.png){kind=icon}
.png){kind=icon}
Return
Morpho Evolution With Learning Using a Controller Archive as an Inheritance Mechanism
.png){kind=icon}
OA
AI
DOI：10.1109/TCDS.2022.3148543.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Most work in evolutionary robotics centers on evolving a controller for a fixed body plan. However, previous studies suggest that simultaneously evolving both controller and body plan could open up many interesting possibilities. However, the joint optimization of body plan and control via evolutionary processes can be challenging in rich morphological spaces. This is because offspring can have body plans that are very different from either of their parents, leading to a potential mismatch between the structure of an inherited neural controller and the new body. To address this, we propose a framework that combines an evolutionary algorithm to generate body plans and a learning algorithm to optimize the parameters of a neural controller. The topology of this controller is created once the body plan of each offspring has been generated. The key novelty of the approach is to add an external archive for storing learned controllers that map to explicit types of robots (where this is defined with respect to the features of the body plan). By initiating learning from a controller with an appropriate structure inherited from the archive, rather than from a randomly initialized one, we show that both the speed and magnitude of learning increase over time when compared to an approach that starts from scratch, using two tasks and three environments. The framework also provides new insights into the complex interactions between evolution and learning.
Keywords:
Robots
Optimization
Topology
Statistics
Sociology
Process control
Aerospace electronics
Embodied intelligence
evolutionary robotics
Journal
IF:
4.9
Papers:
1.0K
Citations:
3.5K
View more organizations