Yoonsang Lee Sungeun Kim Jehee Lee Seoul National University Data-Driven Biped Control
Biped Control ? Human Biped character
Biped Control is Difficult Balance, Robustness, Looking natural Various stylistic gaits ASIMO Honda
Issues in Biped Control Naturalness Robustness Richness Interactivity human-like natural result maintaining balance variety of motor skills interactive control via user interface
Goal As realistic as motion capture data Robust under various conditions Equipped with a variety of motor skills Controlled interactively Naturalness Robustness Richness Interactivity
Related Work Manually designed controller –[Hodgins et al. 1995] [Yin et al. 2007] Non-linear optimization –[Sok 2007] [da Silva 2008] [Yin 2008] [Muico 2009] [Wang 2009] [Lasa 2010] [Wang 2010] [Wu 2010] Advanced control methodologies –[da Silva 2008] [Muico 2009] [Ye 2010] [Coros 2010] [Mordatch 2010] Data-driven approach –[Sok 2007] [da Silva 2008] [Muico 2009] [Tsai 2010] [Ye 2010] [Liu 2010]
Our Approach Control methods have been main focus –Machine learning, optimization, LQR/NQR We focus on reference data –Tracking control while modulating reference data
Our Approach Modulation of reference data –Balancing behavior of human –Importance of ground contact timings
Importance of Ground Contact Timings
Advantages Do not require –Non-linear optimization solver –Derivatives of equations of motion –Optimal control –Precomputation Easy to implement & Computationally efficient
Advantages Reference trajectory generated on-the-fly can be used Any existing data-driven techniques can be used to actuate physically simulated bipeds
Overview forward dynamics simulation animation engine user interaction data-driven control tracking control
Overview forward dynamics simulation user interaction animation engine data-driven control tracking control
Compute joint torques directly PD (Proportional Derivative) Control desired pose current pose generated torque
Compute desired tracking acceleration Forward Dynamics : force -> acceleration Inverse Dynamics : acceleration -> force Hybrid Dynamics –floating root joint : force -> acceleration –internal joints : acceleration -> force Hybrid Dynamics Tracking Control hybrid dynamics desired joint accelerations joint torques external forces
Overview forward dynamics simulation user interaction tracking control animation engine data-driven control
Data-Driven Control Continuous modulation of reference motion Spatial deviation –Simple feedback balance control (Balancing behavior) Temporal deviation –Synchronization reference to simulation (Importance of ground contact timings)
Balancing...reference motion simulation frame nframe n+1frame n+2...
frame nframe n+1frame n+2 Balancing target pose...reference motion simulation...
frame nframe n+1frame n+2 Balancing tracking...reference motion simulation...
frame n+1frame n+2frame n Balancing tracking...reference motion simulation...
Balance Feedback Near-passive knees in human walking Three-step feedback –stance hip –swing hip & stance ankle –swing foot height
Balance Feedback Biped is leaning backward ? reference motion at current frame reference motion at next frame simulation
Stance Hip Balance Feedback target pose at next frame reference frame simulation
Swing Hip & Stance Ankle Balance Feedback target pose at next frame reference frame simulation
Balance Feedback Swing Foot Height target pose at next frame reference frame simulation
Feedback Equations Stance hip Swing hip Stance ankle Swing foot height reference frametarget pose
Feedback Equations desired statescurrent states Stance hip Swing hip Stance ankle Swing foot height
Feedback Equations parameters transition function Stance hip Swing hip Stance ankle Swing foot height
Synchronization reference motion swing foot contacts the ground
Synchronization current time reference motion simulation
Early Landing reference motion contact occurs! simulation
Early Landing reference motion simulation dequed
Early Landing reference motion simulation
Early Landing reference motion simulation warped
Motion Warping motion1 motion2
Motion Warping d motion1 motion2
Early Landing reference motion simulation
Delayed Landing reference motion not contact yet! simulation
Delayed Landing reference motion simulation expand by integration
Delayed Landing reference motion simulation contact occurs! expand by integration
Delayed Landing reference motion simulation warped
Delayed Landing reference motion simulation
Overview forward dynamics simulation user interaction data-driven control tracking control animation engine
High-level control through user interfaces Generate a stream of movement patterns Animation Engine motion fragments query motion DB pattern generator user interaction stream of movement patterns
Collection of half-cycle motion fragments Maintain fragments in a directed graph Motion Database motion capture datamotion fragments
Why does this simple approach work? Human locomotion is inherently robust Mimicking human behavior –Distinctive gait serves as a reference trajectory –We do modulate the reference trajectory
Discussion We do not need optimization, optimal control, machine learning, or any precomputation Physically feasible reference motion data
Acknowledgements Thank –All the members of SNU Movement Research Laboratory –Anonymous reviewers Support –MKE & MCST of Korea
Data-Driven Biped Control Yoonsang Lee, Sungeun Kim, Jehee Lee