Toward Anthropomimetic Robotics: Development, Simulation, and Control of a Musculoskeletal Torso

Autor: Michael Jantsch, Steffen Wittmeier, Hugo Gravato Marques, Nenad Bascarevic, Bratislav Svetozarevic, Bhargav Mitra, Kosta Jovanovic, Rob Knight, Veljko Potkonjak, Owen Holland, David Devereux, Alois Knoll, Alan Diamond, Rolf Pfeifer, Predrag Milosavljevic, Konstantinos Dalamagkidis, Cristiano Alessandro
Přispěvatelé: Wittmeier, S, Alessandro, C, Bascarevic, N, Dalamagkidis, K, Devereux, D, Diamond, A, Jantsch, M, Jovanovic, K, Knight, R, Marques, H, Milosavljevic, P, Mitra, B, Svetozarevic, B, Potkonjak, V, Pfeifer, R, Knoll, A, Holland, O
Rok vydání: 2013
Předmět:
0209 industrial biotechnology
Physics-based modeling
Computer science
02 engineering and technology
General Biochemistry
Genetics and Molecular Biology

Tendons
03 medical and health sciences
020901 industrial engineering & automation
0302 clinical medicine
Morphological computation
Classical control theory
Motor control
Artificial Intelligence
Human–computer interaction
medicine
Humans
Computer Simulation
Anthropomimetic robot
Algorithms
Anthropometry
Artificial intelligence
Computer Simulation
Equipment Design
Humans
Mechanoreceptors
Models
Theoretical
Neural Networks (Computer)
Physics
Robotics
Skeleton
Software
Tendons
Torso

Control (linguistics)
Skeleton
Anthropometry
business.industry
Physics
Torso
Robotics
Equipment Design
Human body
Models
Theoretical

ddc
medicine.anatomical_structure
Robot
Neural Networks
Computer

Artificial intelligence
business
Mechanoreceptors
Algorithms
Software
Simulation
030217 neurology & neurosurgery
Research Article
Zdroj: Artificial Life
Artif Life
ISSN: 1530-9185
1064-5462
DOI: 10.1162/artl_a_00088
Popis: Anthropomimetic robotics differs from conventional approaches by capitalizing on the replication of the inner structures of the human body, such as muscles, tendons, bones, and joints. Here we present our results of more than three years of research in constructing, simulating, and, most importantly, controlling anthropomimetic robots. We manufactured four physical torsos, each more complex than its predecessor, and developed the tools required to simulate their behavior. Furthermore, six different control approaches, inspired by classical control theory, machine learning, and neuroscience, were developed and evaluated via these simulations or in small-scale setups. While the obtained results are encouraging, we are aware that we have barely exploited the potential of the anthropomimetic design so far. But, with the tools developed, we are confident that this novel approach will contribute to our understanding of morphological computation and human motor control in the future.
Databáze: OpenAIRE