Contribuições de aprendizado por reforço em escolha de rota e controle semafórico
DOI:
https://doi.org/10.1590/s0103-4014.2021.35101.008Palavras-chave:
Inteligência artificial, Aprendizado de máquina, Aprendizado por reforço, Sistemas inteligentes de transporte, Mobilidade urbanaResumo
A área de sistemas inteligentes de transporte há muito investiga como empregar tecnologias da informação e comunicação a fim de melhorar a eficiência do sistema como um todo. Isso se traduz basicamente em monitorar e gerenciar a oferta (rede viária, semáforos etc.) e a demanda (deslocamentos de pessoas e mercadorias). A esse esforço, mais recentemente, estão sendo adicionadas técnicas de inteligência artificial. Essa tem o potencial de melhorar a utilização da infraestrutura existente, a fim de melhor atender a demanda. Neste trabalho é fornecido um panorama focado especificamente em duas tarefas onde a inteligência artificial tem contribuições relevantes, a saber, controle semafórico e escolha de rotas. Os trabalhos aqui discutidos objetivam otimizar a oferta e/ou distribuir a demanda.
Downloads
Referências
ABDOOS, M.; MOZAYANI, N.; BAZZAN, A. L. Holonic multi-agent system for traffic signals control. Engineering Applications of Artificial Intelligence, v.26, n.5-6, p.1575-87, 2013.
ADLER, J. L.; BLUE, V. J. Toward the Design of Intelligent Traveller Information
Systems. Transportation Research Part C, v.6, p.157-72, 1998.
ARNOTT, R.; PALMA, A. de; LINDSEY, R. Departure Time and Route Choice for
the Morning Commute. Transportation Research B, v.24, p.209-28, 1990.
BARTHÉLEMY, J.; CARLETTI, T. A dynamic behavioural traffic assignment model
with strategic agents. Transportation Research Part C: Emerging Technologies, v.85, p.23-46, 2017.
BAZZAN, A. L. C. A Distributed Approach for Coordination of Traffic Signal Agents.
Autonomous Agents and Multiagent Systems, v.10, n.1, p.131-64, March 2005.
BAZZAN, A. L. C. Opportunities for Multiagent Systems and Multiagent Reinforcement Learning in Traffic Control. Autonomous Agents and Multiagent Systems, v.18,
n.3, p.342-75, June 2009.
BAZZAN, A. L. C. IA Multiagente: mais inteligência, mais desafios. In: MEIRA JUNIOR, W.;
CARVALHO, A. C. P. L. F. de (Ed.). Atualizações em informática 2010. Rio de Janeiro: PUC-Rio, 2010. p.111-59.
CARVALHO, A. C. P. L. F. Aligning individual and collective welfare in complex socio-technical systems
by combining metaheuristics and reinforcement learning. Eng. Appl. of AI, v.79, p.23-
, 2019.
BAZZAN, A. L. C.; FEHLER, M.; KLÜGL, F. Learning To Coordinate In a Network
Of Social Drivers: the role of information. In: INTERNATIONAL WORKSHOP ON
LEARNING AND ADAPTATION IN MAS (LAMAS 2005), 2006. Proceedings. . .
S.l.: s.n., 2006. n.3898, p.115-28. (Lecture Notes in Artificial Intelligence).
BAZZAN, A. L. C.; GRUNITZKI, R. A multiagent reinforcement learning approach
to en-route trip building. In: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2016., 2016. Anais. . . s.l.: s.n., 2016. p.5288-95.
BAZZAN, A. L. C.; KLÜGL, F. Case Studies on the Braess Paradox: simulating route
recommendation and learning in abstract and microscopic models. Transportation Research C, v.13, n.4, p.299-319, August 2005.
BAZZAN, A. L. C.; KLÜGL, F. Sistemas Inteligentes de Transporte e Tráfego: uma abordagem de tecnologia
da informação. In: KOWALTOWSKI, T.; BREITMAN, K. K. (Ed.). Anais das Jornadas de Atualização em Informática. s.l.: SBC, 2007.
BAZZAN, A. L. C.; KLÜGL, F. Introduction to Intelligent Systems in Traffic and Transportation. s.l.: Morgan
and Claypool, 2013a. 1-137p. n.3. (Synthesis Lectures on Artificial Intelligence and
Machine Learning, v.7).
BAZZAN, A. L. C.; KLÜGL, F. A review on agent-based technology for traffic and transportation. The Knowledge Engineering Review, v.29, n.3, p.375-403, 2013b.
BAZZAN, A. L. C.; OLIVEIRA, D. de; KLÜGL, F.; NAGEL, K. Adapt or not to
adapt – Consequences of adapting driver and traffic light agents. In: TUYLS, K.;
NOWÉ, A.; GUESSOUM, Z.; KUDENKO, D. (ed.). Adaptive agents and multi-
-agent systems III. [S.l.]: Springer-Verlag, 2008, v.4865, p.1–14. (Lecture Notes in
Artificial Intelligence).
BAZZAN, A. L. C.; OLIVEIRA, D. de; SILVA, B. C. da. Learning in Groups of Traffic
Signals. Eng. Applications of Art. Intelligence, v.23, p.560-8, 2010.
BAZZAN, A. L. C.; WAHLE, J.; KLÜGL, F. Agents in Traffic Modelling - from Reactive to Social Behavior. In: ADVANCES IN ARTIFICIAL INTELLIGENCE, 1999,
Berlin/Heidelberg. Anais...Springer, 1999. n.1701, p.303-6. (Lecture Notes in Artificial Intelligence). Extended version appeared in Proc. of the U.K. Special Interest
Group on Multi-Agent Systems (UKMAS), Bristol, UK.
BEN-AKIVA, M.; PALMA, A. de; KAYSI, I. Dynamic Network Models and Driver
Information Systems. Transp. Res. A, v.25, n.5, p.251-66, 1991.
BITTENCOURT, G. Inteligência Artificial: ferramentas e teorias. 2.ed. Florianópolis:Editora da UFSC, 2001.
BONSALL, P. W. The Influence of Route Guidance Advice on Route Choice in Urban
Networks. Transportation, v.19, n.1, 1992.
BRAESS, D. Über ein Paradoxon aus der Verkehrsplanung. Unternehmensforschung,
v.12, p.258, 1968.
BURIOL, L. S. et al. A biased random-key genetic algorithm for road congestion minimization. Optimization Letters, v.4, p.619-33, 2010.
CAGARA, D.; SCHEUERMANN, B.; BAZZAN, A. L. Traffic optimization on Islands. In: IEEE VEHICULAR NETWORKING CONFERENCE (VNC 2015), 7.,
, Kyoto, Japan. Anais. . . IEEE, 2015. p.175-82.
CLAES, R.; HOLVOET, T.; WEYNS, D. A decentralized approach for anticipatory
vehicle routing using delegate multiagent systems. IEEE Transactions on Intelligent
Transportation Systems, v.12, n.2, p.364-73, March 2011.
DIA, H.; PANWAI, S. Intelligent Transport Systems: neural agent (neugent) models of
driver behaviour. s.l.: LAP Lambert Academic Publishing, 2014.
DIAKAKI, C. et al. Extensions and New Applications of the Traffic Signal Control Strategy TUC. In: ANNUAL MEETING OF THE TRANSPORTATION RESEARCH
BOARD, 82., 2003. Proceedings. . . s.l.: s.n., 2003. p.12-16.
DIAS, J. C. et al. An Inverted Ant Colony Optimization approach to traffic. Engineering Applications of Artificial Intelligence, v.36, n.0, p.122-33, 2014.
HUNT, P. B. et al. A Traffic Responsive Method of Coordinating Signals. Berkshire:
Transport and Road Research Laboratory, 1981. TRRL Lab. Report. (1014).
KLÜGL, F.; BAZZAN, A. L. C. Route Decision Behaviour in a Commuting Scenario.
Journal of Artificial Societies and Social Simulation, v.7, n.1, 2004a.
KLÜGL, F.; BAZZAN, A. L. C. Simulation Studies on Adaptative Route Decision and the Influence of Information on Commuter Scenarios. Journal of Intelligent Transportation Systems: Technology, Planning, and Operations, v.8, n.4, p.223-32, October/December 2004b.
KLÜGL, F.; BAZZAN, A. L. C.Agent-based modeling and simulation. AI Magazine, v.33, n.3, p.29-40,
KOBAYASHI, K.; DO, M. The Informational Impacts of Congestion Tolls upon Route
Traffic Demands. Transportation Research A, v.39, n.7-9, p.651–670, August-November 2005.
LEMOS, L. L.; BAZZAN, A. L. C. Combining adaptation at supply and demand levels in microscopic simulation: a multiagent learning approach. Transportation Research Procedia, v.37, p.465-72, 2019. Selected and peer-reviewed from the 21st EURO
Working Group on Transportation (EWGT) meeting.
LEMOS, L. L.; BAZZAN, A. L. C.; PASIN, M. Co-Adaptive Reinforcement Learning
in Microscopic Traffic Systems. In: IEEE CONGRESS ON EVOLUTIONARY COMPUTATION, CEC 2018, RIO DE JANEIRO, BRAZIL, JULY 8-13, 2018, 2018.,
Anais. . . s.l.: s.n., 2018. p.1-8.
LOWRIE, P. The Sydney Coordinate Adaptive Traffic System - Principles, Methodology, Algorithms. In: INTERNATIONAL CONFERENCE ON ROAD TRAFFIC SIGNALLING, 1982, Sydney, Australia. Proceedings. . . s.l.: s.n., 1982.
MAHMASSANI, H. S.; CHEN, P. S. Comparative Assessment of Origin-based and
en route Real-time Information under Alternative user Behavior Rules. Transportation
Research Record, v.1306, p.69-81, 1991.
MANNION, P.; DUGGAN, J.; HOWLEY, E. An Experimental Review of Reinforcement Learning Algorithms for Adaptive Traffic Signal Control. In: MCCLUSKEY, L.
T. et al. (Ed.). Autonomic Road Transport Support Systems. s.l.: Springer, 2016. p.47-66.
MITCHELL, W. J.; BORRONI-BIRD, C. E.; BURNS, L. D. Reinventing the Automobile. Cambridge, MA: MIT Press, 2010.
RAMOS, G. de. O.; BAZZAN, A. L. C.; SILVA, B. C. da. Analysing the impact of travel information for minimising the regret of route choice. Transportation Research Part
C: Emerging Technologies, v.88, p.257-71, Mar 2018.
RAMOS, G. de. O.; GRUNITZKI, R. An Improved Learning Automata Approach
for the Route Choice Problem. In: KOCH, F.; MENEGUZZI, F.; LAKKARAJU, K.
(Ed.). Agent Technology for Intelligent Mobile Services and Smart Societies. s.l.: Springer
Berlin Heidelberg, 2015. p.56-67. (Communications in Computer and Information
Science, v.498).
ROBERTSON, D. I. TRANSYT: a traffic network study tool. London: Road Res.
Lab., 1969. Rep. LR. (253).
SHARON, G. et al. Real-time Adaptive Tolling Scheme for Optimized Social Welfare
in Traffic Networks. In: INTERNATIONAL CONFERENCE ON AUTONOMOUS
AGENTS AND MULTIAGENT SYSTEMS (AAMAS 2017), 16., 2017, São Paulo.
Proceedings. . . IFAAMAS, 2017. p.828-36.
SILVA, B. C. d. et al. Dealing with Non-Stationary Environments using Context Detection. In: INTERNATIONAL CONFERENCE ON MACHINE LEARNING ICML,
, 2006. Proceedings. . . New York: ACM Press, 2006. p.217-24.
TAALE, H.; VAN KAMPEN, J.; HOOGENDOORN, S. Integrated signal control and
route guidance based on back-pressure principles. Transportation Research Procedia,
v.10, p.226-35, 2015.
WAHLE, J.; BAZZAN, A. L. C.; KLÜGL, F. The Impact of Real Time Information in
a Two Route Scenario using Agent Based Simulation. Transportation Research Part C:
Emerging Technologies, v.10, n.5-6, p.73-91, 2002.
WAHLE, J. et al. Decision Dynamics in a Traffic Scenario. Physica A, v.287, n.3-4,
p.669-81, 2000.
WARDROP, J. G. Some theoretical aspects of road traffic research. Proceedings of the
Institution of Civil Engineers, Part II, v.1, n.36, p.325-62, 1952.
WATKINS, C. J. C. H.; DAYAN, P. Q-learning. Machine Learning, Hingham, v.8, n.3,
p.279-92, 1992.
WEI, H. et al. A Survey on Traffic Signal Control Methods. CoRR, , v.abs/1904.08117, 2019.
WIERING, M. Multi-Agent Reinforcement Learning for Traffic Light Control. In: SEVENTEENTH INTERNATIONAL CONFERENCE ON MACHINE LEARNING
(ICML 2000), 2000. Proceedings. . . s.l.: s.n., 2000. p.1151-8.
YAU, K.-L. A. et al. A Survey on Reinforcement Learning Models and Algorithms for Traffic Signal Control. ACM Comput. Surv., v.50, n.3, 2017.
Publicado
Edição
Seção
Licença
Copyright (c) 2021 Ana L. C. Bazzan
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial 4.0 International License.
Estudos Avançados não celebra contrato de cessão de direitos autorais com seus colaboradores, razão pela qual não detém os direitos autorais dos artigos publicados. Os interessados em reproduzir artigos publicados na revista devem necessariamente obter o consentimento do autor e atribuir devidamente os créditos ao periódico.
