On the Dynamics of Robot Exploration Learning

Tani, Jun; Sugita, Yuya

doi:10.1007/3-540-48304-7_36

Cited by 3 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiment examined in the current system treat only one experience and did not test more general cases in which many memory segments could be generated and cause the problem of memory consolidation. The recurrent neural network model may have the superiority to consolidate the sequential data [9]. As the next stage, we would try the more improved memory model so as to cope with the more general situations.…”

Section: Resultsmentioning

confidence: 99%

Acquiring peekaboo communication: Early communication model based on reward prediction

Ogino

Ooide

Watanabe

et al. 2007

2007 IEEE 6th International Conference on Development and Learning

View full text Add to dashboard Cite

Infants become sensitive to the regular behavior of their caregivers by the end of 4 months old. In this paper, we propose a communication system for a robot to acquire early communication. The acquisition of the communication is proceeded by the interactions of the three components; the memory module, the reward prediction module and the internal state module. The emotional change triggers the transfer of the sensor data stored in the short-term memory to the long-term memory. Once the memory segments are formed, the sensor data are compared with them. When the coincidence of the starting signal of stored data with the sensor data is detected, the prediction of the reward begins. The responses of the simulated robot with the proposed system are examined with and without the memory module when the caregiver takes the regular and irregular peekaboo communication. The results partly explain the behaviors observed in infants.

show abstract

Section: Resultsmentioning

confidence: 99%

Acquiring peekaboo communication: Early communication model based on reward prediction

Ogino

Ooide

Watanabe

et al. 2007

2007 IEEE 6th International Conference on Development and Learning

View full text Add to dashboard Cite

show abstract

“…In the review of experiments on goal-directed planning in robot navigation tasks, it was explained that robots can learn compositional structures latent in the obstacle environment through either supervised tutoring (Tani, 1996) or self-exploration (Tani & Yamamoto, 2002). Further, it was noted that such compositional structures develop by self-organizing global attractors of Cantor set-like assembly in the latent state phase space.…”

Section: Discussionmentioning

confidence: 99%

“…Human infants or artificial agents may explore the world by seeking some intrinsic rewards such as novelty in interacting with their environments (Oudeyer et al, 2007;Schmidhuber, 1991;Tschantz et al, 2020). Tani and Yamamoto (2002) extended the study in Tani (1996) to investigate the issue of intrinsic motivation by adding a novelty rewarding mechanism as a drive for seeking novel experiences during exploration. The exploration and the learning phases of this experiment were interleaved, with each happening after the other.…”

Section: Goal-directed Planningmentioning

confidence: 99%

“…Furthermore, some robots (or more generally agents; R. Kaplan & Friston, 2018;Oudeyer et al, 2007;Schmidhuber, 1991;Tani & Yamamoto, 2002) are motivated to learn to predict unpredictable situations by seeking novelty, with the objective of which also seeming rather contradictory or conflictive at first glance. And, to reconcile such conflicts, agents seem to be required to generate creative or fictive mental images accounting for the hidden causal structure in the world.…”

Section: Narrative Selfmentioning

confidence: 99%

See 1 more Smart Citation

Cognitive neurorobotics and self in the shared world, a focused review of ongoing research

Tani

White

2020

Adaptive Behavior

Self Cite

View full text Add to dashboard Cite

Through brain-inspired modeling studies, cognitive neurorobotics aims to resolve dynamics essential to different emergent phenomena at the level of embodied agency in an object environment shared with human beings. This article is a review of ongoing research focusing on model dynamics associated with human self-consciousness. It introduces the free energy principle and active inference in terms of Bayesian theory and predictive coding, and then discusses how directed inquiry employing analogous models may bring us closer to representing the sense of self in cognitive neurorobots. The first section quickly locates cognitive neurorobotics in the broad field of computational cognitive modeling. The second section introduces principles according to which cognition may be formalized, and reviews cognitive neurorobotics experiments employing such formalizations. The third section interprets the results of these and other experiments in the context of different senses of self, both “minimal” and “narrative” self. The fourth section considers model validity and discusses what we may expect ongoing cognitive neurorobotics studies to contribute to scientific explanation of cognitive phenomena including the senses of minimal and narrative self.

show abstract

Representing Robot-Environment Interactions by Dynamical Features of Neuro-controllers

Hülse

Zahedi

Pasemann

2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This article presents a method, which enables an autonomous mobile robot to create an internal representation of the external world. The elements of this internal representation are the dynamical features of a neuro-controller and their time regime during the interaction of the robot with its environment. As an examples of this method the behavior of a Khepera robot is studied, which is controlled by a recurrent neural network. This controller has been evolved to solve an obstacle avoidance task. Analytical investigations show that this recurrent controller has four behavior relevant attractors, which can be directly related to the following environmental categories: free space, obstacle left/right, and deadlock situation. Temporal sequences of those attractors, which occur during a run of the robot are used to characterize the robot-environment interaction. To represent the temporal sequences a technique, called macro-action maps, is applied. Experiments indicate that macro-action maps allow to built up more complex environmental categories and enable an autonomous mobile robot to solve navigation tasks.

show abstract

On the Dynamics of Robot Exploration Learning

Cited by 3 publications

References 4 publications

Acquiring peekaboo communication: Early communication model based on reward prediction

Acquiring peekaboo communication: Early communication model based on reward prediction

Cognitive neurorobotics and self in the shared world, a focused review of ongoing research

Representing Robot-Environment Interactions by Dynamical Features of Neuro-controllers

Contact Info

Product

Resources

About