Swarm intelligence/Innovation

From Wikiversity
Jump to navigation Jump to search
SDG1: Industry, Innovation and Infrastructure - Learning Resouce supports the SDGs - UN-Guidelines[1]

Swarm intelligence (SI) can be applied on the collective behavior that work collaboratively towards a common goal. The decentralized, divers knowledge and expertise in different domain (e.g. medicine, mathematics, geoinformatics, ...) lead in a self-organized Open Innovation Ecosystems to problem solving in complex dynamic systems. The concept is employed especially in systemic problem solving whenever a single discipline cannot provide a sufficient solution because optimization in one discipline could lead to in acceptable impacts in other areas. Even if the concept was introduced by Gerardo Beni and Jing Wang in 1989, in the context of cellular robotic systems[2] the importance for global challenges like Climat Change and global warming have a similar structure.

SI systems consist is visible in Open Innovation Ecosystems. The agents are in this context e.g. scientist with a cross-disciplinary team interacting locally with one another and with their environment for which the problem solving is designed for.

If we look on inspiration for SI from nature, especially biological systems, simple individual solve complex problems a single individual is not able to solve:

  • the individuals use communication and interaction the other to solve problem. Furthermore key performance indicators of individuals should not have the top priority.
  • the individuals need trust in the other individuals, because full insight in the linked disciplines is not possible,
  • the individuals in the team listen to other team members integrate their recommendation in the personal decision making
  • the individuals donate their expertise to accomplish a common goal

The agents/scientist or decision makers have an overview about their decision making rules in the area of expertise and about interfaces to other disciplines. The well-established interfaces is required so that innovation is triggered in coherent way between all disciplines. In general for global challenges like Climate Change and global warming there is no centralized control structure that is aware of a global solution and could dictate how individual experts should be guided in their research and development domain.

A certain degree of random behaviour and interactions between agents is equivalent to developmental or scientific try and errors. Not all scientific and development pathes are successful. Backtracking methods and even real random problem solving attempts explore the environment of problem space. Team members (e.g. developers, scientists, risk exposed citizens combine their "local" knowledge and the integration of linked individual attempts lead to the emergence of "intelligent" global behavior, unknown to the individual agents.

In contrast to the examples in natural systems of SI like ant colonies, bird flocking, animal herding, bacterial growth, and fish schooling, scientistist and developers can learn from the found global solutions and add them to their problem solving skills.

The general approach of swarm intelligence to human beings as problem solvers in an Open Innovation Ecosystem is not quit clear. Due to the fact that linking to others in a swarm is a key to the emergence of "intelligent" global swarm behavior it can be concluded that a requirement is, that a psycholigical requirement is necessary, that "what's in it for me?" and "maximize my personal benefit" seem to be disadvantage for the accomplishment of common global goals.

Learning Tasks[edit | edit source]

  • Analyse the Ant Colony Algorithm[3][4] and regards the two-dimensional plane as a scientific or developmental problem solving area. Optimal routing of ants towards food can be regarded as searching and optimizing to solutions in problem solving domain. Explain similarities and differences between human problem solving for global challenges and problem solving of ants in a two-dimensional space.
  • Expain similarities and difference of Swarm intelligence and Genetic Algorithms (GA!
  • Describe examples in management of companies, hierachies in politics, ... with pros and cons of application of swarm intelligence of human actors!
  • Describe how short-term vs. long-term goals in Risk Literacy could lead to obstacles for the application of Swarm Intelligience for Problem Solving!
  • Describe similarities between Swarm Intelligence and an Open Innovation Ecosystem and explain why Wikiversity supports as community environment to connect the intelligence of individuals for emergence of new ideas!

See also[edit | edit source]

References[edit | edit source]

  1. UN-Guidelines for Use of SDG logo and the 17 SDG icons (2016/10) - http://www.un.org/sustainabledevelopment/wp-content/uploads/2016/10/UN-Guidelines-for-Use-of-SDG-logo-and-17-icons.October-2016.pdf
  2. Beni, G., Wang, J. Swarm Intelligence in Cellular Robotic Systems, Proceed. NATO Advanced Workshop on Robots and Biological Systems, Tuscany, Italy, June 26–30 (1989)
  3. Dorigo, M., & Gambardella, L. M. (1997). Ant colony system: a cooperative learning approach to the traveling salesman problem. IEEE Transactions on evolutionary computation, 1(1), 53-66.
  4. Dréo, J., & Siarry, P. (2002). A new ant colony algorithm using the heterarchical concept aimed at optimization of multiminima continuous functions. Ant algorithms, 216-221.