A Decentralised Approach to Intersection Traffic Management

Authors: Huan Vu, Samir Aknine, Sarvapali D. Ramchurn

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental More specifically, this paper advances the state of the art in the following ways. First, we propose a novel DCOP formulation of the right-of-way allocation problem. Second, we show how to solve the DCOP approximately using the max-sum algorithm [Farinelli et al., 2008; Macarthur et al., 2011]. Third, we empirically show that our algorithm outperforms the state of the art in terms of reductions in waiting time and robustness to dynamic events.
Researcher Affiliation Academia Huan Vu1,2, Samir Aknine1 and Sarvapali Ramchurn3 1 Universit e de Lyon, CNRS, Universit e Lyon 1, LIRIS, UMR5205, Lyon 69622, France 2 University of Transport and Communications, Hanoi, Vietnam 3 University of Southampton, Southampton, United Kingdom
Pseudocode No The paper describes algorithms and uses factor graphs (Figure 3 and 4) but does not provide structured pseudocode blocks.
Open Source Code No The paper does not provide an explicit statement or link for open-source code for the methodology.
Open Datasets No The paper describes a simulation environment for traffic flow and insertion rates rather than using a pre-existing public dataset with explicit training splits.
Dataset Splits No The paper describes evaluation in terms of insertion rates and dynamic events in a simulated environment, but does not specify traditional train/validation/test dataset splits.
Hardware Specification Yes All experiments were performed using an Intel Core i5-4690 3.5 GHz, 8 GB RAM, under Ubuntu 16.04.
Software Dependencies No The paper states: 'Max-sum algorithm is implemented using Frodo [L eaut e et al., 2009].' However, it does not provide a specific version number for Frodo, which is required for reproducibility.
Experiment Setup Yes All algorithms are evaluated according to the insertion rate of vehicles. The insertion rate varies from 0.1 (off-peak) to 0.5 (rush hour) [Junges and Bazzan, 2008].