A Probabilistic Representation for Dynamic Movement Primitives
This work addresses robustness in robot motion control, but it is incremental as it builds on existing DMP frameworks.
The paper tackles the problem of making Dynamic Movement Primitives (DMPs) more robust by reformulating them as a probabilistic linear dynamical system, enabling the use of Kalman filtering for inference and feedback during execution, with initial results showing failure detection on a simulated dataset.
Dynamic Movement Primitives have successfully been used to realize imitation learning, trial-and-error learning, reinforce- ment learning, movement recognition and segmentation and control. Because of this they have become a popular represen- tation for motor primitives. In this work, we showcase how DMPs can be reformulated as a probabilistic linear dynamical system with control inputs. Through this probabilistic repre- sentation of DMPs, algorithms such as Kalman filtering and smoothing are directly applicable to perform inference on pro- prioceptive sensor measurements during execution. We show that inference in this probabilistic model automatically leads to a feedback term to online modulate the execution of a DMP. Furthermore, we show how inference allows us to measure the likelihood that we are successfully executing a given motion primitive. In this context, we show initial results of using the probabilistic model to detect execution failures on a simulated movement primitive dataset.