Reverse Control for Humanoid Robot Task Recognition
Authors:
- 26 April 2012
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
- Vol. 42 (6) , 1524-1537
Abstract
Efficient methods to perform motion recognition have been developed using statistical tools. Those methods rely on primitive learning in a suitable space, for example, the latent space of the joint angle and/or adequate task spaces. Learned primitives are often sequential: A motion is segmented according to the time axis. When working with a humanoid robot, a motion can be decomposed into parallel subtasks. For example, in a waiter scenario, the robot has to keep some plates horizontal with one of its arms while placing a plate on the table with its free hand. Recognition can thus not be limited to one task per consecutive segment of time. The method presented in this paper takes advantage of the knowledge of what tasks the robot is able to do and how the motion is generated from this set of known controllers, to perform a reverse engineering of an observed motion. This analysis is intended to recognize parallel tasks that have been used to generate a motion. The method relies on the task-function formalism and the projection operation into the null space of a task to decouple the controllers. The approach is successfully applied on a real robot to disambiguate motion in different scenarios where two motions look similar but have different purposes.Keywords
This publication has 29 references indexed in Scilit:
- Efficient model-based 3D tracking of hand articulations using Kinect2011
- Recognition of Affect Based on Gait PatternsIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2010
- Task Sequencing for High-Level Sensor-Based ControlIEEE Transactions on Robotics, 2007
- Identification of Humans Using GaitIEEE Transactions on Image Processing, 2004
- Generating and recognizing free-space movements in humanoid robots2004
- Exemplar-based primitives for humanoid movement classification and control2004
- Computational approaches to motor learning by imitationPhilosophical Transactions of the Royal Society B: Biological Sciences, 2003
- Singularity-robust task-priority redundancy resolution for real-time kinematic control of robot manipulatorsIEEE Transactions on Robotics and Automation, 1997
- Recognizing friends by their walk: Gait perception without familiarity cuesBulletin of the Psychonomic Society, 1977
- Automatic Supervisory Control of the Configuration and Behavior of Multibody MechanismsIEEE Transactions on Systems, Man, and Cybernetics, 1977