Goal emulation and planning in perceptual space using learned affordances

Date

2011-7

Author

Ugur, Emre
Oztop, Erhan
Şahin, Erol

Metadata

Show full item record

Item Usage Stats

164
views

0
downloads

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, affordance predictors for each behavior are obtained by learning the mapping from the object features to the effect categories. After learning, the robot can make plans to achieve desired goals, emulate end states of demonstrated actions, monitor the plan execution and take corrective actions using the perceptual structures employed or discovered during learning. We argue that the learning system proposed shares crucial elements with the development of infants of 7-10 months age, who explore the environment and learn the dynamics of the objects through goal-free exploration. In addition, we discuss goal emulation and planning in relation to older infants with no symbolic inference capability and non-linguistic animals which utilize object affordances to make action plans.

Subject Keywords

Affordance, Developmental robotics, Sensorimotor learning, Manipulation, Perception, Cognitive robotics

URI

https://hdl.handle.net/11511/28282

Journal

Robotics and Autonomous Systems

DOI

https://doi.org/10.1016/j.robot.2011.04.005

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

From primitive behaviors to goal-directed behavior using affordances Doǧar, Mehmet R.; Çakmak, Maya; Uǧur, Emre; Şahin, Erol (2007-12-01) In this paper, we studied how a mobile robot equipped with a 3D laser scanner can start from primitive behaviors and learn to use them to achieve goal-directed behaviors. For this purpose, we propose a learning scheme that is based on the concept of "affordances", where the robot first learns about the different kind of effects it can create in the environment and then links these effects with the perception of the initial environment and the executed primitive behavior. It uses these learned relations to c...
GESwarm Grammatical Evolution for the Automatic Synthesis of Collective Behaviors in Swarm Robotics Ferrante, Eliseo; Turgut, Ali Emre; DuenezGuzman, Edgar; Wenseleers, Tom (2013-07-10) In this paper we propose GESwarm, a novel tool that can automatically synthesize collective behaviors for swarms of autonomous robots through evolutionary robotics. Evolutionary robotics typically relies on artificial evolution for tuning the weights of an artificial neural network that is then used as individual behavior representation. The main caveat of neural networks is that they are very difficult to reverse engineer, meaning that once a suitable solution is found, it is very difficult to analyze, to ...
A developmental framework for learning affordances Uğur, Emre; Şahin, Erol; Öztop, Erhan; Department of Computer Engineering (2010) We propose a developmental framework that enables the robot to learn affordances through interaction with the environment in an unsupervised way and to use these affordances at different levels of robot control, ranging from reactive response to planning. Inspired from Developmental Psychology, the robot’s discovery of action possibilities is realized in two sequential phases. In the first phase, the robot that initially possesses a limited number of basic actions and reflexes discovers new behavior primiti...
Staged Development of Robot Skills: Behavior Formation, Affordance Learning and Imitation with Motionese Ugur, Emre; Nagai, Yukie; Şahin, Erol; ÖZTOP, ERHAN (2015-06-01) Inspired by infant development, we propose a three staged developmental framework for an anthropomorphic robot manipulator. In the first stage, the robot is initialized with a basic reach-and-enclose-on-contact movement capability, and discovers a set of behavior primitives by exploring its movement parameter space. In the next stage, the robot exercises the discovered behaviors on different objects, and learns the caused effects; effectively building a library of affordances and associated predictors. Fina...
Decoupled Cascaded PID Control of an Aerial Manipulation System Bulut, Nebi; Turgut, Ali Emre; Arıkan, Kutluk Bilge (2019-12-01) This paper presents the control of an aerial manipulation system with a quadrotor and a 2-DOF robotic arm. Firstly, the kinematic model of the combined system and the Denavit-Hartenberg parameters of the serial robotic arm are obtained. Then, to derive the dynamics of the system, the quadrotor and the 2-DOF robotic arm are modeled as a combined system. The Lagrange-d'Alembert formulation is used to obtain the equation of motion of the combined system. Later, decoupled controllers are developed for the gener...

Citation Formats

E. Ugur, E. Oztop, and E. Şahin, “Goal emulation and planning in perceptual space using learned affordances,” Robotics and Autonomous Systems, pp. 580–595, 2011, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/28282.