Evolutionary Robotics Controllers with Proprioception Facilitated by Neural-Network-Based Simulators

Antin Phillips; Mathys C. du Plessis

首页> 外文期刊>Artificial life. >Evolutionary Robotics Controllers with Proprioception Facilitated by Neural-Network-Based Simulators

【24h】

Evolutionary Robotics Controllers with Proprioception Facilitated by Neural-Network-Based Simulators

机译：Evolutionary Robotics Controllers with Proprioception Facilitated by Neural-Network-Based Simulators

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

Taking inspiration from the navigation ability of humans, this study investigated a method of providing robotic controllers with a basic sense of position. It incorporated robotic simulators into robotic controllers to provide them with a mechanism to approximate the effects their actions had on the robot. Controllers with and without internal simulators were tested and compared. The proposed controller architecture was shown to outperform the regular controller architecture. However, the longer an internal simulator was executed, the more inaccurate it became. Thus, the performance of controllers with internal simulators reduced over time unless their internal simulator was periodically corrected.

著录项

来源
《Artificial life.》 |2020年第4期|455-483|共29页
作者
Antin Phillips; Mathys C. du Plessis;
展开▼
作者单位

Nelson Mandela University Department of Computing Sciences;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类生物医学工程;
关键词
Evolutionary robotics; neural networks; simulator neural networks; proprioception; path integration;

Evolutionary Robotics Controllers with Proprioception Facilitated by Neural-Network-Based Simulators

摘要

著录项

相关主题

期刊订阅