Affordance learning from range data for multi-step planning
نویسندگان
چکیده
In this paper we present the realization of the formalism we have proposed for affordance learning and its use for planning (Şahin et al., 2007) on an anthropomorphic robotic hand. In this realization, the robot interacts with the objects in its environment using the programmed push and grasp-andlift behaviors, and records its interactions in triples that consists of the initial percept of the object, the behavior applied and the observed effect, defined as the difference between the initial and the final percept. The interaction with the environment allows the robot to learn object affordance relations to predict the change in the percept of the object when a certain behavior is applied. These relations can then be used to develop multi-step plans using forward chaining. Our experiments have shown that the robot is able to learn the physical affordances of objects from 3D range images and use them to build symbols and relations that are used for making multi-step plans to achieve a given goal.
منابع مشابه
Learning Social Affordances and Using Them for Planning
This study extends the learning and use of affordances on robots on two fronts. First, we use the very same affordance learning framework that was used for learning the affordances of inanimate things to learn social affordances, that is affordances whose existence requires the presence of humans. Second, we use the learned affordances for making multi-step plans. Specifically, an iCub humanoid...
متن کاملGoal emulation and planning in perceptual space using learned affordances
In this paper, we show that through self-interaction and self-observation, an anthropomorphic robot equipped with a range camera can learn object affordances and use this knowledge for planning. In the first step of learning, the robot discovers commonalities in its action-effect experiences by discovering effect categories. Once the effect categories are discovered, in the second step, afforda...
متن کاملMMDT: Multi-Objective Memetic Rule Learning from Decision Tree
In this article, a Multi-Objective Memetic Algorithm (MA) for rule learning is proposed. Prediction accuracy and interpretation are two measures that conflict with each other. In this approach, we consider accuracy and interpretation of rules sets. Additionally, individual classifiers face other problems such as huge sizes, high dimensionality and imbalance classes’ distribution data sets. This...
متن کاملLearning 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 کاملIranian EFL Learners’ Perception of the Efficacy and Affordance of Activity Theory-based Computer Assisted Language Learning in Writing Achievement
Second language writing instruction has been greatly influenced by the growing importance of technology and the recent shift of paradigm from a cognitive to a social orientation in second language acquisition (Lantolf & Thorne, 2006). Therefore, the applications of computer assisted language learning and activity theory have been suggested as a promising framework for writing studies. The prese...
متن کامل