Active Categorical Perception of Object Shapes in a Simulated Anthropomorphic Robotic Arm

Abstract

Active perception refers to a theoretical approach to the study of perception grounded on the idea that perceiving is a way of acting, rather than a process whereby the brain constructs an internal representation of the world. The operational principles of active perception can be effectively tested by building robot-based models in which the relationship between perceptual categories and the body-environment interactions can be experimentally manipulated. In this paper, we study the mechanisms of tactile perception in a task in which a neuro-controlled anthropomorphic robotic arm, equipped with coarse-grained tactile sensors, is required to perceptually categorize spherical and ellipsoid objects. We show that best individuals, synthesized by artificial evolution techniques, develop a close to optimal ability to discriminate the shape of the objects as well as an ability to generalize their skill in new circumstances. The results show that the agents solve the categorization task in an effective and robust way by self-selecting the required information through action and by integrating experienced sensory-motor states over time.Non peer reviewe

The Facilitatory Role of Linguistic Instructions on Developing Manipulation Skills

“…For each condition, the evolutionary process has been have been simulated by using Newton Game Dynamics (NGD, see: www.newtondynamics.com), a library for accurately simulating rigid body dynamics and collisions. For related approaches, see [23], [22], [24].…”

“…This in turn allows the robot to exploit sensory-motor coordination (i.e., the possibility to act in order to later experience useful sensory states) as well as the properties arising from the physical interactions between the robot and the environment. In [22] it is shown how this approach allows the robot to distinguish objects of different shapes by self-selecting useful stimuli through action, and in [23] it is shown how this approach allows for the exploiting of properties arising from the physical interaction between the robot body and the environment for the purpose of manipulating the object.…”

Haptic SLAM for context-aware robotic hand prosthetics - simultaneous inference of hand pose and object shape using particle filters

“…Several studies have focused on the use of machine learning approaches such as neural networks [8], [9] and Bayesian techniques [10], [11], [12] to identify objects in haptic space. Studies involving tactile exploration by robotic systems are, however, intrinsically limited by the physical design considerations of the device.…”

An Embodied Approach for Evolving Robust Visual Classifiers

“…which category the perceived object belongs to. In the embodied approach, the robot or organism must interact with its environment to generate useful percepts for categorization [1,3,22].…”

“…Beer [1] reported an agent that achieves ACP simply by moving relative to objects in its environment without touching them, while Tuci [22] and Bongard [3] reported robots that achieved ACP by physically manipulating objects. Furthermore, Bongard [3] demonstrated that evolving robot morphology along with control facilitated the evolution of ACP, presumably because evolution could more readily discover grasping strategies that reduced intra-category differences and exaggerated inter-category differences.…”