DART: Diversity-enhanced Autonomy in Robot Teams
Autor: | Nora Ayanian |
---|---|
Rok vydání: | 2019 |
Předmět: |
0209 industrial biotechnology
Dart Computer science Applied Mathematics Mechanical Engineering media_common.quotation_subject Multi-agent system 02 engineering and technology 020901 industrial engineering & automation Artificial Intelligence Human–computer interaction Modeling and Simulation 0202 electrical engineering electronic engineering information engineering Robot 020201 artificial intelligence & image processing Electrical and Electronic Engineering computer Software Autonomy media_common computer.programming_language Diversity (business) |
Zdroj: | The International Journal of Robotics Research. 38:1329-1337 |
ISSN: | 1741-3176 0278-3649 |
Popis: | This paper defines the research area of Diversity-enhanced Autonomy in Robot Teams (DART), a novel paradigm for the creation and design of policies for multi-robot coordination. Although current approaches to multi-robot coordination have been successful in structured, well-understood environments, they have not been successful in unstructured, uncertain environments, such as disaster response. Although robot hardware has advanced significantly in the past decade, the way we solve multi-robot problems has not. Even with significant advances in the field of multi-robot systems, the same problem-solving paradigm has remained: assumptions are made to simplify the problem, and a solution is optimized for those assumptions and deployed to the entire team. This results in brittle solutions that prove incapable if the original assumptions are invalidated. This paper introduces a new multi-robot problem-solving paradigm which uses a diverse set of control policies that work together synergistically within the same team of robots. Such an approach will make multi-robot systems more robust in unstructured and uncertain environments, such as in disaster response, environmental monitoring, and military applications, and allow multi-robot systems to extend beyond the highly structured and highly controlled environments where they are successful today. |
Databáze: | OpenAIRE |
Externí odkaz: |