Dataset Information

Lamarckian Evolution of Simulated Modular Robots.

ABSTRACT: We study evolutionary robot systems where not only the robot brains but also the robot bodies are evolvable. Such systems need to include a learning period right after 'birth' to acquire a controller that fits the newly created body. In this paper we investigate the possibility of bootstrapping infant robot learning through employing Lamarckian inheritance of parental controllers. In our system controllers are encoded by a combination of a morphology dependent component, a Central Pattern Generator (CPG), and a morphology independent part, a Compositional Pattern Producing Network (CPPN). This makes it possible to transfer the CPPN part of controllers between different morphologies and to create a Lamarckian system. We conduct experiments with simulated modular robots whose fitness is determined by the speed of locomotion, establish the benefits of inheriting optimized parental controllers, shed light on the conditions that influence these benefits, and observe that changing the way controllers are evolved also impacts the evolved morphologies.

SUBMITTER: Jelisavcic M

PROVIDER: S-EPMC7805734 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Lamarckian Evolution of Simulated Modular Robots.

Jelisavcic Milan M Glette Kyrre K Haasdijk Evert E Eiben A E AE

Frontiers in robotics and AI 20190218

We study evolutionary robot systems where not only the robot brains but also the robot bodies are evolvable. Such systems need to include a learning period right after 'birth' to acquire a controller that fits the newly created body. In this paper we investigate the possibility of bootstrapping infant robot learning through employing Lamarckian inheritance of parental controllers. In our system controllers are encoded by a combination of a morphology dependent component, a Central Pattern Genera ...[more]

PMID: 33501026

Similar Datasets

Project description:A major goal of autonomous robot collectives is to robustly perform complex tasks in unstructured environments by leveraging hardware redundancy and the emergent ability to adapt to perturbations. In such collectives, large numbers is a major contributor to system-level robustness. Designing robot collectives, however, requires more than isolated development of hardware and software that supports large scales. Rather, to support scalability, we must also incorporate robust constituents and weigh interrelated design choices that span fabrication, operation, and control with an explicit focus on achieving system-level robustness. Following this philosophy, we present the first iteration of a new framework toward a scalable and robust, planar, modular robot collective capable of gradient tracking in cluttered environments. To support co-design, our framework consists of hardware, low-level motion primitives, and control algorithms validated through a kinematic simulation environment. We discuss how modules made primarily of flexible printed circuit boards enable inexpensive, rapid, low-precision manufacturing; safe interactions between modules and their environment; and large-scale lattice structures beyond what manufacturing tolerances allow using rigid parts. To support redundancy, our proposed modules have on-board processing, sensing, and communication. To lower wear and consequently maintenance, modules have no internally moving parts, and instead move collaboratively via switchable magnets on their perimeter. These magnets can be in any of three states enabling a large range of module configurations and motion primitives, in turn supporting higher system adaptability. We introduce and compare several controllers that can plan in the collective's configuration space without restricting motion to a discrete occupancy grid as has been done in many past planners. We show how we can incentively redundant connections to prevent single-module failures from causing collective-wide failure, explore bad configurations which impede progress as a result of the motion constraints, and discuss an alternative "naive" planner with improved performance in both clutter-free and cluttered environments. This dedicated focus on system-level robustness over all parts of a complete design cycle, advances the state-of-the-art robots capable of long-term exploration.

Dataset Information

Lamarckian Evolution of Simulated Modular Robots.

Publications

Lamarckian Evolution of Simulated Modular Robots.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets