Bootstrapping Relational Affordances of Object Pairs Using Transfer

نویسندگان
چکیده

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

Using a SOFM to learn Object Affordances

Learning affordances can be defined as learning action potentials, i.e., learning that an object exhibiting certain regularities offers the possibility of performing a particular action. We propose a method to endow an agent with the capability of acquiring this knowledge by relating the object invariants with the potentiality of performing an action via interaction episodes with each object. W...

متن کامل

On Object Affordances

In the context of robot learning from demonstration, it is very important that a robot understands what an object can be used for. By observing a human performing an activity, a robot should be able to identify the human motion, the objects involved and the outcome of the performed activity. One important aspect of this challenging problem is to detect and reason about objects in terms of affor...

متن کامل

Learning Object Affordances for Planning

We use the notion of affordances as a framework to propose a developmental method that enables a robot to ground symbolic planning mechanisms in its continuous sensorimotor experiences. The method allows the robot to learn object affordance relations which can be used to predict the change in the percept of the object when a certain behavior is applied. Our robot experiments has shown that a ro...

متن کامل

Are Object Affordances Fully Automatic?

Inspired in part by Gibson’s (1979) ecological approach to perception, current neurocognitive theories of action suggest that the simple viewing of an object can automatically elicit motor programs for specific acts. However, the degree to which such affordances should be considered truly automatic is unknown. Here we explored the generation of motor plans afforded by pairs of cue objects that ...

متن کامل

Motor Affordances in Object Perception

Recently, researchers have suggested that when we see an object we automatically represent how that object affords action (Tucker & Ellis, 2001). However, the precise nature of this representation remains unclear: is it a specific motor plan or a more abstract response code? Furthermore, do action representations actually influence what we perceive? In Experiment 1, participants responded to an...

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: IEEE Transactions on Cognitive and Developmental Systems

سال: 2018

ISSN: 2379-8920,2379-8939

DOI: 10.1109/tcds.2016.2616496