Extending robot minds through collective learning

IF 27.5 1区计算机科学 Q1 ROBOTICS

Science Robotics Pub Date : 2025-09-24 DOI:10.1126/scirobotics.adv4049

Amanda Prorok

引用次数: 0

Abstract

The current trend toward generalist robot behaviors with monolithic artificial intelligence (AI) models is unsustainable. I advocate for a paradigm shift that embraces distributed architectures for collective robotic intelligence. A modular “mixture-of-robots” approach with specialized interdependent components can achieve superlinear gains, offering benefits in scalability, adaptability, and learning complex interactive skills.

Abstract Image

查看原文本刊更多论文

通过集体学习扩展机器人的思维

目前采用单一人工智能（AI）模型的通才机器人行为的趋势是不可持续的。我提倡一种范式转变，即为集体机器人智能提供分布式架构。具有专门的相互依赖组件的模块化“机器人混合”方法可以实现超线性增益，提供可伸缩性、适应性和学习复杂交互技能方面的好处。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Science Robotics Mathematics-Control and Optimization

CiteScore

30.60

自引率

2.80%

发文量

期刊介绍： Science Robotics publishes original, peer-reviewed, science- or engineering-based research articles that advance the field of robotics. The journal also features editor-commissioned Reviews. An international team of academic editors holds Science Robotics articles to the same high-quality standard that is the hallmark of the Science family of journals. Sub-topics include: actuators, advanced materials, artificial Intelligence, autonomous vehicles, bio-inspired design, exoskeletons, fabrication, field robotics, human-robot interaction, humanoids, industrial robotics, kinematics, machine learning, material science, medical technology, motion planning and control, micro- and nano-robotics, multi-robot control, sensors, service robotics, social and ethical issues, soft robotics, and space, planetary and undersea exploration.