Intention-Aware Model to Support Agent Deliberation in a Large-Scale Dynamic Multi-Agent Application
It is hoped that the traffic in the cities will be almost optimal when autonomous vehicles will dominate the traffic. We investigate the route selection of autonomous vehicles. We extend, implement and apply a formal model to support the trustworthy route
- PDF / 966,095 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 2 Downloads / 152 Views
ct. It is hoped that the traffic in the cities will be almost optimal when autonomous vehicles will dominate the traffic. We investigate the route selection of autonomous vehicles. We extend, implement and apply a formal model to support the trustworthy route selection of real-world autonomous agents. We trust a model, if the route selection strategy of the model selects routes which are close to the possible fastest all the time. The formal model extends the intention-aware online routing game model with parallel lanes, traffic lights and give way intersections. These extensions are needed for real-world applications. The actual parameters of the formal model are derived from real-world OpenStreetMap data. The large-scale real-world testing of the model uses the SUMO (Simulation of Urban MObility) open source simulator. The implemented intention-aware online routing game model can execute the route selection for each vehicle faster than real-time. Our hypothesis is that the extended intention-aware online routing game model produces at least as good traffic as the dynamic equilibrium route assignment. This hypothesis is confirmed in a real-world scenario. Keywords: Autonomous vehicles equilibrium
1
· Route selection · Dynamic
Introduction
When designing a dynamic multi-agent system, it is important to ensure that the resulting system will not produce unwanted extreme behaviour. This usually requires the application of some kind of deliberative agent architecture, because the agents must be prepared for future changes in a dynamic environment, and the agents must base their actions on the predicted actions of other agents. In order to avoid an unwanted extreme behaviour of the whole system, the agents must somehow coordinate their actions. If the multi-agent system consist of a large number of agents, then direct communication among all the agents is not realistic. In this case, the agents often use stigmergic communication [3] through the environment. An advanced version of stigmergic communication is when c Springer Nature Switzerland AG 2020 M. Bramer and R. Ellis (Eds.): SGAI-AI 2020, LNAI 12498, pp. 301–314, 2020. https://doi.org/10.1007/978-3-030-63799-6_23
302
V. Antal et al.
the agents leave not only traces in the environment, but they also submit their intentions to the environment, which is then able to aggregate the intentions and make predictions [7]. Then the agents can use this prediction in their deliberation process to select their best action towards their goal. Multi-agent systems are applied in many domains since their first industrial applications [13]. Currently, a typical application of large-scale dynamic multiagent systems is the route selection of autonomous vehicles in a city traffic. This is a complex problem, not only because of the complexity of the road network, but also because the traffic changes with delay in response to the actions of the agents. When an agent selects a route to follow, then the agent may contribute to a congestion which will develop in the network sometime later. Agents
Data Loading...
