Machine Learning Best Practices for Soft Robot Proprioception

Machine learning-based approaches for soft robot proprioception have recently gained popularity, in part due to the difficulties in modeling the relationship between sensor signals and robot shape. However, to date, there exists no systematic analysis of the required design choices to set up a machine learning pipeline for soft robot proprioception. Here, we present the first study examining how design choices on different levels of the machine learning pipeline affect the performance of a neural network for predicting the state of a soft robot. We address the most frequent questions researchers face, such as how to choose the appropriate sensor and actuator signals, process input and output data, deal with time series, and pick the best neural network architecture. By testing our hypotheses on data collected from two vastly different systems–an electrically actuated robotic platform and a pneumatically actuated soft trunk–we seek conclusions that may generalize beyond one specific type of soft robot and hope to provide insights for researchers to use machine learning for soft robot proprioception.

Authors

• Annan Zhang
• Tsun-Hsuan Wang
• Ryan L. Truby
• Lillian Chin
• Daniela Rus

Keywords

• Actuators
• Systematics
• Pipelines
• Neural networks
• Time series analysis
• Machine learning
• Soft robotics
• Proprioceptive
• Soft Robots
• Neural Network
• Sensory Signals
• Design Choices
• Input Processing
• Robotic Platform
• Robot State
• Machine Learning Pipeline
• Long-term Effects
• Test Data
• Convolutional Neural Network
• Time Delay
• Validation Set
• Center Of Mass
• Prediction Error
• Time Series Data
• Soft Materials
• Domain Shift
• Performance Of Configurations
• Actuator Input
• Lowest Error
• Constant Curvature
• Keypoint Locations
• Worth Consideration
• Model Architecture
• Soft System
• Position Error
• Time-dependent Effects