Generative character of perception: a neural architecture for sensorimotor anticipation

Groß, Horst–Michael; Heinze, A.; Seiler, T.; Völker, Stephan

doi:10.1016/s0893-6080(99)00047-7

Cited by 49 publications

(40 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other words, even perception might be based on the same system. Therefore, I propose that an MMC-like structure may represent the basis for a perceptual system, too (for a stimulating discussion of a tight connection between perception and the motor system see also Gross, Heinze, Seiler, & Stephan, 1999). This agrees with the observation of the already mentioned "mirror neurons."…”

Section: Planningsupporting

confidence: 82%

The evolution of cognition—a hypothesis

Cruse¹

2003

Cognitive Science

View full text Add to dashboard Cite

Behavior may be controlled by reactive systems. In a reactive system the motor output is exclusively driven by actual sensory input. An alternative solution to control behavior is given by "cognitive" systems capable of planning ahead. To this end the system has to be equipped with some kind of internal world model. A sensible basis of an internal world model might be a model of the system's own body. I show that a reactive system with the ability to control a body of complex geometry requires only a slight reorganization to form a cognitive system. This implies that the assumption that the evolution of cognitive properties requires the introduction of new, additional modules, namely internal world models, is not justified. Rather, these modules may already have existed before the system obtained cognitive properties. Furthermore, I discuss whether the occurrence of such world models may lead to systems having internal perspective.

show abstract

Section: Planningsupporting

confidence: 82%

The evolution of cognition—a hypothesis

Cruse¹

2003

Cognitive Science

View full text Add to dashboard Cite

show abstract

“…Different from other robotic studies on sensorimotor anticipation, which were limited to navigational tasks (Tani, 1996;Tani and Nolfi, 1999;Gross et al, 1999;Ziemke et al, 2005), in the present study, a spatial arrangement is understood by a passive observer. A dead end could be recognized by a robot that stands still.…”

Section: Introductionmentioning

confidence: 88%

“…Actions like crawling, walking, turning, poking, and grasping cause specific changes in the sensory signals of the actor, and these causal relationships can be learned. Several authors suggested that these learned relationships are the basis of certain perceptual qualities, like understanding the spatial arrangement of obstacles, the function of tools, and the material properties of objects (Möller, 1996(Möller, , 1999Gross et al, 1999;O'Regan and Noë, 2001;Grush, 2004;Hoffmann and Möller, 2004).…”

Section: Introductionmentioning

confidence: 99%

“…Thus, overt motor commands can be replaced by covert ones (Hesslow, 2002). Such a sensorimotor anticipation was successfully applied to reinforcement learning (Sutton, 1992;Schaal, 1997) and to mobile-robot navigation (Tani, 1996;Tani and Nolfi, 1999;Gross et al, 1999;Ziemke et al, 2005).…”

Section: Introductionmentioning

confidence: 99%

“…Thus, the sensorimotor simulation must start from a single image. Analyzing only a single image prohibits the use of flow fields as in Gross et al (1999) and the use of Elman recurrent neural networks for prediction (Tani, 1996;Tani and Nolfi, 1999;Ziemke et al, 2005). Instead, here, given only the current image, a forward model predicts the next image.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Perception through visuomotor anticipation in a mobile robot

Hoffmann

2007

Neural Networks

View full text Add to dashboard Cite

Several scientists suggested that certain perceptual qualities are based on sensorimotor anticipation: for example, the softness of a sponge is perceived by anticipating the sensations resulting from a grasping movement. For the perception of spatial arrangements, this article demonstrates that this concept can be realized in a mobile robot. The robot first learned to predict how its visual input changes under movement commands. With this ability, two perceptual tasks could be solved: judging the distance to an obstacle in front by 'mentally' simulating a movement toward the obstacle, and recognizing a dead end by simulating either an obstacle-avoidance algorithm or a recursive search for an exit. A simulated movement contained a series of prediction steps. In each step, a multi-layer perceptron anticipated the next image, which, however, became increasingly noisy. To denoise an image, it was split into patches, and each patch was projected onto a manifold obtained by modeling the density of the distribution of training patches with a mixture of Gaussian functions.

show abstract

Neural Architecture for Mental Imaging of Sequences Based on Optical Flow Predictions

Völker

Groß

2001

Artificial Neural Networks — ICANN 2001

View full text Add to dashboard Cite

Generative character of perception: a neural architecture for sensorimotor anticipation

Cited by 49 publications

References 43 publications

The evolution of cognition—a hypothesis

The evolution of cognition—a hypothesis

Perception through visuomotor anticipation in a mobile robot

Neural Architecture for Mental Imaging of Sequences Based on Optical Flow Predictions

Contact Info

Product

Resources

About