A SUMO Extension for Norm-Based Traffic Control Systems

Abstract

Autonomous vehicles will most likely participate in traffic in the near future. The advent of autonomous vehicles allows us to explore innovative ideas for traffic control such as norm based control systems. A norm is a violable rule that describes correct behavior. Norm based traffic control systems monitor traffic and effectuate sanctions in case vehicles violate norms. In this paper we present an extension of SUMO that enables the user to apply norm based control systems to traffic simulations. In our extension, vehicles are capable of making an autonomous decision on whether to comply with the norms or not. We provide a description of the extension, a summary on its implementation and an experimental evaluation.

Norm-based mechanism design

“…Finally, we follow the convention, similar to the programming language Prolog [13], to use "_" as a place-holder for any action in an action profile specification. 12 For example, we use (Pre, (M, _), Post) to indicate that the performance of action profiles (M, M) and (M, W ) in states that satisfy the precondition Pre results in states that satisfies the postcondition Post.…”

“…In this section we present a more complex and realistic application of the proposed specification language. This application concerns the development of norm-based traffic environments for SUMO (Simulation of Urban MObility) [12]. SUMO [46] is a traffic simulation platform that supports the modelling of traffic, including cars, public transport and pedestrians.…”

“…The SUMO extension [12] is used to simulate a ramp merging traffic scenario. A schematic representation of the ramp merging scenario is illustrated in Fig.…”

SUMO Based Platform for Cooperative Intelligent Automotive Agents

“…One side of Budaörsi street is closed. For 'Irreg1' case it is northbound, and for 'Irreg2' case it is southbound 3. The placements of the markers, specifications of the corresponding distances were not correct.…”

“…Norm-based traffic [3] is an interesting multi-agent system solution. It requires, however, also some central controlling agents with norm data bases and well-distributed information among the agents.…”