A Deep Incremental Boltzmann Machine for Modeling Context in Robots

Context is an essential capability for robots that are to be as adaptive as possible in challenging environments. Although there are many context modeling efforts, they assume a fixed structure and number of contexts. In this paper, we propose an incremental deep model that extends Restricted Boltzmann Machines. Our model gets one scene at a time, and gradually extends the contextual model when necessary, either by adding a new context or a new context layer to form a hierarchy. We show on a scene classification benchmark that our method converges to a good estimate of the contexts of the scenes, and performs better or on-par on several tasks compared to other incremental models or non-incremental models.

• Publication year

  2017

• Venue

  IEEE International Conference on Robotics and Automation

• Publication date

  2017-10-13

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/ICRA.2018.8462925arXiv 1710.04975
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

  2016influential reference
• Description logics of context

  2016cited by this paper
• An incremental learning approach for restricted boltzmann machines

  2015influential reference
• SUN RGB-D: A RGB-D scene understanding benchmark suite

  2015cited by this paper
• Incremental training of Restricted Boltzmann Machines using information driven saccades

  2014cited by this paper
• Learning and using context on a humanoid robot using latent dirichlet allocation

  2014cited by this paper
• Contextually guided semantic labeling and search for three-dimensional point clouds

  2013cited by this paper
• Nested Hierarchical Dirichlet Processes

  2012cited by this paper
• Learning to place new objects in a scene

  2012cited by this paper
• Contextually Guided Semantic Labeling and Search for 3D Point Clouds

  2011cited by this paper
• Deep Boltzmann Machines

  2009cited by this paper
• Actions in context

  2009cited by this paper
• Online Inference of Topics with Latent Dirichlet Allocation

  2009cited by this paper
• Simulation, situated conceptualization, and prediction

  2009cited by this paper
• Restricted Boltzmann machines for collaborative filtering

  2007cited by this paper
• Hierarchical Dirichlet Processes

  2006cited by this paper
• The situated nature of concepts.

  2006cited by this paper
• Finding scientific topics

  2004cited by this paper
• Context-based vision system for place and object recognition

  2003cited by this paper
• Contextual Priming for Object Detection

  2003cited by this paper
• Propositional Logic of Context

  1993cited by this paper
• Notes on Formalizing Context

  1993influential reference
• Using latent semantic analysis to improve access to textual information

  1988cited by this paper
• Information processing in dynamical systems: foundations of harmony theory

  1986cited by this paper
• A Learning Algorithm for Boltzmann Machines

  1985cited by this paper

• STREAK: Streaming Network for Continual Learning of Object Relocations under Household Context Drifts

  2024cites this paper
• Open Challenges on Generating Referring Expressions for Human-Robot Interaction

  2021cites this paper
• Continual Learning for Affective Robotics: Why, What and How?

  2020cites this paper
• A review of algorithms and techniques for image-based recognition and inference in mobile robotic systems

  2020cites this paper
• Mind Your Manners! A Dataset and a Continual Learning Approach for Assessing Social Appropriateness of Robot Actions

  2020cites this paper
• CINet: A Learning Based Approach to Incremental Context Modeling in Robots

  2018influential citation
• COSMO: Contextualized Scene Modeling with Boltzmann Machines

  2018cites this paper
• Neurorobotics—A Thriving Community and a Promising Pathway Toward Intelligent Cognitive Robots

  2018cites this paper
• Learning to Increment a Contextual Model

  2018cites this paper
• A Learning Based Approach to Incremental Context Modeling in Robots

  2017cites this paper
• forActivity Prediction in

  year unknowncites this paper