The recently introduced lane-free traffic paradigm removes the restrictions of the traffic lanes, so that autonomous vehicles can move anywhere laterally across the road's width. Previous research in this domain h...
详细信息
ISBN:
(纸本)9783031206139;9783031206146
The recently introduced lane-free traffic paradigm removes the restrictions of the traffic lanes, so that autonomous vehicles can move anywhere laterally across the road's width. Previous research in this domain has employed the celebrated max-plus message-passing algorithm in order to allow the coordination of all (connected and autonomous) vehicles in the environment. However, when allowing for the realistic perspective that there exist vehicles that are unable or unwilling to communicate with others, the uncertainty introduced renders the aforementioned coordination approach ineffective. To combat this, in this paper we adjust the max-plus algorithm accordingly so that agents using max-plus for coordination can also observe and take into consideration independent agents via emulated messages. We put forward different methods to form these messages-namely the maximax, maximin, Hurwicz, Minimax Regret and Laplace decision-making criteria. Finally, we provide a thorough evaluation of our approach, including a detailed comparison of all criteria used for message-forming.
We focus on a real-time multiagent decision making problem in a collaborative setting including a cost factor for the planning and execution of actions. We present the centralized coordination of a multiagent system i...
详细信息
ISBN:
(纸本)9781665427449
We focus on a real-time multiagent decision making problem in a collaborative setting including a cost factor for the planning and execution of actions. We present the centralized coordination of a multiagent system in which the team must make a collaborative decision to maximize the global payoff. We used the framework of Coordination Graphs, which exploit dependencies among agents to decompose the global payoff function value as the sum of local terms. We revise the centralized max-plus algorithm by presenting a new Cost max-plus algorithm for planning and acting by including the cost in the local interactions of agents. We propose a two-step planning and acting algorithm called Factored Value-MCTS-Cost-max-plus algorithm that is online, anytime, and scalable in terms of the number of agents and their local interactions.
This paper addresses the problem of collaborative multi-agent autonomous driving of connected and automated vehicles (CAVs) in lane-free highway scenarios. We eliminate the lane-changing task, i.e., CAVs may be locate...
详细信息
ISBN:
(纸本)9781713832621
This paper addresses the problem of collaborative multi-agent autonomous driving of connected and automated vehicles (CAVs) in lane-free highway scenarios. We eliminate the lane-changing task, i.e., CAVs may be located in any arbitrary lateral position within the road boundaries, hence allowing for better utilization of the available road capacity. As a consequence, vehicles operate in a much more complex environment, and the need for the individual CAVs to select actions that are efficient for the group as a whole is highly desired. We formulate this environment as a multiagent collaboration problem represented via a coordination graph, thus decomposing the problem with local utility functions, based on the interactions between vehicles. We produce a tractable and scalable solution by estimating the joint action of all vehicles via the anytime max-plus algorithm, with local utility functions provided by potential fields, designed to promote collision avoidance. Specifically, the fields have an ellipsoid form that is most suitable for lane-free highway environments. This novel use of max-plus with potential fields gives rise to a coordinated control policy that exploits only local information specific to each CAV. Our experimental evaluation confirms the effectiveness of our approach: lane-free movement allows for increased traffic flow rates, and vehicles are able to achieve speeds that are both high and close to their desired ones, even in demanding environments with high traffic flow.
Coordination graphs provide a tractable framework for cooperative multiagent decision making by decomposing the global payoff function into a sum of local terms. In this paper we review some distributed algorithms for...
详细信息
ISBN:
(纸本)0780385667
Coordination graphs provide a tractable framework for cooperative multiagent decision making by decomposing the global payoff function into a sum of local terms. In this paper we review some distributed algorithms for action selection in a coordination graph and discuss their pros and cons. For real-time decision making we emphasize the need for anytime algorithms for action selection: these are algorithms that improve the quality of the solution over time. We describe variable elimination, coordinate ascent, and the max-plus algorithm, the latter being an instance of the belief propagation algorithm in Bayesian networks. We discuss some interesting open problems related to the use of the max-plus algorithm in real-time multiagent decision making.
暂无评论