Towards robust online inverse dynamics learning

Learning of inverse dynamics modeling errors is key for compliant or force control when analytical models are only rough approximations. Thus, designing real time capable function approximation algorithms has been a necessary focus towards the goal of online model learning. However, because these approaches learn a mapping from actual state and acceleration to torque, good tracking is required to observe data points on the desired path. Recently it has been shown how online gradient descent on a simple modeling error offset term to minimize tracking at acceleration level can address this issue. However, to adapt to larger errors a high learning rate of the online learner is required, resulting in reduced compliancy. Thus, here we propose to combine both approaches: The online adapted offset term ensures good tracking such that a nonlinear function approximator is able to learn an error model on the desired trajectory. This, in turn, reduces the load on the adaptive feedback, enabling it to use a lower learning rate. Combined this creates a controller with variable feedback and low gains, and a feedforward model that can account for larger modeling errors. We demonstrate the effectiveness of this framework, in simulation and on a real system.

Authors

• Franziska Meier
• Daniel Kappler
• Nathan D. Ratliff
• Stefan Schaal

Keywords

• Acceleration
• Adaptation models
• Feedforward neural networks
• Torque
• Computational modeling
• Predictive models
• Dynamics
• Inverse Dynamics
• Learning Models
• Dynamic Model
• Learning Rate
• Gradient Descent
• Large Errors
• Error Model
• Online Learning
• Function Approximation
• Nonlinear Estimation
• Good Tracking
• Offset Term
• Higher Learning Rate
• Acceleration Level
• Lower Learning Rate
• Time Step
• Model Estimates
• Model Validation
• Hyperparameters
• Nonlinear Model
• Feedback Term
• Gaussian Process Regression Model
• Gaussian Process
• Proportional-integral-derivative
• Gaussian Process Model
• Kriging
• Exponential Smoothing
• Feedback Gain
• Total Torque
• Rigid Body Dynamics