Verification and Creation of Autonomous Vehicle Trajectories for Non-Experts with Reactive Design-Time Feedback and Sensor-Based Response

Alex Day (Clarion University of Pennsylvania)
Sam Hum (Colorado College)
Riley Wagner
 (the University of Arizona)

An increase in the demand of cyber-physical systems (CPS) has brought about an increase in the complexity of such systems. As their complexity increases, CPS are becoming increasingly inaccessible to those who do not have knowledge in this specific domain. Thus, there exists a need for a language that combines CPS with an interface that is accessible to non-experts.  To offset this problem we propose the use of a domain-specific modeling language (DSML) designed in WebGME — a server-based generic modeling environment. The language mirrors the curriculum of non-expert programmers and incorporates the use of sensor data, which is to be deployed on both the Cognitive and Autonomous Test Vehicle (CATVehicle) and Lego EV3 robots. However, maintaining safety within these DSML-designed CPS can be an issue. We aim to address this by coupling the language with assorted verification techniques such as reachability analysis at design time, compile time, and run time. One of these techniques involves the implementation of an off-the-shelf verification tool as a method of providing error messages at both design and compile-time. This paper concerns itself with providing a simple interface to allow non-experts to program safe paths without the need for expert review.

CAT Vehicle 2019

Brandon Dominique (New Jersey Institute of Technology)

Daniel Fishbein (Missouri State University)
Christopher
 Kreienkamp (University of Notre Dame)

Alex Day (Clarion University of Pennsylvania)
Sam Hum (Colorado College)
Riley Wagner
 (the University of Arizona)

Eric Av (Gonzaga University)
Hoang Huynh (Georgia State University-Perimeter College)
John Nguyen (University of Minnesota, Twin Cities)

Brandon Dominique's experience: A brief overview of the work that I did at the University of Arizona for their student-led self driving car project, the CAT Vehicle.

Pages