The autonomous vehicle will be accepted and certified for widespread use if its software is verified and validated as safe or safer than a human equivalent. One of the main verification criteria is safe interaction with other road users. Based on studies, real-road testing is not practical for safety validation due to its time and cost consuming. Therefore, Simulating miles driven is the only feasible way to overcome this limitation. The primary goal of the related research project is to develop advanced techniques in the human-robot interaction (HRI) safety validation area by usage of immersive simulation technologies. Developing methods for the creation of the simulation environment will enable us to make experiments in a digital environment rather than real. The main aim of the paper is to develop an effective method of creating a virtual environment for performing simulations on industrial robots, mobile robots and autonomous vehicles (AV-s) from the safety perspective for humans. Simulating real-life elements like grass, trees, buildings, etc. will not only make the simulations more realistic but will aid in matching the simulated data to the recorded one. This will allow more efficient testing of autonomous vehicles and help reduce errors. Therefore, developing efficient methods for mapping real environments and simulating their variables is crucial for the development of autonomous vehicles. An unmanned Aerial Vehicle was used to collect aerial imagery from the specific area where the simulations will perform. These geotagged images were utilized in the mapping process. The prepared map creates a virtual environment for the Autoware software, which is the software of the real AV shuttle. With the aim of virtual sensors and lidars, the vehicle can be localized in the virtual map and is ready to examine the different scenarios. Different scenarios are variations of distinct situations that AV shuttle interact with other road users such as pedestrians or other vehicles. High potential risk scenarios were tested and the reaction of the AV was monitored. Then based on the decisions, which it makes, the control algorithms were developed and verified also the HRI system that is the main scope of our research was evaluated. Furthermore, the geospatial data can be collected by using Lidars instead of RGB cameras. Lidars allow creating point-cloud maps. As Lidar was utilized in the real AV, the test results of the virtual sensor in the virtual environment, which was created with the Lidar, would be close to reality.


Virtual Simulations Environment Development for Autonomous Vehicles Interaction

Division / Sponsors: 
Aerospace, Bioengineering, Applied Mechanics, Design Engineering Division, Advanced Energy Systems, Manufacturing Engineering Division, Noise Control and Acoustics, Nondestructive Evaluation, Diagnosis, and Prognosis (NDPD), Nuclear Engineering Division, Process Industries Division, Fluids Engineering, Heat Transfer, Materials, Microelectromechanical Systems, Safety Engineering and Risk Analysis, Computers & Information in Engineering


Paper Proceedings: https://asmedigitalcollection.asme.org/IMECE/IMECE2020/volume/84478

IMECE2020 - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.