Skip to main content

Pedro Mariano

Universidade de Lisboa, Departamento de Informática (FCUL), Faculty Member

Followers

13

Following

9

Co-authors

4

Public Views

Pedro Mariano holds a 5 year BS degree in Informatics Engineering obtained in 1997 and a MSc degree in Applied Artificial Intelligence in 2000, both obtained at the Faculty of Science and Technology of the New University of Lisbon. He obtained a PhD degree in Computer Science at the Faculty of Sciences of the University of Lisbon in 2006.He is currently a post-doc researcher at the Faculty of Sciences of the University of Lisbon.He has participated in international research projects --EEII: Evolution and Ecology of Interacting Infohabitants

less

InterestsView All (7)

Uploads

Papers by Pedro Mariano

Cooperative Coevolution of Partially Heterogeneous Multiagent Systems

adaptive agents and multi-agents systems, May 4, 2015

Cooperative coevolution algorithms (CCEAs) facilitate the evolution of heterogeneous, cooperating... more Cooperative coevolution algorithms (CCEAs) facilitate the evolution of heterogeneous, cooperating multiagent systems. Such algorithms are, however, subject to inherent scalability issues, since the number of required evaluations increases with the number of agents. A possible solution is to use partially heterogeneous (hybrid) teams: behaviourally heterogeneous teams composed of homogeneous sub-teams. By having different agents share controllers, the number of coevolving populations in the system is reduced. We propose Hyb-CCEA, an extension of cooperative coevolution to partially heterogeneous multiagent systems. In Hyb-CCEA, both the agent controllers and the team composition are under evolutionary control. During the evolutionary process, we rely on measures of behaviour similarity for the formation of homogeneous sub-teams (merging), and propose a stochastic mechanism to increase heterogeneity (splitting). We evaluate Hyb-CCEA in multiple variants of a simulated herding task, and compare it with a fully heterogeneous CCEA. Our results show that Hyb-CCEA can achieve solutions of similar quality using significantly fewer evaluations, and in most setups, Hyb-CCEA even achieves significantly higher fitness scores than the CCEA. Overall, we show that merging and splitting populations are viable mechanisms for the cooperative coevolution of hybrid teams.

Assisi Playground: A Simulation Tool For Collective Bio-Hybrid System Research

This paper presents \emph{ASSISI Playground}, a simulator for facilitating research in the area o... more This paper presents \emph{ASSISI Playground}, a simulator for facilitating research in the area of collective bio-hybrid systems. Its development is motivated by the specific use-case of simulating bio-hybrid societies consisting of honeybees and static robotic units called CASUs (Combined Actuator-Sensor Units). However, due to its modular design, the simulator can easily be extended to other animal species and other types of robot. The distinguishing features of the software are the ability to simulate societies consisting of hundreds of individuals in real time, behaviour of individuals implemented in Python scripts that can be easily modified and extended by the user, and the ability to directly transfer controllers from simulated to real robots. Furthermore, the simulator implements several modalities of physical interaction that are not typically provided by conventional simulation frameworks but highly relevant to bio-hybrid research, including vibrations, airflow and heat tr...

Transverse Activity on Intelligent Robotics – IEETA – DETI

Abstract. Diplomacy is a 7-player game that requires coordination between players in order to ach... more Abstract. Diplomacy is a 7-player game that requires coordination between players in order to achieve victory. Its huge search space makes existing search algorithms useless. In this paper we present Darkblade, a player designed as a Multi-Agent System that uses potential fields to calculate moves and evaluate board positions. We tested our player against other recent players. Although there are some limitations, the results are promising. 1

Supplemental Information: Cooperative Coevolution of Control for a Real Multirobot System

Supplemental Information: Challenges in Cooperative Coevolution of Physically Heterogeneous Robot Teams

Natural Computing, 2016

Comparing Machine Learning Methods for Classifying Plant Drought Stress from Leaf Reflectance Spectra in Arabidopsis thaliana

Applied Sciences, 2021

Plant breeders and plant physiologists are deeply committed to high throughput plant phenotyping ... more Plant breeders and plant physiologists are deeply committed to high throughput plant phenotyping for drought tolerance. A combination of artificial intelligence with reflectance spectroscopy was tested, as a non-invasive method, for the automatic classification of plant drought stress. Arabidopsis thaliana plants (ecotype Col-0) were subjected to different levels of slowly imposed dehydration (S0, control; S1, moderate stress; S2, severe stress). The reflectance spectra of fully expanded leaves were recorded with an Ocean Optics USB4000 spectrometer and the soil water content (SWC, %) of each pot was determined. The entire data set of the reflectance spectra (intensity vs. wavelength) was given to different machine learning (ML) algorithms, namely decision trees, random forests and extreme gradient boosting. The performance of different methods in classifying the plants in one of the three drought stress classes (S0, S1 and S2) was measured and compared. All algorithms produced very...

Artificial Intelligence Meets Marine Ecotoxicology: Applying Deep Learning to Bio-Optical Data from Marine Diatoms Exposed to Legacy and Emerging Contaminants

Biology, 2021

Over recent decades, the world has experienced the adverse consequences of uncontrolled developme... more Over recent decades, the world has experienced the adverse consequences of uncontrolled development of multiple human activities. In recent years, the total production of chemicals has been composed of environmentally harmful compounds, the majority of which have significant environmental impacts. These emerging contaminants (ECs) include a wide range of man-made chemicals (such as pesticides, cosmetics, personal and household care products, pharmaceuticals), which are of worldwide use. Among these, several ECs raised concerns regarding their ecotoxicological effects and how to assess them efficiently. This is of particular interest if marine diatoms are considered as potential target species, due to their widespread distribution, being the most abundant phytoplankton group in the oceans, and also being responsible for key ecological roles. Bio-optical ecotoxicity methods appear as reliable, fast, and high-throughput screening (HTS) techniques, providing large datasets with biologic...

An Affordable Vehicle-Mounted Sensing Solution for Mobile Air Quality Monitoring

2020 5th International Conference on Smart and Sustainable Technologies (SpliTech), 2020

This paper presents the first prototype of the Expo-LIS system and its preliminary laboratory and... more This paper presents the first prototype of the Expo-LIS system and its preliminary laboratory and field experiments. The ExpoLIS system is composed of an affordable vehicle-mounted mobile sensor network and its supporting user-centred services whose aim is to provide citizens with real-time and dense spatiotemporal air quality data. A set of preliminary static laboratory experiments and dynamic field experiments were conducted, showing that the current prototype is already able to track changes in the air quality and provide citizens with access to these events via a mobile application.

Game-Like 3D Visualisation of Air Quality Data

Multimodal Technologies and Interaction, 2020

The data produced by sensor networks for urban air quality monitoring is becoming a valuable asse... more The data produced by sensor networks for urban air quality monitoring is becoming a valuable asset for informed health-aware human activity planning. However, in order to properly explore and exploit these data, citizens need intuitive and effective ways of interacting with it. This paper presents CityOnStats, a visualisation tool developed to provide users, mainly adults and young adults, with a game-like 3D environment populated with air quality sensing data, as an alternative to the traditionally passive visualisation techniques. CityOnStats provides several visual cues of pollution presence with the purpose of meeting each user’s preferences. Usability tests with a sample of 30 participants have shown the value of air quality 3D game-based visualisation and have provided empirical support for which visual cues are most adequate for the task at hand.

Using Rapid Chlorophyll Fluorescence Transients to Classify Vitis Genotypes

Plants, 2020

When a dark-adapted leaf is illuminated with saturating light, a fast polyphasic rise of fluoresc... more When a dark-adapted leaf is illuminated with saturating light, a fast polyphasic rise of fluorescence emission (Kautsky effect) is observed. The shape of the curve is dependent on the molecular organization of the photochemical apparatus, which in turn is a function of the interaction between genotype and environment. In this paper, we evaluate the potential of rapid fluorescence transients, aided by machine learning techniques, to classify plant genotypes. We present results of the application of several machine learning algorithms (k-nearest neighbors, decision trees, artificial neural networks, genetic programming) to rapid induction curves recorded in different species and cultivars of vine grown in the same environmental conditions. The phylogenetic relations between the selected Vitis species and Vitis vinifera cultivars were established with molecular markers. Both neural networks (71.8%) and genetic programming (75.3%) presented much higher global classification success rate...

Evolving robot controllers for a bio-hybrid system

The 2018 Conference on Artificial Life, 2018

In this paper we report the first results of evolving bio-hybrid societies. Our goal is to have r... more In this paper we report the first results of evolving bio-hybrid societies. Our goal is to have robots that are integrated in an animal society, and here we evolve robot controllers using animals as fitness providers, directly judging the success of integration. In particular, we are using juvenile honeybees and robots that are able to produce vibration patterns. Previous studies have shown that honeybees react to different vibration patterns, such as exhibiting freezing or stopping behaviours. In this paper we investigate whether we are able to evolve a vibration pattern that acts as a locally acting 'stop signal' for bees. Honeybees were placed in two containers with no communication between them: one with an active, vibrating robot, and a second with a passive robot. Post-hoc evaluations of key evolved digital genotypes generally confirm fitness values obtained during evolution. We also tested the transferability of key genotypes to a single container, in which bees are free to visit one vibrating and two dummy robots. Encouragingly, most genotypes are able to selectively stop bees, i.e., only in the vicinity of the vibrating robot, despite having been evolved under the more constrained setup. These results speak to the value of an evolutionary approach for discovering how to interact with animals.

Challenges in cooperative coevolution of physically heterogeneous robot teams

Natural Computing, 2016

Heterogeneous multirobot systems have shown significant potential in many applications. Cooperati... more Heterogeneous multirobot systems have shown significant potential in many applications. Cooperative coevolutionary algorithms (CCEAs) represent a promising approach to synthesise controllers for such systems, as they can evolve multiple co-adapted components. Although CCEAs allow for an arbitrary level of team heterogeneity, in previous works heterogeneity is typically only addressed at the behavioural level. In this paper, we study the use of CCEAs to evolve control for a heterogeneous multirobot system where the robots have disparate morphologies and capabilities. Our experiments rely on a simulated task where a simple ground robot must cooperate with a complex aerial robot to find and collect items. We first show that CCEAs can evolve successful controllers for physically heterogeneous teams, but find that differences in the complexity of the skills the robots need to learn can impair CCEAs’ effectiveness. We then study how different populations can use different evolutionary algorithms and parameters tuned to the agents’ complexity. Finally, we demonstrate how CCEAs’ effectiveness can be improved using incremental evolution or novelty-driven coevolution. Our study shows that, despite its limitations, coevolution is a viable approach for synthesising control for morphologically heterogeneous systems.

Dynamic Team Heterogeneity in Cooperative Coevolutionary Algorithms

IEEE Transactions on Evolutionary Computation, 2018

We propose Hyb-CCEA, a cooperative coevolutionary algorithm for the evolution of genetically hete... more We propose Hyb-CCEA, a cooperative coevolutionary algorithm for the evolution of genetically heterogeneous multiagent teams. The proposed approach extends the cooperative coevolution architecture with operators that put the number of coevolving populations under evolutionary control. Populations are dynamically merged based on behavioural similarity, thus decreasing team heterogeneity, and stochastic population splits are used to explore increased team heterogeneity. Hyb-CCEA is capable of converging to suitable team compositions for the given task, be it a completely homogeneous team where all agents share the same control logic, a heterogeneous team where each agent has distinct control logic, or a partially heterogeneous team. By placing both the team composition and the agent controllers under evolutionary control, Hyb-CCEA can be applied to domains for which the experimenter has limited or no knowledge about possible solutions. We study Hyb-CCEA extensively in an abstract domain, and conduct a series of validation experiments with four simulated multi-robot tasks: two multi-rover foraging tasks, and two robotic soccer tasks. The results show that Hyb-CCEA takes advantage of partial heterogeneity and frequently outperforms the standard cooperative coevolution approach, both in terms of fitness scores achieved and number of evaluations needed to evolve solutions.

Public and Private Partner Selection in Battle of Sexes

International Journal of Adaptive, Resilient and Autonomic Systems, 2015

In this paper the authors investigate what factors can promote population diversity. They compare... more In this paper the authors investigate what factors can promote population diversity. They compare different partner selection models and strategy mobility on the Battle of Sexes game. This is a game with a coordination dilemma where players must decide which event to attend given that each one has its preferred event but they prefer going together. They investigate two types of partner selection: one based in private information and another based on public information, which is based on an opinion model. The authors analyze two variants of the opinion model. Experimental analysis shows that partner selection plays a minor role of favoring population diversity. One of the most important factors is strategy mobility either implicitly through mutation or explicitly when an offspring is placed in a different location.

The Eect of Agreements in a Game with Multiple Strategies for

We present a model suited not only for the study of evolution of cooperation but also to study be... more We present a model suited not only for the study of evolution of cooperation but also to study behaviours such as treason and exploitation. This game has multiple Pareto Optimal solutions, which causes shifts in the agent strategies that we can interpret as either treason or exploitation. This requires some form of coordination between agents to avoid penalising behaviours. We present results of our game with and without an agreement model. We show that our game provides rich evolutionary dynamics.

Novelty-Driven Cooperative Coevolution

Evolutionary Computation, 2017

Cooperative coevolutionary algorithms (CCEAs) rely on multiple coevolving populations for the evo... more Cooperative coevolutionary algorithms (CCEAs) rely on multiple coevolving populations for the evolution of solutions composed of coadapted components. CCEAs enable, for instance, the evolution of cooperative multiagent systems composed of heterogeneous agents, where each agent is modelled as a component of the solution. Previous works have, however, shown that CCEAs are biased toward stability: the evolutionary process tends to converge prematurely to stable states instead of (near-)optimal solutions. In this study, we show how novelty search can be used to avoid the counterproductive attraction to stable states in coevolution. Novelty search is an evolutionary technique that drives evolution toward behavioural novelty and diversity rather than exclusively pursuing a static objective. We evaluate three novelty-based approaches that rely on, respectively (1) the novelty of the team as a whole, (2) the novelty of the agents’ individual behaviour, and (3) the combination of the two. We...

Coordination of collective behaviours in spatially separated agents

07/20/2015-07/24/2015, 2015

We aim to better understand collective behaviours in social animals, doing so in the context of b... more We aim to better understand collective behaviours in social animals, doing so in the context of bio-hybrid societies, i.e., those that comprise robots and animals. Together, they make up a collective adaptive system, in which the self-organising patterns of the natural society can be understood, augmented and modified by the presence of robots. Here, we conduct a series of simulation-based experiments to investigate how natural behaviours in juvenile honeybees can be influenced by robots that are able to change key environmental stimuli. Firstly, we show specific couplings between animals and robots that can lead to symmetry-breaking and collective decision-making, even from an initially homogeneous environment. Secondly, we demonstrate that collective decisions made by animals in distinct habitats can be coordinated, through robots that share only relatively simple informationbetween habitats. Such mixed animal-robot societies exhibit multiple interactions and feedback loops, the understanding of which is key to the design of engineered parts that successfully harness the potential of the overall complex system.

Cooperative Coevolution of Morphologically Heterogeneous Robots

07/20/2015-07/24/2015, 2015

Morphologically heterogeneous multirobot teams have shown significant potential in many applicati... more Morphologically heterogeneous multirobot teams have shown significant potential in many applications. While cooperative coevolutionary algorithms can be used for synthesising controllers for heterogeneous multirobot systems, they have been almost exclusively applied to morphologically homogeneous systems. In this paper, we investigate if and how cooperative coevolutionary algorithms can be used to evolve behavioural control for a morphologically heterogeneous multirobot system. Our experiments rely on a simulated task, where a ground robot with a simple sensor-actuator configuration must cooperate tightly with a more complex aerial robot to find and collect items in the environment. We first show how differences in the number and complexity of skills each robot has to learn can impair the effectiveness of cooperative coevolution. We then show how coevolution's effectiveness can be improved using incremental evolution or novelty-driven coevolution. Despite its limitations, we show that coevolution is a viable approach for synthesising control for morphologically heterogeneous systems.

Devising Effective Novelty Search Algorithms

Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation, 2015

Novelty search is a state-of-the-art evolutionary approach that promotes behavioural novelty inst... more Novelty search is a state-of-the-art evolutionary approach that promotes behavioural novelty instead of pursuing a static objective. Along with a large number of successful applications, many different variants of novelty search have been proposed. It is still unclear, however, how some key parameters and algorithmic components influence the evolutionary dynamics and performance of novelty search. In this paper, we conduct a comprehensive empirical study focused on novelty search's algorithmic components. We study the k parameter-the number of nearest neighbours used in the computation of novelty scores; the use and function of an archive; how to combine novelty search with fitness-based evolution; and how to configure the mutation rate of the underlying evolutionary algorithm. Our study is conducted in a simulated maze navigation task. Our results show that the configuration of novelty search can have a significant impact on performance and behaviour space exploration. We conclude with a number of guidelines for the implementation and configuration of novelty search, which should help future practitioners to apply novelty search more effectively.

Hyb-CCEA

Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation, 2015

Jorge Gomes BioMachines Lab & Instituto de Telecomunicações & Faculdade de Ciências, Univ... more Jorge Gomes BioMachines Lab & Instituto de Telecomunicações & Faculdade de Ciências, Universidade de Lisboa, BioISI Lisbon, Portugal jgomes@di.fc.ul.pt Pedro Mariano Faculdade de Ciências, Universidade de Lisboa, BioISI Lisbon, Portugal plmariano@fc.ul.pt Anders Lyhne Christensen BioMachines Lab & Instituto de Telecomunicações & Instituto Universitário de Lisboa (ISCTE-IUL) Lisbon, Portugal anders.christensen@iscte.pt