Abstract Concept Learning in Cognitive Robots

نویسندگان

چکیده

Abstract Purpose of Review Understanding and manipulating abstract concepts is a fundamental characteristic human intelligence that currently missing in artificial agents. Without it, the ability these robots to interact socially with humans while performing their tasks would be hindered. However, what needed empower our such capability? In this article, we discuss some recent attempts on cognitive robot modeling underpinned by neurophysiological principles. Recent Findings For advanced learning concepts, an agent needs (robotic) body, because concrete are considered continuum, can learned linking them embodied perceptions. Pioneering studies provided valuable information about simulation demonstrated value robotics approach study aspects cognition. Summary There few successful examples models knowledge based connectionist probabilistic techniques. concept limited at narrow tasks. To make further progress, argue closer collaboration among multiple disciplines required share expertise co-design future studies. Particularly important create benchmark datasets behavior.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Towards concept anchoring for cognitive robots

We present a model for anchoring categorical conceptual information which originates from physical perception and the web. The model is an extension of the anchoring framework which is used to create and maintain over time semantically grounded sensor information. Using the augmented anchoring framework that employs complex symbolic knowledge from a commonsense knowledge base, we attempt to gro...

متن کامل

Towards the Grounding of Abstract Categories in Cognitive Robots

concepts pose a classic challenge for grounded cognition. How can theories that focus on modal simulations explain concepts that do not appear modal? L. W. Barsalou

متن کامل

Same/different abstract-concept learning by pigeons.

Eight pigeons were trained and tested in a simultaneous same/different task. After pecking an upper picture, they pecked a lower picture to indicate same or a white rectangle to indicate different. Increases in the training set size from 8 to 1,024 items produced improved transfer from 51.3% to 84.6%. This is the first evidence that pigeons can perform a two-item same/different task as accurate...

متن کامل

Cognitive Robots Learning Failure Contexts Through Experimentation

We propose a lifelong experimental learning method for cognitive robots to build and transfer knowledge among appropriate contexts. Experience gained through learning is used as a guide to future decisions of robots for both efficiency and robustness.

متن کامل

Quantifying the Inductive Bias in Concept Learning (Extended Abstract)

We show that the notion of bias in inductive concept learning can be quantified in a way that directly relates to learning performance, and that this quantitative theory of bias can provide guidance in the design of effective learning algorithms. We apply this idea by measuring some common language biases, including restriction to conjunctive concepts and conjunctive concepts with internal disj...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Current Robotics Reports

سال: 2021

ISSN: ['2662-4087']

DOI: https://doi.org/10.1007/s43154-020-00038-x