A Machine
Babyface
Making Meaning With Machines
Time to Compile

Robots and Dance: A Promising Young Alchemy

By A. LaViers
Counts of Mechanical, External Configurations Compared to Computational, Internal Configurations in Natural and Artificial Systems
Center-of-Mass Control for Expressive and Effective Movement in Bipedal Robots
Programmed Improvisation Inspired From Autonomous Humanoids
Breathing With Robots: Notating Performer Strategy, Alongside Choreographer Intent and Audience Observation, In Breath-driven Robotic Dance Performance
An Open Data Infrastructure for Bodily Expressed Emotion Understanding
Modeling the Interactions of Context and Style on Affect in Motion Perception: Stylized Gaits Across Multiple Environmental Contexts
Character Recognition on a Varied Robotic Platforms via a Laban Movement Analysis in Expert and Lay Groups
First Encounters with Robots Through Embodied Observation, Imagined Narrative, and Choreography
Controls and Art
Automatic Sequencing of Ballet Poses: A Formal Approach to Phrase Generation
Toward an Expressive Bipedal Robot: Variable Gait Synthesis and Validation in a Planar Model

Abstractions for Design-by-Humans of Heterogeneous Autonomous Behaviors

Written by A. LaViers, A. Bashiri, Y. Sheng, J. Heddy, and L. Bai
Style-based Robotic Motion in Contemporary Dance Performance
Babyface: Performance and Installation Art Exploring the Feminine Ideal in Gendered Machines

Automation Supporting Prolonged Independent Residence for the Elderly (ASPIRE)

National Science Foundation Award #1528036
Time to Compile: A Performance Installation as Human-Robot Interaction Study Examining Self-Evaluation and Perceived Control Through the Lenses of Movement and Technology Literacy and Valence
Imitation of Human Motion by Low Degree-of-Freedom Simulated Robots and Human Preference for Mappings Driven by Spinal, Arm, and Leg Activity
Ideal Mechanization: Exploring the Machine Metaphor Through Theory and Performance
Laban-Inspired Task-Constrained Expressive, Variable Motion Generation on Aerial Robots
Feasible Stylized Motion: Robotic Manipulator Imitation of a Human Demonstration with Collision Avoidance and Style in Increasingly Cluttered Environments
An Embodied, Platform-invariant Architecture for Connecting High-level Spatial Commands to Platform Articulation
Choreographic and Somatic Approaches for the Development of Expressive Robotic Systems

Can a Robot Do a Trust Fall? Absurdity as a Component of Human Intelligence and Embodiment

By A. LaViers and I. Vidrin
Toward Human-like Teleoperated Robot Motion: Performance and Perception of a Choreography-inspired Method in Static and Dynamic Tasks for Rapid Pose Selection of Articulated Robots
Motion-activated Wearable Robot for Live Dance Performance Investigating the Feminine Cyborg Metaphor

CURTAIN and Time to Compile: A Demonstration of an Experimental Testbed for Human-robot Interaction

Written by C. Cuan, I. Pakrasi, E. Berl, and A. LaViers
Close

Style-based Segmentation of Human Motion

Citation: Y. Sheng and A. LaViers. "Style-based Segmentation of Human Motion." IEEE International Conference on Systems Man and Cybernetics (SMC). 240-245. San Diego, CA. Oct. 2014.

Download PDF

Abstract: This paper presents a method for segmenting human motion based on a notion of quality and the movement of a user such that the exact segmentation is tailored for different subjects. The problem is solved via an inverse optimal control problem where the parameter of optimization is a time along the movement trajectory that splits the longer trajectory into distinct “moves.” First, trajectories are generated using a “forward” optimal control problem; then, the match of these generated trajectories is optimized via a second, “inverse” optimization, which determines the appropriate point of segmentation. An analytical solution to this set up, its numerical implementation, and an application to real data are presented. A key novel contribution of this paper is the analytical derivation of first order necessary conditions for optimality. The segmented movements may populate a library of movement primitives in order for robots and automated systems to perform and interpret novel tasks.