Novelty-Based Evolutionary Design of Morphing Underwater Robots

Corucci, Francesco, Calisti, Marcello, Hauser, Helmut and Laschi, Cecilia (2015) Novelty-Based Evolutionary Design of Morphing Underwater Robots. In: GECCO, 2015.

Full content URL: https://doi.org/10.1145/2739480.2754686

Full text not available from this repository.

Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

Recent developments in robotics demonstrated that bioinspiration and embodiement are powerful tools to achieve robust behavior in presence of little control. In this context morphological design is usually performed by humans, following a set of heuristic principles: in general this can be limiting, both from an engineering and an artificial life perspectives. In this work we thus suggest a different approach, leveraging evolutionary techniques. The case study is the one of improving the locomotion capabilities of an existing bioinspired robot. First, we explore the behavior space of the robot to discover a number of qualitatively different morphology-enabled behaviors, from whose analysis design indications are gained. The suitability of novelty search -- a recent open-ended evolutionary algorithm -- for this intended purpose is demonstrated. Second, we show how it is possible to condense such behaviors into a reconfigurable robot capable of online morphological adaptation (morphosis, morphing). Examples of successful morphing are demonstrated, in which changing just one morphological parameter entails a dramatic change in the behavior: this is promising for a future robot design. The approach here adopted represents a novel computed-aided, bioinspired, design paradigm, merging human and artificial creativity. This may result in interesting implications also for artificial life, having the potential to contribute in exploring underwater locomotion "as-it-could-be".

Keywords:Computing methodologies, Artificial intelligence, Planning and scheduling, Robotic planning, Evolutionary robotics, Machine learning, Machine learning approaches, Bio-inspired approaches, Artificial life, Genetic algorithms
Subjects:H Engineering > H671 Robotics
Divisions:College of Science > Lincoln Institute for Agri-Food Technology
ID Code:46187
Deposited On:24 Aug 2021 10:02

Repository Staff Only: item control page