment before proving ground and public road testing. The level of detail in the simulation environment helps ensure the safety of a real-world implementation and reduces algorithm development cost by allowing developers to complete most of the validation in the simulation environment. Considering sensors like camera, LiDAR, radar, and V2X used in autonomous vehicles, it is essential to create a simulation environment that can provide these sensor simulations as realistically as possible. While sensor simulations are of crucial importance for perception algorithm development, the simulation environment will be incomplete for the simulation of holistic AV operation without being complemented by a realistic vehicle dynamic model and traffic co-simulation. Therefore, this paper investigates existing simulation environments, identifies use case scenarios, and creates a co-simulation environment to satisfy the simulation requirements for autonomous driving function development using the Carla simulator based on the Unreal game engine for the environment, Sumo or Vissim for traffic co-simulation, Carsim or Matlab/Simulink for vehicle dynamics co-simulation and Autoware or the authors’ or users’ own routines for autonomous driving algorithm co-simulation. As a result of this work, a model-based vehicle dynamics simulation with realistic sensor simulation and traffic simulation is presented. A sensor fusion methodology is implemented in the created simulation environment as a use case scenario. The results of this work will be a valuable resource for researchers who need a comprehensive co-simulation environment to develop connected and autonomous driving algorithms.This publication has 24 references indexed in Scilit:
- Real time implementation of socially acceptable collision avoidance of a low speed autonomous shuttle using the elastic band methodMechatronics, 2018
- AirSim: High-Fidelity Visual and Physical Simulation for Autonomous VehiclesPublished by Springer Science and Business Media LLC ,2017
- A hybrid electric vehicle hardware-in-the-loop simulator as a development platform for energy management algorithmsInternational Journal of Vehicle Design, 2016
- The potential of collective perception in vehicular ad-hoc networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Automated Robust Path Following Control Based on Calculation of Lateral Deviation and Yaw Angle ErrorPublished by ASME International ,2015
- Object scene flow for autonomous vehiclesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Lateral stability control of fully electric vehiclesInternational Journal of Automotive Technology, 2015
- Robust PID Steering Control in Parameter Space for Highly Automated DrivingInternational Journal of Vehicular Technology, 2014
- A new performance measure and evaluation benchmark for road detection algorithmsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013