MuscleVAE: Model-based Controllers of Muscle-Actuated Characters
SIGGRAPH ASIA 2023
Why Muscle?
Potential for highly realistic and accurate character movements
Torque
Joint-based
Muscle-based
Constraint
Contributions
(1) We propose a novel simulation and control framework for muscle-actuated characters.
(2) We develop a generative control policy for muscle-driven characters.
Novel Muscle Model (w/ Fatigue) + ControlVAE
Muscle Modeling
Symmetry modified
Musculoskeletal model from MASS [Lee et al. 2019]
MuscleVAE Model
Muscle Modeling
Muscle = Polyline defined by anchor points
anchor point positions computed by LBS
Muscle Dynamics
Hill-type muscle model
CE (Contractile Element) : active contractile force
PE (Parallel elastic Element) : passive, non-linear spring force
SE (Series or tendon element)
Simplification:
Muscle Dynamics
Hill-type muscle model [Hill 1938; Zajac 1989]
Activation level,
Normalized muscle length and its rate of change
Active force-length, Active force-velocity, Passive force-length function
Fatigue Dynamics
3CC-r model [Looft et al. 2018]
Each muscle consists of multiple muscle-tendon actuators, in one of three possible states (M = percentage)
Activated actuators produce maximal contractile forces, while others don’t
= activation level of entire muscle ( )
Fatigue Dynamics
3CC-r model [Looft et al. 2018]
Fatigue Dynamics
3CC-r model [Looft et al. 2018]
Target Load
Transfer rate, determined by difference between target load and activation level
Recovery coefficient
Fatigue coefficient
Muscle Space Control
Attempt: Using muscle activation levels as action space lead to poor convergence
Muscle Space Control
MASS method
Joint PD-target
Muscle activation
Muscle Space Control
Alternative: PD control-like formulation to calculate muscle force, one-step
Muscle Space Control
Target muscle length
Current muscle length, and its rate of change
Predefined PD gains
Muscle can only be contractile
Muscle Space Control
Muscle Activation Constraints
is not always realizable based on !
must be in feasible range to achieve proper activation
Muscle Space Control
Assuming =
Next activation level is determined by previous muscle activation level and target load
and
increases monotonically with target load
Muscle Space Control
Policy outputs action for each muscle and computes target muscle length
Reference muscle length in T-pose
Muscle Space Control
Model
MuscleVAE
Inspired by ControlVAE [Yao et al. 2022]
MuscleVAE
Inspired by ControlVAE [Yao et al. 2022]
not included, as it can be directly computed from
Positions
Orientations
Velocities of all rigid bones
= ( , )
MuscleVAE
Inspired by ControlVAE [Yao et al. 2022]
Encoder
Decoder
MuscleVAE
Inspired by ControlVAE [Yao et al. 2022]
Encoder
Predefined
Standard deviation
Posterior distribution
~
=
State-dependent prior distribution
MuscleVAE
Inspired by ControlVAE [Yao et al. 2022]
Objective function
weight parameter
MuscleVAE
Inspired by ControlVAE [Yao et al. 2022]
Objective function
Reconstruction Loss
Reference states
Simulation states
Weight matrices
Discount factor
MuscleVAE
Inspired by ControlVAE [Yao et al. 2022]
Objective function
KL-Divergence Loss
MuscleVAE
Inspired by ControlVAE [Yao et al. 2022]
Objective function
Regularization Loss
Mitigate excessive control
Satisfy biological requirements of minimal bioenergy and activation thresholds
MuscleVAE
Inspired by ControlVAE [Yao et al. 2022]
Objective function
Can’t be directly optimized!
Complex rigid body simulation is required
MuscleVAE
Inspired by ControlVAE [Yao et al. 2022]
Model-based Learning
World Model
Approximates dynamics of musculoskeletal system with Network
MuscleVAE
Inspired by ControlVAE [Yao et al. 2022]
Model-based Learning
In real simulation, generate a simulation sequence
using current MuscleVAE to track random sequence
Starting from , create a synthetic sequence by executing same action series
Train world model by optimizing objective
High-Level Policies
With a trained MuscleVAE, goal-conditioned task policy can be trained
Result
Motion Tracking
Result
Random Motion Sampling
Supplementary Materials
Supplementary Materials