Institutional Robotics: Difference between revisions

From ISRWiki
Jump to navigation Jump to search
No edit summary
 
(24 intermediate revisions by 3 users not shown)
Line 1: Line 1:
Institutional Robotics is a new strategy to conceptualize multi-robot systems, which takes institutions as the main tool of social life of robots with bounded rationality and bounded autonomy. This institutional approach intends to get inspiration from philosophical and social sciences research on social and collective phenomena, and is mainly inspired by concepts from Institutional Economics, an alternative to mainstream neoclassical economic theory.
Institutional Robotics is a new strategy to conceptualize multi-robot systems, which takes institutions as the main tool of social life of robots with bounded rationality and bounded autonomy. This institutional approach intends to get inspiration from philosophical and social sciences research on social and collective phenomena, and is mainly inspired by concepts from Institutional Economics, an alternative to mainstream neoclassical economic theory.


O objectivo é que sistemas de múltiplos robots possam desenvolver actividades num ambiente partilhado com humanos, de tal modo que os humanos possam interagir com os robots de forma “natural”, intuitiva, sem uma aprendizagem específica de técnicas para lidar com os robots. Não se foca particularmente a interacção individual, mas os comportamentos em ambientes físicos e sociais onde interagem múltiplos agentes naturais e artificiais. Para isso, os robots devem ser capazes de reconhecer, nomeadamente, normas, rotinas, sinais, formas de organização material do mundo, papéis sociais, formas sociais como organizações ou equipas – em geral, instituições e indicadores institucionais que os humanos reconhecem como formas de estruturar as suas relações sociais complexas.
The goal is to have multiple robots developing activities in a shared environment with human, in such a way that humans can interact with robots "naturally", intuitively, without a need to learn specific techniques to deal with them. The focus is not one-to-one interaction, but social behaviour in physical and social environments populated with many natural as well as artificial agents. So, the robots must be able to recognize institutions and institutional indicators that humans also recognize as structuring forms of their complex social relationships. This includes, for instance, rules, routines, signs, forms of organization of the material world, social roles, and social forms as organizations or teams.


'''References''':
SILVA, Porfírio, and LIMA, Pedro U., "Institutional Robotics", in Fernando Almeida e Costa ''et al.'' (eds.), Advances in Artificial Life. Proceedings of the 9th European Conference, ECAL 2007, Berlim e Heidelbergh, Springer-Verlag, 2007, pp. 595-604 [http://www.springerlink.com/content/jv82627127585321/fulltext.pdf link]


'''References''':
SILVA, Porfírio, VENTURA, Rodrigo, and LIMA, Pedro U.,"Institutional Environments", in Proc. of Workshop AT2AI: From agent theory to agent implementation, AAMAS 2008 - 7th International Conference on Autonomous Agents and Multiagent Systems, Estoril, Portugal, 2008 [http://www.ofai.at/research/agents/conf/at2ai6/papers/Silva.pdf link]


SILVA, Porfírio, and LIMA, Pedro U., "Institutional Robotics", in Fernando Almeida e Costa ''et al.'' (eds.), Advances in Artificial Life. Proceedings of the 9th European Conference, ECAL 2007, Berlim e Heidelbergh, Springer-Verlag, 2007, pp. 595-604 [[Media:Institutional-Robotics-final.pdf|PDF]]
SILVA, Porfírio, PEREIRA, José N., and LIMA, Pedro U., "Institutional Robotics: Institutions for Social Robots. International Journal of Social Robotics, DOI 10.1007/s12369-015-0300-4, 2015 [http://link.springer.com/article/10.1007/s12369-015-0300-4 link]


SILVA, Porfírio, VENTURA, Rodrigo, and LIMA, Pedro,"Institutional Environments", in Proc. of Workshop AT2AI: From agent theory to agent implementation, AAMAS 2008 - 7th International Conference on Autonomous Agents and Multiagent Systems, Estoril, Portugal, 2008 [[Media:Institutional-Environments_AT2AI-6_WorkingNotes.pdf|PDF]]


== The roundabout case study ==


== The roundabour casestudy ==
To put to a first test some of the basic concepts of Institutional Robotics, there is an ongoing case study with a minimalist setting.
We want a set of robots to become able to behave as car drivers in an urban traffic scenario. The minimal setup represents several roundabouts connected by a small system of streets. Robots will have to know how to deal with basic aspects of the road code, some traffic signs, and agents playing special roles (police robots).  Some more general rules, typical of human societies (“respect the integrity of other agents”, for example) must also be acknowledged and respected by the robots. Teams of e-pucks (the small robots being used) should be able to act in a “normal”, “conformist” way in the institutional environment while competing for the realization of a particular task (for example, collecting energy). But the robots could also be able, guided by utility-based considerations, to opt for inobservance of the institutional framework. The experiment will address the consequences of that co-existence of "conformist" and "non-conformist" behaviours within the same “robotic society”.


Está actualmente em curso um estudo de caso com um cenário minimalista para um primeiro teste de alguns dos conceitos da Robótica Institucionalista.


O objectivo é termos robots capazes de comportar-se como condutores de automóveis num cenário de tráfego urbano: várias rotundas ligadas por um pequeno sistema de ruas. Para isso terão de conhecer, nomeadamente, as normas constantes do código da estrada, os sinais que regulam o trânsito, os agentes com autoridade nesse contexto (polícias de trânsito) – mas também certas normas mais gerais que são aceites nas sociedades humanas (a importância de respeitar a integridade dos outros, por exemplo).
The case study explores an aspect that is essential in many institutions. Most of the time, institutions have both material and mental aspects. The roundabout in a traffic scenario instances that property. On the one hand, the roundabout, just due to its physical features, constrains behaviour:  vehicles can not move on, drivers must choose either to turn right or to turn left if they want to proceed. Now, doing that (deciding in a conformist way, in Portugal, to go right) implies invoking a mental entity, a rule.  It is well known that this rule is not the same in all countries. But it always combines with material features of the roundabout to play its role in a institutional environment.
Os pequenos robots que estão a ser utilizados, e-pucks, deverão ser capazes de respeitar – mas também de desrespeitar! – esse ambiente institucional, ao mesmo tempo que são colocados a competir na realização de uma determinada tarefa. Sabendo, por exemplo, que penalizações podem resultar de obedecer ou desobedecer a certas prescrições, terão, a partir de certa altura, a possibilidade de escolher entre serem “conformistas” e “bem comportados” ou “não conformistas” e capazes de desrespeitar as regras para tentarem ser mais eficientes na prossecução da sua tarefa. E aí começam as complicações…


O estudo de caso pretende explorar um aspecto que, sendo essencial em muitas instituições, está também presente numa rotunda como parte do sistema do controlo do trânsito. É que os efeitos da existência da rotunda num cenário de tráfego urbano resultam de uma combinação de dois aspectos. Por um lado, a rotunda, devido apenas às suas características físicas, significa um constrangimento: os veículos não podem seguir em frente, têm de contornar pela direita ou pela esquerda. Mas, para decidir o comportamento adequado face à rotunda, é preciso fazer apelo a uma entidade mental, uma regra: a circulação faz-se contornando pela direita. Essa regra é, como sabe, diferente noutros países. Ora, esta combinação de elementos físicos e elementos mentais nas ferramentas usadas na organização das sociedades é estratégica na compreensão das instituições e das capacidades que têm de ter os agentes para compreenderem as instituições.




[[Image:26set08-rotunda-epucks-142w.jpg]]
[[Image:26set08-rotunda-epucks-142w.jpg]]


<object width="425" height="350"> <param name="movie" value="http://www.youtube.com/v/mEImm1aAH_o"> </param> <embed src="http://www.youtube.com/v/mEImm1aAH_o" type="application/x-shockwave-flash" width="425" height="350"> </embed> </object>
Part of the experimental setup at Researchers’ Night 2008 (26th September 2008, Centro Cultural de Belém)
 
 
 
 
[[Image:Experiment_small.png]]
 
A step of the experiment ahead
 
 
 
<html><object width="425" height="350"> <param name="movie" value="http://www.youtube.com/v/mEImm1aAH_o"> </param> <embed src="http://www.youtube.com/v/mEImm1aAH_o" type="application/x-shockwave-flash" width="425" height="350"> </embed> </object></html>
 
Basic behaviours: obstacles avoidance, wall following.
 
 
 
 
<html><object width="425" height="344"><param name="movie" value="http://www.youtube.com/v/PUuHuMEyc1A&hl=en&fs=1"></param><param name="allowFullScreen" value="true"></param><param name="allowscriptaccess" value="always"></param><embed src="http://www.youtube.com/v/PUuHuMEyc1A&hl=en&fs=1" type="application/x-shockwave-flash" allowscriptaccess="always" allowfullscreen="true" width="425" height="344"></embed></object></html>
 
Cognitions does not preclude emergence: one e-puck got stuck on a small elevation; another robot, just passing through, and not being aware of the situation, smooths down the elevation with its own weight and frees its fellow.
 
 
== UML Models ==
 
In the development of our work with Institutional Robotics a UML model structure was created. This structure is guided by a set of tuple definitions previously presented and aims to provide a prescriptive guideline to the actual implementation of IR concepts in robots. Some diagrams for the roundabout case study are presented in the links below.
 
- [http://users.isr.ist.utl.pt/~jpereira/IR_uml/IR%20Concept%20Model%20-%20Class%20Diagram.pdf IR Concept Model - Class Diagram]
 
- [http://users.isr.ist.utl.pt/~jpereira/IR_uml/IR%20Roundabout%20Case%20Exp0%20Model%20-%20Class%20Diagram.pdf IR Roundabout Case Study Experiment 0 - Class Diagram]


colocar aqui dois vídeos da noite dos investigadores
- [http://users.isr.ist.utl.pt/~jpereira/IR_uml/IR%20Roundabout%20Case%20Exp0%20Model%20-%20Use%20Case%20Diagram.pdf IR Roundabout Case Study Experiment 0 - Use Case Diagram]
 
- [http://users.isr.ist.utl.pt/~jpereira/IR_uml/IR%20Roundabout%20Case%20Exp1%20Model%20-%20Class%20Diagram.pdf IR Roundabout Case Study Experiment 1 - Class Diagram]
 
- [http://users.isr.ist.utl.pt/~jpereira/IR_uml/IR%20Roundabout%20Case%20Exp1%20Model%20-%20Sequence%20Diagram.pdf IR Roundabout Case Study Experiment 1 - Sequence Diagram]
 
- [http://users.isr.ist.utl.pt/~jpereira/IR_uml/IR%20Roundabout%20Case%20Exp1%20Model%20-%20Use%20Case%20Diagram.pdf IR Roundabout Case Study Experiment 1 - Use Case Diagram]
 
- [http://users.isr.ist.utl.pt/~jpereira/IR_uml/IR%20Roundabout%20Case%20Exp2%20Model%20-%20Class%20Diagram.pdf IR Roundabout Case Study Experiment 2 - Class Diagram]
 
- [http://users.isr.ist.utl.pt/~jpereira/IR_uml/IR%20Roundabout%20Case%20Exp2%20Model%20-%20Use%20Case%20Diagram.pdf IR Roundabout Case Study Experiment 2 - Use Case Diagram]


== "From Human Societies to Artificial Societies" ==
== "From Human Societies to Artificial Societies" ==
Line 31: Line 71:
The series of conferences "From Human Societies to Artificial Societies" are a forum for transdisciplinar reflection on social and collective phenomena, establishing a bridge between Collective Robotics projects under development at ISR/IST and theoretical working on philosophy and social sciences.   
The series of conferences "From Human Societies to Artificial Societies" are a forum for transdisciplinar reflection on social and collective phenomena, establishing a bridge between Collective Robotics projects under development at ISR/IST and theoretical working on philosophy and social sciences.   


The first edition of this series of conferences was hold between April and July 2008. Details (in portuguese) [http://institutionalrobotics.wordpress.com/ here]).
* The first edition of this series of conferences was held between April and July 2008. Details (in portuguese) [http://institutionalrobotics.wordpress.com/ here]).
 
* The 2009 edition was held on February and March ([http://institutionalrobotics2009.isr.ist.utl.pt/ more in portuguese here]).
 
* The 2011 edition was held on April and May ([http://institutionalrobotics2011.isr.ist.utl.pt/ more in portuguese here]).
 
== FCT BioInstBots project ==


The 2009 edition will be hold on next February and March (program to be announced soon).
The [http://mediawiki.isr.ist.utl.pt/wiki/From_Bio-Inspired_to_Institutional-Inspired_Collective_Robotics BioInstBots] project is a national project funded by FCT where we explore the Institutional Robotics concepts and compare them to bio-inspired approaches to collective robotics. Check the pages of the project for more information.


== Institutional Robotics blog ==
== Institutional Robotics blog ==


[http://institutionalrobotics.blogspot.com/  Institutional Robotics] is a weblog edited by Porfírio Silva.  "An ongoing scientific, philosophical, and pragmatic research on Collective Robotics. A strategy to conceptualize multi-robot systems, which takes institutions as the main tool of social life of robots." Open to comments, criticism, questions, suggestions.
[http://institutionalrobotics.blogspot.com/  Institutional Robotics] is a weblog edited by Porfírio Silva.  "An ongoing scientific, philosophical, and pragmatic research on Collective Robotics. A strategy to conceptualize multi-robot systems, which takes institutions as the main tool of social life of robots." Open to comments, criticism, questions, suggestions.

Latest revision as of 10:56, 14 May 2015

Institutional Robotics is a new strategy to conceptualize multi-robot systems, which takes institutions as the main tool of social life of robots with bounded rationality and bounded autonomy. This institutional approach intends to get inspiration from philosophical and social sciences research on social and collective phenomena, and is mainly inspired by concepts from Institutional Economics, an alternative to mainstream neoclassical economic theory.

The goal is to have multiple robots developing activities in a shared environment with human, in such a way that humans can interact with robots "naturally", intuitively, without a need to learn specific techniques to deal with them. The focus is not one-to-one interaction, but social behaviour in physical and social environments populated with many natural as well as artificial agents. So, the robots must be able to recognize institutions and institutional indicators that humans also recognize as structuring forms of their complex social relationships. This includes, for instance, rules, routines, signs, forms of organization of the material world, social roles, and social forms as organizations or teams.

References:

SILVA, Porfírio, and LIMA, Pedro U., "Institutional Robotics", in Fernando Almeida e Costa et al. (eds.), Advances in Artificial Life. Proceedings of the 9th European Conference, ECAL 2007, Berlim e Heidelbergh, Springer-Verlag, 2007, pp. 595-604 link

SILVA, Porfírio, VENTURA, Rodrigo, and LIMA, Pedro U.,"Institutional Environments", in Proc. of Workshop AT2AI: From agent theory to agent implementation, AAMAS 2008 - 7th International Conference on Autonomous Agents and Multiagent Systems, Estoril, Portugal, 2008 link

SILVA, Porfírio, PEREIRA, José N., and LIMA, Pedro U., "Institutional Robotics: Institutions for Social Robots. International Journal of Social Robotics, DOI 10.1007/s12369-015-0300-4, 2015 link


The roundabout case study

To put to a first test some of the basic concepts of Institutional Robotics, there is an ongoing case study with a minimalist setting. We want a set of robots to become able to behave as car drivers in an urban traffic scenario. The minimal setup represents several roundabouts connected by a small system of streets. Robots will have to know how to deal with basic aspects of the road code, some traffic signs, and agents playing special roles (police robots). Some more general rules, typical of human societies (“respect the integrity of other agents”, for example) must also be acknowledged and respected by the robots. Teams of e-pucks (the small robots being used) should be able to act in a “normal”, “conformist” way in the institutional environment while competing for the realization of a particular task (for example, collecting energy). But the robots could also be able, guided by utility-based considerations, to opt for inobservance of the institutional framework. The experiment will address the consequences of that co-existence of "conformist" and "non-conformist" behaviours within the same “robotic society”.


The case study explores an aspect that is essential in many institutions. Most of the time, institutions have both material and mental aspects. The roundabout in a traffic scenario instances that property. On the one hand, the roundabout, just due to its physical features, constrains behaviour: vehicles can not move on, drivers must choose either to turn right or to turn left if they want to proceed. Now, doing that (deciding in a conformist way, in Portugal, to go right) implies invoking a mental entity, a rule. It is well known that this rule is not the same in all countries. But it always combines with material features of the roundabout to play its role in a institutional environment.


Part of the experimental setup at Researchers’ Night 2008 (26th September 2008, Centro Cultural de Belém)



A step of the experiment ahead


Basic behaviours: obstacles avoidance, wall following.



Cognitions does not preclude emergence: one e-puck got stuck on a small elevation; another robot, just passing through, and not being aware of the situation, smooths down the elevation with its own weight and frees its fellow.


UML Models

In the development of our work with Institutional Robotics a UML model structure was created. This structure is guided by a set of tuple definitions previously presented and aims to provide a prescriptive guideline to the actual implementation of IR concepts in robots. Some diagrams for the roundabout case study are presented in the links below.

- IR Concept Model - Class Diagram

- IR Roundabout Case Study Experiment 0 - Class Diagram

- IR Roundabout Case Study Experiment 0 - Use Case Diagram

- IR Roundabout Case Study Experiment 1 - Class Diagram

- IR Roundabout Case Study Experiment 1 - Sequence Diagram

- IR Roundabout Case Study Experiment 1 - Use Case Diagram

- IR Roundabout Case Study Experiment 2 - Class Diagram

- IR Roundabout Case Study Experiment 2 - Use Case Diagram

"From Human Societies to Artificial Societies"

The series of conferences "From Human Societies to Artificial Societies" are a forum for transdisciplinar reflection on social and collective phenomena, establishing a bridge between Collective Robotics projects under development at ISR/IST and theoretical working on philosophy and social sciences.

  • The first edition of this series of conferences was held between April and July 2008. Details (in portuguese) here).

FCT BioInstBots project

The BioInstBots project is a national project funded by FCT where we explore the Institutional Robotics concepts and compare them to bio-inspired approaches to collective robotics. Check the pages of the project for more information.

Institutional Robotics blog

Institutional Robotics is a weblog edited by Porfírio Silva. "An ongoing scientific, philosophical, and pragmatic research on Collective Robotics. A strategy to conceptualize multi-robot systems, which takes institutions as the main tool of social life of robots." Open to comments, criticism, questions, suggestions.