Abstract
The evolution of driving technology has recently progressed from active safety features and ADAS systems to fully sensor-guided autonomous driving. Bringing such a vehicle to market requires not only simulation and testing but formal verification to account for all possible traffic scenarios. A new verification approach, which combines the use of two well-known model checkers: model checker for multi-agent systems (MCMAS) and probabilistic model checker (PRISM), is presented for this purpose. The overall structure of our autonomous vehicle (AV) system consists of: (1) A perception system of sensors that feeds data into (2) a rational agent (RA) based on a belief–desire–intention (BDI) architecture, which uses a model of the environment and is connected to the RA for verification of decision-making, and (3) a feedback control systems for following a self-planned path. MCMAS is used to check the consistency and stability of the BDI agent logic during design-time. PRISM is used to provide the RA with the probability of success while it decides to take action during run-time operation. This allows the RA to select movements of the highest probability of success from several generated alternatives. This framework has been tested on a new AV software platform built using the robot operating system (ROS) and virtual reality (VR) Gazebo Simulator. It also includes a parking lot scenario to test the feasibility of this approach in a realistic environment. A practical implementation of the AV system was also carried out on the experimental testbed.
Highlights
The Defense Advanced Research Projects Agency (DARPA) sponsored competitions between 2004–2007 [1,2] presented new results on autonomous ground vehicles that showed large steps forward in the field
We investigated how a robotic agent can use model checking through the use of the model checker for multi-agent systems (MCMAS) model checker [25] to examine the consistency and stability of its rules, beliefs, and actions through computational tree logic (CTL) for the rational agent (RA) that has been implemented within the limited instruction set agent (LISA) agent programming framework [10,26]
probabilistic model checker (PRISM) is used by the RA at run-time to ask questions such as ‘what is the probability of success of the current action’ or ‘what is the probability of achieving the current goal within a time limit’ [27], the parameters used to estimate the probabilities depending on the driving scenario were, for example, the speed of the autonomous vehicle (AV), speed of moving objects, and the direction of movements
Summary
The Defense Advanced Research Projects Agency (DARPA) sponsored competitions between 2004–2007 [1,2] presented new results on autonomous ground vehicles that showed large steps forward in the field. We are concerned with the high-level software components responsible for decisions in an AV capable of navigation, obstacle detection and avoidance, and autonomous parking These logic-based decisions can either be implemented through a rational agent [9,10,16,17,18,19] or through fuzzy logic [20,21,22] depending on the level of performance guarantee required. Simulation, and implementation of an AV through ROS open-source physicsbased system for a Tata Ace vehicle Both the AVs in simulation and experimental implementation use the same perception, rational agent, planning, and control system software designed for a parking lot environment
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
