skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: S-Learning: A Biomimetic Algorithm for Learning Memory and Control in Robots.


Abstract not provided.

Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
Report Number(s):
DOE Contract Number:
Resource Type:
Resource Relation:
Conference: Proposed for presentation at the 3rd International IEEE EMBS Conference on Neural Engineering held May 2-5, 2007 in Kohala Coast, HI.
Country of Publication:
United States

Citation Formats

Rohrer, Brandon R. S-Learning: A Biomimetic Algorithm for Learning Memory and Control in Robots.. United States: N. p., 2007. Web. doi:10.1109/CNE.2007.369634.
Rohrer, Brandon R. S-Learning: A Biomimetic Algorithm for Learning Memory and Control in Robots.. United States. doi:10.1109/CNE.2007.369634.
Rohrer, Brandon R. Thu . "S-Learning: A Biomimetic Algorithm for Learning Memory and Control in Robots.". United States. doi:10.1109/CNE.2007.369634.
title = {S-Learning: A Biomimetic Algorithm for Learning Memory and Control in Robots.},
author = {Rohrer, Brandon R.},
abstractNote = {Abstract not provided.},
doi = {10.1109/CNE.2007.369634},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Thu Mar 01 00:00:00 EST 2007},
month = {Thu Mar 01 00:00:00 EST 2007}

Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • The authors present a scalable parallel Strassen`s matrix multiply algorithm for distributed memory, message passing computers. Strassen`s algorithm to multiply two N x N matrices reduces the asymptotic operation count from O(N{sup 3}) of the traditional algorithm to O(N{sup 2.81}). In a sequential implementation the Strassen`s algorithm offers better performance even for relatively low order matrices. However, due to its complexity, the parallel Strassen`s algorithm is less than straight forward. Here a scalable parallel Strassen`s algorithm is presented and compared with several other parallel algorithms. Performances of these algorithms are tested on a 128-processor Intel iPSC/860.
  • We address the problem of learning robust plans for robot navigation by observing particular robot behaviors. In this Paper we present a method which can learn a robust reactive example of a desired behavior. The translating a sequence of events arising system into a plan which represents among such events. This method allows us to rely or the underlying stability properties of low-level behavior processes in order to produce robust plans. Since the resultant plan reproduces the original behavior of the robot at a high level, it generalizes over small environmental changes and is robust to sensor and effector noise.
  • The main paradigm in sub-symbolic learning robot domain is the reinforcement learning method. Various techniques have been developed to deal with the memorization/generalization problem, demonstrating the superior ability of artificial neural network implementations. In this paper, the authors address the issue of designing the reinforcement so as to optimize the exploration part of the learning. They also present and summarize works relative to the use of bias intended to achieve the effective synthesis of the desired behavior. Demonstrative experiments involving a self-organizing map implementation of the Q-learning and real mobile robots (Nomad 200 and Khepera) in a task of obstaclemore » avoidance behavior synthesis are described. 3 figs., 5 tabs.« less
  • Most fuzzy logic-based reasoning schemes developed for robot control are fully reactive, i.e., the reasoning modules consist of fuzzy rule bases that represent direct mappings from the stimuli provided by the perception systems to the responses implemented by the motion controllers. Due to their totally reactive nature, such reasoning systems can encounter problems such as infinite loops and limit cycles. In this paper, we proposed an approach to remedy these problems by adding a memory and memory-related behaviors to basic reactive systems. Three major types of memory behaviors are addressed: memory creation, memory management, and memory utilization. These are firstmore » presented, and examples of their implementation for the recognition of limit cycles during the navigation of an autonomous robot in a priori unknown environments are then discussed.« less
  • This paper presents a domain decomposition method for optimal control problems and the massively parallel implementation of the resulting algorithm.