Our research is developing flexible strategies for forming and routing future platoons of automated urban logistics vehicles. We propose the notion of compensational platooning using automated negotiation between agents representing vehicles. After the vehicles reach the end of a common route, an agent can propose part of its route along with a monetary value to platoon partners for further together-travel. If negotiation is successful, a new platoon is formed and follows the proposed route. If the compensation is too small or the route proposed oversteps the agent’s limitations, the offer is rejected and the vehicles continue their travel separately. A contribution of this paper is a negotiation strategy that proposes compensation based on beliefs of what the opponent’s payment threshold would be. In doing so, the bid with the highest acceptance likelihood is calculated, keeping negotiations short and effective. Our model is tested on a synthetic network and a real urban example. We show that by using negotiation, vehicles can identify mutually beneficial new routes that a centralised/distributed approach would not find, with utility improvements of up to 8%.

Automated negotiation, Decentralised agent coordination, Opponent modelling, Platoon matching
Lecture Notes in Computer Science/Lecture Notes in Artificial Intelligence
International Conference on Principles of Practice in Multi-Agent Systems
Centrum Wiskunde & Informatica, Amsterdam, The Netherlands

Sebe, S.-M, Baarslag, T, & Müller, J.P., J.P. (2021). Automated negotiation mechanism and strategy for compensational vehicular platooning. In PRIMA 2020: Principles and Practice of Multi-Agent Systems (pp. 317–324). doi:10.1007/978-3-030-69322-0_20