Enactive Robot Vision | EPFL Graph Search

Enactivism claims that sensory-motor activity and embodiment are crucial in perceiving the environment and that machine vision could be a much simpler business if considered in this context. However, computational models of enactive vision are very rare and often rely on handcrafted control systems. In this paper, we describe results from experiments where evolutionary robots can choose whether to exploit sensory motor coordination in a set of vision- based tasks. We show that complex visual tasks can be tackled with remarkably simple neural architectures generated by a co-evolutionary process of active vision and feature selection. We describe the application of this methodology in four sets of experiments, namely shape discrimination, car driving, and wheeled/bipedal robot navigation. A further set of experiments where the visual system can develop the receptive fields by means of unsupervised Hebbian learning, demonstrates that the receptive fields are significantly affected by the behavior of the system and differ from those predicted by most computational models of visual cortex. Finally, we show that our robots can also replicate the performance deficiencies observed in experiments of sensory deprivation with kitten.

Enactive robot vision

Mototaka Suzuki

The complexity of today's autonomous robots poses a major challenge for Artificial Intelligence. These robots are equipped with sophisticated sensors and mechanical abilities that allow them to enter our homes and interact with humans. For example, today's robots are almost all equipped with vision and several of them can move over rough terrain with wheels or legs. The methods developed so far in Artificial Intelligence, however, are not yet ready to cope with the complexity of the information gathered through the robot sensors and the need for rapid action in partially unknown and dynamic environments. In this thesis, I will argue that the apparent complexity of the environment and of the robot brain can be significantly simplified if perception, behavior, and learning are allowed to co-develop on the same time scale. In doing so, robots become sensitive to, and actively exploit, characteristics of the environment that they can tackle within their own computational and physical constraints. This line of work is grounded on philosophical and psychological research showing that perception is an active process mediated by behavior. However, computational models of active vision are very rare and often rely on architectures that are preprogrammed to detect certain characteristics of the environment. Previous work have shown that complex visual tasks, such as position and size invariant shape recognition as well as navigation, can be tackled with remarkably simple neural architectures generated by a coevolutionary process of active vision and feature selection. Behavioral machines equipped with primitive vision systems and direct pathways between visual and motor neurons were evolved while freely interacting with their environments. I proceed further on this line of investigation and describe the application of this methodology in three situations, namely car driving with an omnidirectional camera, goal-oriented navigation of a humanoid robot, and cooperative tasks by two agents. I will show that these systems develop sensitivity to a number of oriented, retinotopic, visual features – oriented edges, corners, height – and a behavioral repertoire to locate, bring, and keep these features in sensitive regions of the vision system that allow them to accomplish their goals. In a second set of experiments, I will show that active vision can be exploited by the robot to perform anticipatory exploration of the environment in a task that requires landmark-based navigation. Evolved robots exploit an internal expectation system that makes use of active exploration to check for expected events in the environment. I will describe a third set of experiments where, in addition to an evolutionary process, the visual system of the robot can develop receptive fields by means of unsupervised Hebbian learning and show that these receptive fields are significantly affected by the behavior of the system and differ from those predicted by most computational models of visual cortex. Finally, I will show that these robots replicate the performance deficiencies observed in experiments of motor deprivation with kitten when they are exposed to the same type of motor deprivations. Furthermore, the analyses of our robot brains suggest an explanation for the deficiencies observed in kitten that have not yet been fully understood.

EPFL2007

Constraints on Body Movement during Visual Development Affect Behavior of Evolutionary Robots

Dario Floreano, Mototaka Suzuki

We explore the role of active body movement in the developmental process of the visual system. Receptive fields of an evolved mobile robot are developed during active or passive movement with the generalized Hebbian algorithm (Sanger, 1989). In accordance to experimental observations of kitten, we show that the receptive fields and behavior of the robot developed under active condition significantly differ from those developed under passive condition. A possible explanation of this difference is derived by correlating receptive field formation and behavioral performance in the two conditions.

2005

The Contribution of Active Body Movement to Visual Development in Evolutionary Robots

Dario Floreano, Mototaka Suzuki

Inspired by the pioneering work by Held and Hein (1963) on the development of kitten visuo-motor systems, we explore the role of active body movement in the developmental process of the visual system by using robots. The receptive fields in an evolved mobile robot are developed during active or passive movement with a Hebbian learning rule. In accordance to experimental observations in kittens, we show that the receptive fields and behavior of the robot developed under active condition significantly differ from those developed under passive condition. A possible explanation of this difference is derived by correlating receptive field formation and behavioral performance in the two conditions.

2005

Enactive robot vision

Mototaka Suzuki

EPFL2007