• Publications
  • Influence
Automated Derivation of Primitives for Movement Classification
A method for automatically deriving a set of primitives directly from human movement data, using movement data gathered from a psychophysical experiment on human imitation to derive the primitives.
A spatio-temporal extension to Isomap nonlinear dimension reduction
ST-Isomap augments the existing Isomap framework to consider temporal relationships in local neighborhoods that can be propagated globally via a shortest-path mechanism to reduce nonlinear dimension reduction for data with both spatial and temporal relationships.
Estimation of human core temperature from sequential heart rate observations.
A model to estimate the time course of core temperature using a series of HR measurements as a leading indicator using a Kalman filter is developed and suggests it is accurate enough to provide practical indication of thermal work strain for use in the work place.
Physical simulation for probabilistic motion tracking
A full-body 3D physical simulation-based prior that explicitly incorporates motion control and dynamics into the Bayesian filtering framework is proposed and is able to recover the physically-plausible kinematic and dynamic state of the body from monocular and multi-view imagery.
Dogged Learning for Robots
A learning system (dogged learning) that combines learning from demonstration and mixed initiative control to enable lifelong learning for unknown tasks is presented.
Rosbridge: ROS for Non-ROS Users
Rosbridge provides a simple, socket-based programmatic access to robot interfaces and algorithms provided by ROS, the open-source “Robot Operating System”, the current state-of-the-art in robot middleware.
Automated derivation of behavior vocabularies for autonomous humanoid motion
The utility of derived vocabularies derived by this methodology for synthesizing new humanoid motion that is structurally similar to the original demonstrated motion can be used in a variety of applications.
Deriving action and behavior primitives from human motion data
  • O. Jenkins, M. Matarić
  • Computer Science
    IEEE/RSJ International Conference on Intelligent…
  • 10 December 2002
This work presents a data-driven method for deriving perceptual-motor action and behavior primitives from human motion capture data using a spatio-temporal non-linear dimension reduction technique on a set of motion segments.
The Oz of Wizard: Simulating the human for interaction research
This paper distinguishes between methodologically rigorous human modeling and placeholder simulations using simplified human models, and describes a framework for describing the various permutations of Wizard and Oz states.
Interactive Task Learning
This article presents a new research area called interactive task learning (ITL), in which an agent actively tries to learn not just how to perform a task better but the actual definition of a task