Bootstrapping Perception Using Information Theory: Case Studies in a Quadruped Robot Running on Different Grounds

Schmidt, Nico M.; Hoffmann, Matej; Nakajima, Kohei; Pfeifer, Rolf

doi:10.1142/s0219525912500786

Cited by 24 publications

(29 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, in a robot study, Maye and Engel (2011) describe in probabilistic terms the transitions between sensed situations and action outcomes of the closed-loop system, constructing what can be considered slices through a stochastic SM habitat. Similarly, Schmidt et al (2012) have studied the statistical information transfer between the different sensors and motors of a compliant quadruped robot that is controlled by externally induced (open-loop) leg actuations. Their approach reveals that directional correlations between sensors and motors depend on the environment (type of floor surface) and the body structure (hip actuators driving hip angle sensors in the same leg).…”

Section: Discussionmentioning

confidence: 99%

A Dynamical Systems Account of Sensorimotor Contingencies

Bührmann¹,

Paolo²,

Barandiaran³

2013

Front. Psychol.

View full text Add to dashboard Cite

According to the sensorimotor approach, perception is a form of embodied know-how, constituted by lawful regularities in the sensorimotor flow or in sensorimotor contingencies (SMCs) in an active and situated agent. Despite the attention that this approach has attracted, there have been few attempts to define its core concepts formally. In this paper, we examine the idea of SMCs and argue that its use involves notions that need to be distinguished. We introduce four distinct kinds of SMCs, which we define operationally. These are the notions of sensorimotor environment (open-loop motor-induced sensory variations), sensorimotor habitat (closed-loop sensorimotor trajectories), sensorimotor coordination (reliable sensorimotor patterns playing a functional role), and sensorimotor strategy (normative organization of sensorimotor coordinations). We make use of a minimal dynamical model of visually guided categorization to test the explanatory value of the different kinds of SMCs. Finally, we discuss the impact of our definitions on the conceptual development and empirical as well as model-based testing of the claims of the sensorimotor approach.

show abstract

Section: Discussionmentioning

confidence: 99%

A Dynamical Systems Account of Sensorimotor Contingencies

Bührmann¹,

Paolo²,

Barandiaran³

2013

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…Akin to this paper are methods for analyzing emergent behavior (Lungarella and Sporns, 2006; Ay et al, 2008; Wang et al, 2012; Schmidt et al, 2013) using information theory. A new quantification based on excess entropy (predictive information) and attractor dimension was recently proposed in Martius and Olbrich (2015) and applied to similar self-organizing behavior as found in this paper.…”

Section: Robot Behavior As a Self-excited Physical Modementioning

confidence: 99%

Self-Organized Behavior Generation for Musculoskeletal Robots

Der

Martius

2017

Front. Neurorobot.

View full text Add to dashboard Cite

With the accelerated development of robot technologies, control becomes one of the central themes of research. In traditional approaches, the controller, by its internal functionality, finds appropriate actions on the basis of specific objectives for the task at hand. While very successful in many applications, self-organized control schemes seem to be favored in large complex systems with unknown dynamics or which are difficult to model. Reasons are the expected scalability, robustness, and resilience of self-organizing systems. The paper presents a self-learning neurocontroller based on extrinsic differential plasticity introduced recently, applying it to an anthropomorphic musculoskeletal robot arm with attached objects of unknown physical dynamics. The central finding of the paper is the following effect: by the mere feedback through the internal dynamics of the object, the robot is learning to relate each of the objects with a very specific sensorimotor pattern. Specifically, an attached pendulum pilots the arm into a circular motion, a half-filled bottle produces axis oriented shaking behavior, a wheel is getting rotated, and wiping patterns emerge automatically in a table-plus-brush setting. By these object-specific dynamical patterns, the robot may be said to recognize the object's identity, or in other words, it discovers dynamical affordances of objects. Furthermore, when including hand coordinates obtained from a camera, a dedicated hand-eye coordination self-organizes spontaneously. These phenomena are discussed from a specific dynamical system perspective. Central is the dedicated working regime at the border to instability with its potentially infinite reservoir of (limit cycle) attractors “waiting” to be excited. Besides converging toward one of these attractors, variate behavior is also arising from a self-induced attractor morphing driven by the learning rule. We claim that experimental investigations with this anthropomorphic, self-learning robot not only generate interesting and potentially useful behaviors, but may also help to better understand what subjective human muscle feelings are, how they can be rooted in sensorimotor patterns, and how these concepts may feed back on robotics.

show abstract

“…Associated with Francisco Varela, Humberto Maturana, and Evan Thompson among others (see e.g. [27,26,54,51]), the spirit of enactivism is perhaps best summarized in a poem of Anotonio Machado, translated by Varela [53, p. 63]):…”

Section: Plusesmentioning

confidence: 99%

“…Then, MFL, MFR, MHL, MHR correspond to the four motor channels; HFL, HFR, HHL, HHR denote potentiometers in the hip joints, and KFL, KFR, KHL, KHR in the passive knee joints; PFL, PFR, PHL, PHR are feet pressure sensors, AX, AY , AZ linear accelerations in three axes, and GX , GY , GZ are angular velocities. (Figure adapted from [51]. )…”

Section: Specifics Of Cognition In a Quadruped Robotmentioning

confidence: 99%

Contemporary Sensorimotor Theory

Bishop¹,

Martin²

2014

Studies in Applied Philosophy, Epistemology and Rational Ethics

View full text Add to dashboard Cite

Studies in Applied Philosophy, Epistemology and Rational Ethics (SAPERE) publishes new developments and advances in all the fields of philosophy, epistemology, and ethics, bringing them together with a cluster of scientific disciplines and technological outcomes: from computer science to life sciences, from economics, law, and education to engineering, logic, and mathematics, from medicine to physics, human sciences, and politics. It aims at covering all the challenging philosophical and ethical themes of contemporary society, making them appropriately applicable to contemporary theoretical, methodological, and practical problems, impasses, controversies, and conflicts. The series includes monographs, lecture notes, selected contributions from specialized conferences and workshops as well as selected PhD theses. Advisory BoardA.

show abstract

Bootstrapping Perception Using Information Theory: Case Studies in a Quadruped Robot Running on Different Grounds

Cited by 24 publications

References 33 publications

A Dynamical Systems Account of Sensorimotor Contingencies

A Dynamical Systems Account of Sensorimotor Contingencies

Self-Organized Behavior Generation for Musculoskeletal Robots

Contemporary Sensorimotor Theory

Contact Info

Product

Resources

About