To Adapt or Not to Adapt – Consequences of Adapting Driver and Traffic Light Agents

Abstract

Abstract.One way to cope with the increasing traffic demand is to integrate standard solutions with more intelligent control measures. However, the result of possible interferences between intelligent control or information provision tools and other components of the overall traffic system is not easily predictable. This paper discusses the effects of integrating co-adaptive decision-making regarding route choices (by drivers) and control measures (by traffic lights). The motivation behind this is that optimization of traffic light control is starting to be integrated with navigation support for drivers. We use microscopic, agent-based modelling and simulation, in opposition to the classical network analysis, as this work focuses on the effect of local adaptation. In a scenario that exhibits features comparable to real-world networks, we evaluate different types of adaptation by drivers and by traffic lights, based on local perceptions. In order to compare the performance, we have also used a global level optimization method based on genetic algorithms.

Routing multiple cars in large scale networks: Minimizing road network breakdown probability

“…Their behaviour, especially those resulting in simulated movement, can be visualized, monitored, and validated at individual level, leading to new possibilities for analysing, debugging, and illustrating traffic phenomena [8]. We can divide the agent-based approaches within the application domain of traffic management into three subareas, namely, agent-based vehicle control [4], [9], [10], [11], [12], agent-based traffic light control [6], [13], [14], and hybrid agent-based control [7], [15].…”

“…Recently, there is a new trend of modeling both traffic lights and vehicles as agents [7], [15]. In this case, it is a hybrid agent-based control.…”

“…1) Agent Perspective: Since vehicles and urban traffic lights can be naturally modelled as agents, most of the researchers are applying multi-agent/agent-based technologies to solve the multi-vehicle routing problem [4], [5], [6], [7].…”

Opportunities for multiagent systems and multiagent reinforcement learning in traffic control

“…However equilibrium-based concepts are not completely adequate as they overlook the within-day variability for example. In [7,11] authors investigate what happens when different actors interact, each having its own goal and learning algorithm. The objective of local traffic control is obviously to minimize queues in a spatially limited area (e.g.…”

More Shared Responsibility for “More Appropriate Communication”

“…These seven articles are listed in Table 1. Most of these articles address “more appropriate communication” between literal peers, such as undergraduate students with other undergraduate students (Lowry, Roberts, Romano, Cheney, & Hightower, 2006; Tu & Corry, 2004), traffic light controllers with other traffic light controllers (Bazzan, de Oliveira, Klügl, & Nagel, 2008; Bazzan, Klügl, & Nagel, 2007), and spouses with their spouses (Sayers, Baucom, & Rankin, 1993). …”