• Corpus ID: 5723058

View-based cognitive map learning by an autonomous robot

  title={View-based cognitive map learning by an autonomous robot},
  author={Hanspeter A. Mallot and Heinrich H. B{\"u}lthoff and Philip Georg and Bernhard Sch{\"o}lkopf and Kenji Yasuhara and Françoise Fogelman-Souli{\'e}},
This paper presents a view based approach to map learning and nav igation in mazes By means of graph theory we have shown that the view graph is a su cient representation for map behaviour such as path planning A neural network for unsupervised learning of the view graph from sequences of views is constructed We use a modi ed Kohonen learning rule that transforms temporal sequence rather than fea tural similarity into connectedness In the main part of the paper we present a robot implementation… 
Recognition-Triggered Response and the View-Graph Approach to Spatial Cognition
Psychophysical evidence from experiments using virtual reality indicating that human subjects do make use of simple view-movement associations without recognizing places is presented, indicating that the view-graph is less computationally expensive and can easily be adapted to the coarseness of spatial knowledge.
A Distributed Cognitive Map for Spatial Navigation Based on Graphically Organized Place Agents
A novel system for mobile robotic navigation that like its biological counterpart decomposes explored space into a distributed graphical network of behaviorally significant places, each represented by an independent “place agent” (PA) that actively maintains the spatial and behavioral knowledge relevant for navigation in that place.
Learning view graphs for robot navigation
A purely vision-based scheme for learning a topological representation of an open environment, which represents selected places by local views of the surrounding scene, and finds traversable paths between them using a graph model of the environment.
Learning View Graphs for Robot Navigation
A purely vision-based scheme for learning a topological representation of an open environment that represents selected places by local views of the surrounding scene, and finds traversable paths between them, and can be performed without using metric information.
A connectionist model for localization and route learning based on remembrance of perception and action
This paper proposes a connectionist model to learn a spatial representation of the world based on temporal memory of perceptions and actions of the robot. It is constructed at run-time to merge the
Segmentation of Environment and Formation of Graph-based Maps in Mobile Robots
A new approach in Artificial Intelligence (AI), which focuses on agent’s interaction with the world, is expected to solve difficulties in the classical AI. The interaction leads an agent to exhibit
Segmentation of Environment and Formation of Graph-based Maps in Mobile Robots
A new approach to segmentation in a mobile robot by a modular network SOM (mnSOM) is proposed, and Hidden Markov models (HMMs) are used instead of a deterministic method to form a graph-based map for efficient processing.
Neural Network Architecture for Cognitive Navigation in Dynamic Environments
The proposed architecture provides the robot with cognitive abilities and enables reliable and flexible navigation in realistic time-evolving environments and it is proved that the subconscious pathway is robust against uncertainty in the sensory information.
The View-Graph Approach to Visual Navigation and Spatial Memory
It is argued that the graph of local views (snapshots) is a general and biologically plausible means of representing space and integrating the various mechanisms of map behaviour.
Context-Based Cognitive Map Learning for an Autonomous Robot Using a Model of Cortico-Hippocampal Interplay
This paper presents an additional module of cortico-hippocampal interplay to the view-based competitive sequence learning scheme of spatial memory by use of a middle-term memory module as a model of hippocampal function.


View-Based Cognitive Mapping and Path Planning
A neural network is presented that learns the view graph during a random exploration of the maze using an unsupervised competitive learning rule translating temporal sequence of views into connectedness in the network, improving the view-recognition performance.
A Robust, Qualitative Approach To A Spatial Learning Mobile Robot
This work uses a qualitative method which can be robust in the face of various possible errors in the real world, and uses a multi-layered map which consists of procedural knowledge for movement, topological model for the structure of the environment, and metrical information for geometrical accuracy.
Self-Organization and Associative Memory
The purpose and nature of Biological Memory, as well as some of the aspects of Memory Aspects, are explained.
Vehicles, Experiments in Synthetic Psychology
These imaginative thought experiments are the inventions of one of the world's eminent brain researchers. They are "vehicles," a series of hypothetical, self-operating machines that exhibit
Mobile Robot Miniaturisation: A Tool for Investigation in Control Algorithms
This invention relates to chess-type board games with movable playing pieces wherein the playing pieces are moved in accordance with selected patterns by one player in order to capture playing pieces of another player.
A robust, qualitative a p p r o a c h to a spatial learning mobile robot
  • SPIE Vol. 1003 Sensor Fusion: Spatial Reasoning and Scene Interpretation. I n ternational Society for Optical Engineering (SPIE)
  • 1988
Experiments in Synthetic Psychology
  • 1984
Active n a vigation with a monocular robot
  • Biological Cybernetics