Toward Computational Motivation for Multi-Agent Systems and Swarms

Khan, Md. Mohiuddin; Kasmarik, Kathryn; Barlow, Michael

doi:10.3389/frobt.2018.00134

Cited by 7 publications

(3 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Most computational models of intrinsic motivation use reinforcement learning in single agent scenarios both in simulation and on real robots, while swarm and multi-agent settings are only rarely studied. Khan et al [49] discuss that multiagent settings may allow for the emergence of new functionality, like communication, and for new models of motivation, like sharing motivations with other agents. In our work, we combine an intrinsic motivation measure with methods of evolutionary computation in a swarm scenario.…”

Section: Intrinsically Motivated Learningmentioning

confidence: 99%

Innate Motivation for Robot Swarms by Minimizing Surprise: From Simple Simulations to Real-World Experiments

Kaiser¹,

Hamann²

2022

IEEE Trans. Robot.

View full text Add to dashboard Cite

Applications of large-scale mobile multi-robot systems can be beneficial over monolithic robots because of higher potential for robustness and scalability. Developing controllers for multi-robot systems is challenging because the multitude of interactions is hard to anticipate and difficult to model. Automatic design using machine learning or evolutionary robotics seem to be options to avoid that challenge, but bring the challenge of designing reward or fitness functions. Generic reward and fitness functions seem unlikely to exist and task-specific rewards often have undesired side effects. Approaches of so-called innate motivation try to avoid the specific formulation of rewards and work instead with different drivers, such as curiosity. Our approach to innate motivation is to minimize surprise, which we implement by maximizing the accuracy of the swarm robot's sensor predictions using neuroevolution. A unique advantage of the swarm robot case is that swarm members populate the robot's environment and can trigger more active behaviors in a selfreferential loop. We summarize our previous simulation-based results concerning behavioral diversity, robustness, scalability, and engineered self-organization, and put them into context. In several new studies, we analyze the influence of the optimizer's hyperparameters, the scalability of evolved behaviors, and the impact of realistic robot simulations. Finally, we present results using real robots that show how the reality gap can be bridged.

show abstract

Section: Intrinsically Motivated Learningmentioning

confidence: 99%

Innate Motivation for Robot Swarms by Minimizing Surprise: From Simple Simulations to Real-World Experiments

Kaiser¹,

Hamann²

2022

IEEE Trans. Robot.

View full text Add to dashboard Cite

show abstract

“…Merkezi olmayan sistem, ağda alt görevleri gerçekleştiren ve birlikte kararlar alan bir grup aracı oluşturur [185,186]. Merkezi kontrole sahip etmenlerin aksine, merkezi olmayan sistem, birden fazla etmenin üretim sistemindeki görevlere ve karar verme sürecine katkıda bulunmasını sağlayarak sistemin verimliliğinin artırılmasına katkı sağlar [181,187,188]. Bununla birlikte, her iki sistem de üretim sistemindeki birden fazla etmenin etkileşimini içermektedir.…”

Section: Platformların Iş Birliği (Platform Interoperability)unclassified

IoT uygulamalarında çok etmenli sistemlerin (MAS) birlikte çalışabilirliğinin rolü: Akıllı üretim sistemlerindeki son gelişmeler üzerine bir araştırma

Uslu

2022

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

Çok Etmenli Sistemler (MAS), Nesnelerin İnterneti (IoT) uygulamaları içerisinde, akıllı nesnelerin etmenler (agent) olarak tasarlanması aracılığı ile birden çok akıllı cihazdan bilgilerin algılamasını, toplamasını, paylaşmasını, pekiştirilmesini ve revize edilmesini mümkün kılmaktadır. Çok etmenli sistemler ve ilgili araçlar, sistemlerin optimizasyonunda kullanılan paradigmalar için önemli değişikliklere katkıda bulunmakla birlikte, MAS hakkındaki mevcut literatür, IoT cihazlarının gelişmiş işbirliğini açıklayan modern dağıtılmış hesaplama yöntemlerini açıklamak için yeterli düzeyde değildir. Bu araştırma, IoT içerisinde yer alan akıllı cihazların, MAS teknolojisi ile birlikte çalışabilirliği hakkında kapsamlı bir araştırma sunmaktadır. Bu kapsamda, önce etmen tabanlı sistemler ve IoT teknolojisi hakkında genel bir bilgilendirilme sunularak, çok etmenli sistemler içerisinde birlikte çalışabilirliğin önemi ve üretim sistemleri özelinde çoklu etmen teknolojisinin, sensör verilerini yakalamadan karar vermeye kadar çeşitli amaçlarla nasıl kullanılabileceğini açıklanmıştır. Çok etmenli sistemlerde birlikte çalışabilirlik için geliştirilen ve üreticiden bağımsız olarak birbirini anlayabilen iki ana dil hakkında bilgilendirme sunulmuştur. MAS'in IoT tabanlı kablosuz sensör ağında (WSN'ler) veri toplama ve entegrasyonu açıklanmıştır. Akıllı üretim sistemlerinin tasarımında, MAS'in geliştirmeye açık alanları ve gelecekteki trendlerinde IoT uygulamasını ele almak, bu makalenin bir diğer katkısı olarak sunulmuştur. Araştırmanın, IoT ve MAS üzeride çalışan araştırmacılar, tasarımcılar ve yöneticiler için bir yol gösterici olması beklenmektedir.

show abstract

“…In fact, to fully grasp the extent of current and future human–machine interaction and their socio-technological co-evolution, it is essential to understand that erobots are not just their perceived characters (e.g., Harmony’s VR character or robotic-headed doll), but are composed of vast interconnected, multi-layered, and (increasingly adaptative) multi-agent systems that enable their (emerging) capabilities [ 161 , 228 ]. For example, when people interact with an erobot, they engage with its interfaces (e.g., application and characters), but the erotic capabilities of those interfaces also depend upon clusters of enabling-systems including: software-hardware, cloud-based algorithms learning from multiple users, databanks, search engines, and humans (e.g., programmers, engineers, designers, artists, and partners).…”

Section: Towards Eroboticsmentioning

confidence: 99%

Foundations of Erobotics

Dubé

Anctil

2020

Int J of Soc Robotics

View full text Add to dashboard Cite

Technology is giving rise to artificial erotic agents, which we call erobots ( erôs + bot). Erobots, such as virtual or augmented partners, erotic chatbots, and sex robots, increasingly expose humans to the possibility of intimacy and sexuality with artificial agents. Their advent has sparked academic and public debates: some denounce their risks (e.g., promotion of harmful sociosexual norms), while others defend their potential benefits (e.g., health, education, and research applications). Yet, the scientific study of human–machine erotic interaction is limited; no comprehensive theoretical models have been proposed and the empirical literature remains scarce. The current research programs investigating erotic technologies tend to focus on the risks and benefits of erobots, rather than providing solutions to resolve the former and enhance the latter. Moreover, we feel that these programs underestimate how humans and machines unpredictably interact and co-evolve, as well as the influence of sociocultural processes on technological development and meaning attribution. To comprehensively explore human–machine erotic interaction and co-evolution, we argue that we need a new unified transdisciplinary field of research—grounded in sexuality and technology positive frameworks—focusing on human-erobot interaction and co-evolution as well as guiding the development of beneficial erotic machines. We call this field Erobotics . As a first contribution to this new discipline, this article defines Erobotics and its related concepts; proposes a model of human-erobot interaction and co-evolution; and suggests a path to design beneficial erotic machines that could mitigate risks and enhance human well-being.

show abstract

Toward Computational Motivation for Multi-Agent Systems and Swarms

Cited by 7 publications

References 81 publications

Innate Motivation for Robot Swarms by Minimizing Surprise: From Simple Simulations to Real-World Experiments

Innate Motivation for Robot Swarms by Minimizing Surprise: From Simple Simulations to Real-World Experiments

IoT uygulamalarında çok etmenli sistemlerin (MAS) birlikte çalışabilirliğinin rolü: Akıllı üretim sistemlerindeki son gelişmeler üzerine bir araştırma

Foundations of Erobotics

Contact Info

Product

Resources

About