Research >> Projects

In the context of this work, the primitive set is the basis set of behaviors that is sufficient for generating a large repertoire of movements, through composition operators of sequencing and superposition.  We call these generative primitives to distinguish them from evolutionary primitives, such as spinal central pattern generators.

The primary focus of this project is with regard to primitive set determination, i.e., the process of automatically extracting a set of primitives from the movement data.  To address this problem, we are focusing on the issue of appropriately representing the input motion so as to facilitate primitive extraction.  The encoding and decoding of this representations are handled by the Motion Preprocessor and the Motor Controller, respectively. Motion Preprocessing The Motion Preprocessing module is responsible for converting "raw" perceptual data (given knowledge about kinematic substructures) into the intermediate form.  This component performs two major operations: segmentation and normalization.  Motion segmentation is a difficult problem, and will not be explicitly addressed within the scope of this project.  Instead, the incoming motion stream will be assumed as an atomic motion.  The normalization procedure is performed in order to apply useful invariances to the motion data. But what invariances are most useful?  From, the motion of an end-point with invariance to absolute position (translation) and scale appear to provide some good normalization results.  Rotational invariance can be added by specifying more information about a significant kinematic substructures.
Our contention is that a kinematic substructure in the intermediate form should be specified by a base, a feature center (feature centroid), and an end-point.  Considering a human arm, the base and end-point could be represented by the shoulder and middle fingertip locations, respectively.  The feature center would be the mean location of all of the features of the arm.  The feature locations could consist of the shoulder, elbow, wrist, and middle fingertip.  The intuition for using this representation is that the main purpose of the motion for arm substructure is to generate the end-point trajectory, but information about the intermediate joints cannot be discarded.  The feature center provides a meaningful estimation of the configuration of the intermediate features and where a behavior is happening with respect to a larger coordinate frame.  Rotational invariance is now added to the motion data by constructing a new coordinate frame at the substructure base with the vector from the base to the feature center serving as the system's z-axis and transforming the end-point information into this system.  The motion data is now the end-point in the rotationally normalized system (what is the behavior) and the feature center in substructure coordinate (where the behavior is being performed).  The remaining normalization issues to be addressed in this component is that of motion duration.  In order to handle movements of various number of samples, we have made some initial attempts using wavelet decompositions, primarily with the simple Haar wavelet. Primitive Set Determination This component is responsible for clustering various incoming motion segments into meaningful classes of behaviors.  Two main operations take place: clustering and stereotyping.  From the preprocessing procedure, various motion segments should cluster into meaningful classes of behaviors.  The motion data are clustered based primarily on the end-point information, with the feature center being clustered in a supplementary space.  The clustering procedure may be as simple as one of the heuristic methods, but all of these methods require a known number of classes or some other complex parameter.  Once the clusters are formed, they must be stereotyped (generalized) in order to generate appropriate paramerizations.  From these stereotypical descriptions, the basis set of primitives is formed. Motor Control We are currently exploring different approaches to forming motor primitives. One is based on of substructure motion; it uses substructure information to compute desired trajectories for each joint, which could then be actuated by an appropriate form of PID control.

Publications

• Odest Chadwicke Jenkins and Maja J Mataric´, "Deriving Action and Behavior Primitives from Human Motion Data". In the IEEE/RSJ Internation Conference on Intelligent Robots and Systems (IROS-2002), pages 2551-2556, Lausanne, Switzerland, 2002. [PS] [PDF]

• Odest Chadwicke Jenkins, Maja J Mataric´, and Stefan Weber, "Primitive-Based Movement Classification for Humanoid Imitation", Proceedings, First IEEE-RAS International Conference on Humanoid Robotics (Humanoids-2000), MIT, Cambridge, MA, Sep 7-8, 2000. (Accompanying Movie)

• Ajo Fod, Maja J Mataric´, and Odest Chadwicke Jenkins, "Automated Derivation of Primitives for Movement Classification" , Proceedings, First IEEE-RAS International Conference on Humanoid Robotics (Humanoids-2000), MIT, Cambridge, MA, Sep 7-8, 2000.

• Stefan Weber, Chad Jenkins, and Maja J Mataric´, "Imitation Using Perceptual and Motor Primitives", Proceedings, Autonomous Agents 2000, Barcelona, Spain, June 3-7, 2000, 136-137.

• Odest C. Jenkins and Maja J Mataric´, "Primitives and Behavior-Based Architectures for Interactive Entertainment", AAAI Fall Symposium on on AI and Interactive Entertainment, Stanford, CA, CA, Mar 26-28, 2001.

• Maja J Mataric´, Odest C. Jenkins, Ajo Fod, and Victor Zordan, "Control and Imitation in Humanoids", AAAI Fall Symposium on Simulating Human Agents, North Falmouth, MA, Nov 3-5, 2000.

 For more information about this project: contact Chad Jenkins at cjenkins@pollux.usc.edu or Maja Mataric at mataric@usc.edu.