In-Situ Sensing and Dynamics Predictions for Electrothermally-Actuated Soft Robot Limbs
Untethered soft robots that locomote using electrothermally-responsive materials like shape memory alloy (SMA) face challenging design constraints for sensing actuator states. At the same time, modeling of actuator behaviors faces steep challenges, even with available sensor data, due to complex ele...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-05-01
|
| Series: | Frontiers in Robotics and AI |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2022.888261/full |
| _version_ | 1811253406560419840 |
|---|---|
| author | Andrew P. Sabelhaus Andrew P. Sabelhaus Rohan K. Mehta Anthony T. Wertz Anthony T. Wertz Carmel Majidi Carmel Majidi |
| author_facet | Andrew P. Sabelhaus Andrew P. Sabelhaus Rohan K. Mehta Anthony T. Wertz Anthony T. Wertz Carmel Majidi Carmel Majidi |
| author_sort | Andrew P. Sabelhaus |
| collection | DOAJ |
| description | Untethered soft robots that locomote using electrothermally-responsive materials like shape memory alloy (SMA) face challenging design constraints for sensing actuator states. At the same time, modeling of actuator behaviors faces steep challenges, even with available sensor data, due to complex electrical-thermal-mechanical interactions and hysteresis. This article proposes a framework for in-situ sensing and dynamics modeling of actuator states, particularly temperature of SMA wires, which is used to predict robot motions. A planar soft limb is developed, actuated by a pair of SMA coils, that includes compact and robust sensors for temperature and angular deflection. Data from these sensors are used to train a neural network-based on the long short-term memory (LSTM) architecture to model both unidirectional (single SMA) and bidirectional (both SMAs) motion. Predictions from the model demonstrate that data from the temperature sensor, combined with control inputs, allow for dynamics predictions over extraordinarily long open-loop timescales (10 min) with little drift. Prediction errors are on the order of the soft deflection sensor’s accuracy. This architecture allows for compact designs of electrothermally-actuated soft robots that include sensing sufficient for motion predictions, helping to bring these robots into practical application. |
| first_indexed | 2024-04-12T16:50:27Z |
| format | Article |
| id | doaj.art-fb19044b5eb2492fb0d3920f7cdd7eaa |
| institution | Directory Open Access Journal |
| issn | 2296-9144 |
| language | English |
| last_indexed | 2024-04-12T16:50:27Z |
| publishDate | 2022-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Robotics and AI |
| spelling | doaj.art-fb19044b5eb2492fb0d3920f7cdd7eaa2022-12-22T03:24:25ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442022-05-01910.3389/frobt.2022.888261888261In-Situ Sensing and Dynamics Predictions for Electrothermally-Actuated Soft Robot LimbsAndrew P. Sabelhaus0Andrew P. Sabelhaus1Rohan K. Mehta2Anthony T. Wertz3Anthony T. Wertz4Carmel Majidi5Carmel Majidi6Soft Robotics Control Lab, Department of Mechanical Engineering, Boston University, Boston, MA, United StatesSoft Machines Lab, Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, United StatesSoft Machines Lab, Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, United StatesSoft Machines Lab, Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, United StatesRobotics Institute, Carnegie Mellon University, Pittsburgh, PA, United StatesSoft Machines Lab, Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, United StatesRobotics Institute, Carnegie Mellon University, Pittsburgh, PA, United StatesUntethered soft robots that locomote using electrothermally-responsive materials like shape memory alloy (SMA) face challenging design constraints for sensing actuator states. At the same time, modeling of actuator behaviors faces steep challenges, even with available sensor data, due to complex electrical-thermal-mechanical interactions and hysteresis. This article proposes a framework for in-situ sensing and dynamics modeling of actuator states, particularly temperature of SMA wires, which is used to predict robot motions. A planar soft limb is developed, actuated by a pair of SMA coils, that includes compact and robust sensors for temperature and angular deflection. Data from these sensors are used to train a neural network-based on the long short-term memory (LSTM) architecture to model both unidirectional (single SMA) and bidirectional (both SMAs) motion. Predictions from the model demonstrate that data from the temperature sensor, combined with control inputs, allow for dynamics predictions over extraordinarily long open-loop timescales (10 min) with little drift. Prediction errors are on the order of the soft deflection sensor’s accuracy. This architecture allows for compact designs of electrothermally-actuated soft robots that include sensing sufficient for motion predictions, helping to bring these robots into practical application.https://www.frontiersin.org/articles/10.3389/frobt.2022.888261/fullsoft robot controlsoft robot sensingsoft robot dynamicssoft robot modelingmachine learningsensor design |
| spellingShingle | Andrew P. Sabelhaus Andrew P. Sabelhaus Rohan K. Mehta Anthony T. Wertz Anthony T. Wertz Carmel Majidi Carmel Majidi In-Situ Sensing and Dynamics Predictions for Electrothermally-Actuated Soft Robot Limbs Frontiers in Robotics and AI soft robot control soft robot sensing soft robot dynamics soft robot modeling machine learning sensor design |
| title | In-Situ Sensing and Dynamics Predictions for Electrothermally-Actuated Soft Robot Limbs |
| title_full | In-Situ Sensing and Dynamics Predictions for Electrothermally-Actuated Soft Robot Limbs |
| title_fullStr | In-Situ Sensing and Dynamics Predictions for Electrothermally-Actuated Soft Robot Limbs |
| title_full_unstemmed | In-Situ Sensing and Dynamics Predictions for Electrothermally-Actuated Soft Robot Limbs |
| title_short | In-Situ Sensing and Dynamics Predictions for Electrothermally-Actuated Soft Robot Limbs |
| title_sort | in situ sensing and dynamics predictions for electrothermally actuated soft robot limbs |
| topic | soft robot control soft robot sensing soft robot dynamics soft robot modeling machine learning sensor design |
| url | https://www.frontiersin.org/articles/10.3389/frobt.2022.888261/full |
| work_keys_str_mv | AT andrewpsabelhaus insitusensinganddynamicspredictionsforelectrothermallyactuatedsoftrobotlimbs AT andrewpsabelhaus insitusensinganddynamicspredictionsforelectrothermallyactuatedsoftrobotlimbs AT rohankmehta insitusensinganddynamicspredictionsforelectrothermallyactuatedsoftrobotlimbs AT anthonytwertz insitusensinganddynamicspredictionsforelectrothermallyactuatedsoftrobotlimbs AT anthonytwertz insitusensinganddynamicspredictionsforelectrothermallyactuatedsoftrobotlimbs AT carmelmajidi insitusensinganddynamicspredictionsforelectrothermallyactuatedsoftrobotlimbs AT carmelmajidi insitusensinganddynamicspredictionsforelectrothermallyactuatedsoftrobotlimbs |