Evolution and Morphogenesis of Simulated Modular Robots: A Comparison Between a Direct and Generative Encoding

Author(s):  
Frank Veenstra ◽  
Andres Faina ◽  
Sebastian Risi ◽  
Kasper Stoy
Symmetry ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 471
Author(s):  
Jai Hoon Park ◽  
Kang Hoon Lee

Designing novel robots that can cope with a specific task is a challenging problem because of the enormous design space that involves both morphological structures and control mechanisms. To this end, we present a computational method for automating the design of modular robots. Our method employs a genetic algorithm to evolve robotic structures as an outer optimization, and it applies a reinforcement learning algorithm to each candidate structure to train its behavior and evaluate its potential learning ability as an inner optimization. The size of the design space is reduced significantly by evolving only the robotic structure and by performing behavioral optimization using a separate training algorithm compared to that when both the structure and behavior are evolved simultaneously. Mutual dependence between evolution and learning is achieved by regarding the mean cumulative rewards of a candidate structure in the reinforcement learning as its fitness in the genetic algorithm. Therefore, our method searches for prospective robotic structures that can potentially lead to near-optimal behaviors if trained sufficiently. We demonstrate the usefulness of our method through several effective design results that were automatically generated in the process of experimenting with actual modular robotics kit.


2018 ◽  
Vol 38 (1) ◽  
pp. 73-89 ◽  
Author(s):  
Meibao Yao ◽  
Christoph H. Belke ◽  
Hutao Cui ◽  
Jamie Paik

Reconfigurability in versatile systems of modular robots is achieved by changing the morphology of the overall structure as well as by connecting and disconnecting modules. Recurrent connectivity changes can cause misalignment that leads to mechanical failure of the system. This paper presents a new approach to reconfiguration, inspired by the art of origami, that eliminates connectivity changes during transformation. Our method consists of an energy-optimal reconfiguration planner that generates an initial 2D assembly pattern and an actuation sequence of the modular units, both resulting in minimum energy consumption. The algorithmic framework includes two approaches, an automatic modeling algorithm as well as a heuristic algorithm. We further demonstrate the effectiveness of our method by applying the algorithms to Mori, a modular origami robot, in simulation. Our results show that the heuristic algorithm yields reconfiguration schemes with high quality, compared with the automatic modeling algorithm, simultaneously saving a considerable amount of computational time and effort.


2017 ◽  
Vol 14 (3) ◽  
pp. 172988141771045 ◽  
Author(s):  
Alberto Brunete ◽  
Avinash Ranganath ◽  
Sergio Segovia ◽  
Javier Perez de Frutos ◽  
Miguel Hernando ◽  
...  

2008 ◽  
Vol 27 (3-4) ◽  
pp. 423-443 ◽  
Author(s):  
Alexander Sproewitz ◽  
Rico Moeckel ◽  
Jérôme Maye ◽  
Auke Jan Ijspeert

Author(s):  
Seong-Ho Kang ◽  
Delbert Tesar

A modular robot system is a collection of actuators, links, and connections that can be arbitrarily assembled into a number of different robot configurations and sequences. High performance modular robots require more than just sophisticated controls. They also need top-quality mechanical components. Bearings in particular must operate well at low speed, have high rotational accuracy, be compact for low weight, and especially be stiff for high positional accuracy. To ensure the successful use of bearings in precision modular robots, knowledge of the bearing properties and requirements are investigated. Background information on various topics such as modular robots, precision modular actuators, and their error sources are described with respect to precision engineering. Extensive literature on thin section bearings is reviewed to examine their use in precision robotic applications. Theoretical studies are performed to calculate bearing stiffness adopting a methodology based on Hertzian theory. This approach is applied to analyze two proposed designs of equivalent-sized crossed roller and four-point bearings, principal bearings used for transmitting all the payload and mass of the robot structure. The maximum deflections and contact stresses for the proposed actuator assembly and loading conditions are estimated and compared including a range of general bearing properties such as friction, cost, and shock resistance.


2017 ◽  
Vol 9 (3) ◽  
pp. 168781401769569 ◽  
Author(s):  
Dongyang Bie ◽  
Gangfeng Liu ◽  
Yu Zhang ◽  
Jie Zhao ◽  
Yanhe Zhu
Keyword(s):  

Author(s):  
Robert O. Ambrose ◽  
Delbert Tesar

Abstract The ability to reconfigure automation equipment will reduce the manufacturing costs of obsolesence, training and maintenance while allowing for a faster response to changes in the product line. A modular philosophy will give the user these advantages, but only if based on a common connection standard. A mechanical connection was selected for the UT Modular Robotics Testbed and used in the designs of four robot joint modules and nine robot link modules. The standard was also used for assecories, such as the testand, loading fixtures and endeffectors. Three years of experiments with this connection standard are reviewed, and used as the basis for new connection designs. Experiments using multiple modules assembled as dextrous robots, as well as experiments focusing on the connection itself, will be described. Goals for future connection standards include designs with upward compatibility, combinations of both mechanical and electrical fittings, and robot triendly constraints that allow for automated or remote assembly of modular robots.


Sign in / Sign up

Export Citation Format

Share Document