Pedro Mariano
Universidade de Lisboa, Departamento de Informática (FCUL), Faculty Member
- Evolutionary Biology, Game Theory, Crystal Growth, Brain-computer interfaces, Biomimetics, Evolution, and 9 morePopulation Dynamics, Hydrogels, Science Teaching Methods, Multimodal Interfaces, Reputation, Multi-Agent Systems, Multimedia information retrieval, Evolution of Cooperation, and Partner Selectionedit
- Pedro Mariano holds a 5 year BS degree in Informatics Engineering obtained in 1997 and a MSc degree in Applied Artifi... morePedro 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 Infohabitantsedit
Research Interests:
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... 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...
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... 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
Research Interests:
Research Interests:
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... 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...
Research Interests:
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,... 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...
Research Interests:
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... 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.
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... 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.
Research Interests:
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,... 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...
Research Interests:
Research Interests:
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... 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.
Research Interests:
Research Interests:
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... 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.
Research Interests:
Research Interests:
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... 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...
Research Interests:
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... 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.
Research Interests:
Research Interests:
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,... 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
Research Interests:
Research Interests:
Research Interests:
Research Interests:
In this paper we investigate how to build a model to predict pollution levels using geographical information. By focusing on this kind of attributes we hope to contribute to an effective city management as we will find the urban... more
In this paper we investigate how to build a model to predict pollution levels using geographical information. By focusing on this kind of attributes we hope to contribute to an effective city management as we will find the urban configurations that conduct to the lowest pollution levels. We used decision trees to build a regression model. We performed a parameter grid search using cross validation. Ablation analysis where some attributes were removed from training showed that geographical based attributes impact the prediction error of decision trees.
Research Interests: Computer Science and IEEE
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 multi- ple Pareto Optimal solutions, which causes shifts in the agent strategies... 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 multi- ple Pareto Optimal solutions, which causes shifts in the agent strategies that we can interpret as either treason or exploitation. This requires some form of coordina- tion between agents to avoid penalising
Research Interests:
We analyse Give and Take, a multi-stage resource sharing game to be played between two players. Payoff is dependent on the possession of an indivisible and durable resource, and on each stage players may either do nothing or, depending on... more
We analyse Give and Take, a multi-stage resource sharing game to be played between two players. Payoff is dependent on the possession of an indivisible and durable resource, and on each stage players may either do nothing or, depending on their roles, give the resource, or take it. Despite these simple rules we show that this game has interesting complex dynamics. Unique to Give and Take is the existence of multiple Pareto Optimal profiles that can also be Nash Equilibria, and a built-in punishment action. This game allows us to study cooperation in sharing an indivisible and durable resource. Since there are multiple strategies to cooperate, Give and Take provides a base to investigate coordination under implicit or explicit agreements. We discuss its position in face of other games and real world situations that are better modelled by it. The paper presents an in-depth analysis of the game for the range of admissible parameter values. We show that when taking is costly for both pl...
ABSTRACT We examine the effect of different partner selection models in population diversity and dynamics when agents interact through a coordination game, namely the Battle of Sexes. In this type of game there are usually more than one... more
ABSTRACT We examine the effect of different partner selection models in population diversity and dynamics when agents interact through a coordination game, namely the Battle of Sexes. In this type of game there are usually more than one Nash Equilibrium. Each one can be considered as a niche that a population may occupy. We compare a partner selection model based on private information with a partner selection based on public opinion. Experimental analysis shows that each one is better than random partner selection, but the outcome is different. While in the private based partner selection usually only one of the Nash Equilibrium survives, in the opinion based partner selection each strategy profile is able to resist. These results were obtained when each strategy was confined to its location and no movement was allowed between places. This raises some questions on how diversity can be maintained with mutation and strategy mobility having a negative impact.
One of the main motivations for the use of competitive coevolution systems is their ability to capitalise on arms races between competing species to evolve increasingly sophisticated solutions. Such arms races can, however, be hard to... more
One of the main motivations for the use of competitive coevolution systems is their ability to capitalise on arms races between competing species to evolve increasingly sophisticated solutions. Such arms races can, however, be hard to sustain, and it has been shown that the competing species often converge prematurely to certain classes of behaviours. In this paper, we investigate if and how novelty search, an evolutionary technique driven by behavioural novelty, can overcome convergence in coevolution. We propose three methods for applying novelty search to coevolutionary systems with two species: (i) score both populations according to behavioural novelty; (ii) score one population according to novelty, and the other according to fitness; and (iii) score both populations with a combination of novelty and fitness. We evaluate the methods in a predator-prey pursuit task. Our results show that novelty-based approaches can evolve a significantly more diverse set of solutions, when com...
Research Interests:
ABSTRACT Evolutionary techniques driven by behavioural diversity, such as novelty search, have shown significant potential in evolutionary robotics. These techniques rely on priorly specified behaviour characterisations to estimate the... more
ABSTRACT Evolutionary techniques driven by behavioural diversity, such as novelty search, have shown significant potential in evolutionary robotics. These techniques rely on priorly specified behaviour characterisations to estimate the similarity between individuals. Characterisations are typically defined in an ad hoc manner based on the experimenter's intuition and knowledge about the task. Alternatively, generic characterisations based on the sensor-effector values of the agents are used. In this paper, we propose a novel approach that allows for systematic derivation of behaviour characterisations for evolutionary robotics, based on a formal description of the agents and their environment. Systematically derived behaviour characterisations (SDBCs) go beyond generic characterisations in that they can contain task-specific features related to the internal state of the agents, environmental features, and relations between them. We evaluate SDBCs with novelty search in three simulated collective robotics tasks. Our results show that SDBCs yield a performance comparable to the task-specific characterisations, in terms of both solution quality and behaviour space exploration.
ABSTRACT One of the main motivations for the use of competitive coevolution systems is their ability to capitalise on arms races between competing species to evolve increasingly sophisticated solutions. Such arms races can, however, be... more
ABSTRACT One of the main motivations for the use of competitive coevolution systems is their ability to capitalise on arms races between competing species to evolve increasingly sophisticated solutions. Such arms races can, however, be hard to sustain, and it has been shown that the competing species often converge prematurely to certain classes of behaviours. In this paper, we investigate if and how novelty search, an evolutionary technique driven by behavioural novelty, can overcome convergence in coevolution. We propose three methods for applying novelty search to coevolutionary systems with two species: (i) score both populations according to behavioural novelty; (ii) score one population according to novelty, and the other according to fitness; and (iii) score both populations with a combination of novelty and fitness. We evaluate the methods in a predator-prey pursuit task. Our results show that novelty-based approaches can evolve a significantly more diverse set of solutions, when compared to traditional fitness-based coevolution.
Research Interests:
I UNINOVA, New University of Lisbon, Quinta da Tome, 2829-516 Caparica, Portugal * Informatics Department, New University of Lisbon, Quinta da Tome, 2829-516 Caparica, Portugal Electrical and Electronic Engineering Department, Imperial... more
I UNINOVA, New University of Lisbon, Quinta da Tome, 2829-516 Caparica, Portugal * Informatics Department, New University of Lisbon, Quinta da Tome, 2829-516 Caparica, Portugal Electrical and Electronic Engineering Department, Imperial College, London, England 'Information ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
We analyse a resource sharing game under different conditions in order to study social behaviours such as cooperation and treason. We concentrate in analysing the game under different scenarios in order to find out which one produces a... more
We analyse a resource sharing game under different conditions in order to study social behaviours such as cooperation and treason. We concentrate in analysing the game under different scenarios in order to find out which one produces a more cooperative population. This is possible since the game while having multiple Pareto Optimal strategies, also has multiple pure and mixed Nash Equilibriums, which results in complex population dynamics. We introduce a simple form of agreement and compare the results with the previous cases.