Learning agent's spatial configuration from sensorimotor invariants

Abstract

The design of robotic systems is largely dictated by our purely human intuition about how we perceive the world. This intuition has been proven incorrect with regard to a number of critical issues, such as visual change blindness. In order to develop truly autonomous robots, we must step away from this intuition and let robotic agents develop their own way of perceiving. The robot should start from scratch and gradually develop perceptual notions, under no prior assumptions, exclusively by looking into its sensorimotor experience and identifying repetitive patterns and invariants. One of the most fundamental perceptual notions, space, cannot be an exception to this requirement. In this paper we look into the prerequisites for the emergence of simplified spatial notions on the basis of a robot's sensorimotor flow. We show that the notion of space as environment-independent cannot be deduced solely from exteroceptive information, which is highly variable and is mainly determined by the contents of the environment. The environment-independent definition of space can be approached by looking into the functions that link the motor commands to changes in exteroceptive inputs. In a sufficiently rich environment, the kernels of these functions correspond uniquely to the spatial configuration of the agent's exteroceptors. We simulate a redundant robotic arm with a retina installed at its end-point and show how this agent can learn the configuration space of its retina. The resulting manifold has the topology of the Cartesian product of a plane and a circle, and corresponds to the planar position and orientation of the retina.

26 pages, 5 images, published in Robotics and Autonomous Systems

References in corpus (5)

• Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots
• Fast Damage Recovery in Robotics with the T-Resilience Algorithm
• Body Schema Acquisition through Active Learning
• Space as an invention of biological organisms
• Where do goals come from? A Generic Approach to Autonomous Goal-System Development

Cited by in corpus (6)

• Grounding the Experience of a Visual Field through Sensorimotor Contingencies
• Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction
• Body models in humans, animals, and robots: mechanisms and plasticity
• Grounding object perception in a naive agent's sensorimotor experience
• On the Sensory Commutativity of Action Sequences for Embodied Agents
• Emergence of Spatial Coordinates via Exploration