The Effects of Learning in Morphologically Evolving Robot Systems

• URL: http://arxiv.org/abs/2107.08249v1
• Date: Sat, 17 Jul 2021 14:38:26 GMT
• Title: The Effects of Learning in Morphologically Evolving Robot Systems
• Authors: Jie Luo, Jakub M. Tomczak, Agoston E. Eiben
• Abstract summary: We set up a system where modular robots can create offspring that inherit the bodies of parents by recombination and mutation. The first approach entails solely evolution which means the brain of a robot child is inherited from its parents. The second approach is evolution plus learning which means the brain of a child is inherited as well, but additionally is developed by a learning algorithm.
• Score: 10.592277756185046
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When controllers (brains) and morphologies (bodies) of robots simultaneously evolve, this can lead to a problem, namely the brain & body mismatch problem. In this research, we propose a solution of lifetime learning. We set up a system where modular robots can create offspring that inherit the bodies of parents by recombination and mutation. With regards to the brains of the offspring, we use two methods to create them. The first one entails solely evolution which means the brain of a robot child is inherited from its parents. The second approach is evolution plus learning which means the brain of a child is inherited as well, but additionally is developed by a learning algorithm - RevDEknn. We compare these two methods by running experiments in a simulator called Revolve and use efficiency, efficacy, and the morphology intelligence of the robots for the comparison. The experiments show that the evolution plus learning method does not only lead to a higher fitness level, but also to more morphologically evolving robots. This constitutes a quantitative demonstration that changes in the brain can induce changes in the body, leading to the concept of morphological intelligence, which is quantified by the learning delta, meaning the ability of a morphology to facilitate learning.

Related papers

• Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignment [65.268245109828]
  We examine algorithms for conducting credit assignment in artificial neural networks that are inspired or motivated by neurobiology. We organize the ever-growing set of brain-inspired learning schemes into six general families and consider these in the context of backpropagation of errors. The results of this review are meant to encourage future developments in neuro-mimetic systems and their constituent learning processes.
  arXiv  Detail & Related papers  (2023-12-01T05:20:57Z)
• Lamarck's Revenge: Inheritance of Learned Traits Can Make Robot Evolution Better [2.884244918665901]
  We investigate the question What if the 18th-century biologist Lamarck was not completely wrong and individual traits learned during a lifetime could be passed on to offspring through inheritance?'' Within this framework, we compare a Lamarckian system, where learned bits of the brain are inheritable, with a Darwinian system, where they are not.
  arXiv  Detail & Related papers  (2023-09-22T15:29:15Z)
• Universal Morphology Control via Contextual Modulation [52.742056836818136]
  Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control. Existing methods utilize graph neural networks or transformers to handle heterogeneous state and action spaces across different morphologies. We propose a hierarchical architecture to better model this dependency via contextual modulation.
  arXiv  Detail & Related papers  (2023-02-22T00:04:12Z)
• HERD: Continuous Human-to-Robot Evolution for Learning from Human Demonstration [57.045140028275036]
  We show that manipulation skills can be transferred from a human to a robot through the use of micro-evolutionary reinforcement learning. We propose an algorithm for multi-dimensional evolution path searching that allows joint optimization of both the robot evolution path and the policy.
  arXiv  Detail & Related papers  (2022-12-08T15:56:13Z)
• Comparing lifetime learning methods for morphologically evolving robots [3.6095388702618414]
  Evolving morphologies and controllers of robots simultaneously leads to a problem. Even if the parents have well-matching bodies and brains, the recombination can break this match and cause a body-brain mismatch in their offspring. We argue that this can be mitigated by having newborn robots perform a learning process that optimize their inherited brain quickly after birth.
  arXiv  Detail & Related papers  (2022-03-08T09:49:56Z)
• The Effects of Learning in Morphologically Evolving Robot Systems [8.627180519837657]
  We show that learning can greatly increase task performance and reduce the number of generations required to reach a certain fitness level. Although learning only directly affects the controllers, we demonstrate that the evolved morphologies will be also different. We observe that the learning delta, the performance difference between the inherited and the learned brain, is growing throughout the evolutionary process.
  arXiv  Detail & Related papers  (2021-11-18T18:20:33Z)
• Embodied Intelligence via Learning and Evolution [92.26791530545479]
  We show that environmental complexity fosters the evolution of morphological intelligence. We also show that evolution rapidly selects morphologies that learn faster. Our experiments suggest a mechanistic basis for both the Baldwin effect and the emergence of morphological intelligence.
  arXiv  Detail & Related papers  (2021-02-03T18:58:31Z)
• The Dynamic of Body and Brain Co-Evolution [0.0]
  We introduce a method that permits to co-evolve the body and the control properties of robots. It can be used to adapt the morphological traits of robots with a hand-designed morphological bauplan or to evolve the morphological bauplan as well. Our results indicate that robots with co-adapted body and control traits outperform robots with fixed hand-designed morphologies.
  arXiv  Detail & Related papers  (2020-11-23T14:41:57Z)
• Morphological Development at the Evolutionary Timescale: Robotic Developmental Evolution [5.000272778136268]
  We propose to design a developmental process happening at the phylogenetic timescale. We show that this produces better and qualitatively different gaits than an evolutionary search with only adult robots. Our method is conceptually simple, and can be effective on small or large populations of robots.
  arXiv  Detail & Related papers  (2020-10-28T11:24:23Z)
• A Developmental Neuro-Robotics Approach for Boosting the Recognition of Handwritten Digits [91.3755431537592]
  Recent evidence shows that a simulation of the children's embodied strategies can improve the machine intelligence too. This article explores the application of embodied strategies to convolutional neural network models in the context of developmental neuro-robotics.
  arXiv  Detail & Related papers  (2020-03-23T14:55:00Z)
• Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning [65.88200578485316]
  We present a new meta-learning method that allows robots to quickly adapt to changes in dynamics. Our method significantly improves adaptation to changes in dynamics in high noise settings. We validate our approach on a quadruped robot that learns to walk while subject to changes in dynamics.
  arXiv  Detail & Related papers  (2020-03-02T22:56:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.