Journal article Open Access

Model-Based Reinforcement Learning for Closed-Loop Dynamic Control of Soft Robotic Manipulators

Thuruthel, Thomas George; Falotico, Egidio; Renda, Federico; Laschi, Cecilia

Citation Style Language JSON Export

{
"DOI": "10.1109/TRO.2018.2878318",
"author": [
{
"family": "Thuruthel, Thomas George"
},
{
"family": "Falotico, Egidio"
},
{
"family": "Renda, Federico"
},
{
"family": "Laschi, Cecilia"
}
],
"issued": {
"date-parts": [
[
2018,
11,
12
]
]
},
"abstract": "<p>Dynamic control of soft robotic manipulators is an open problem yet to be well explored and analyzed. Most of the current applications of soft robotic manipulators utilize static or quasi-dynamic controllers based on kinematic models or linearity in the joint space. However, such approaches are not truly exploiting the rich dynamics of a soft-bodied system. In this paper, we present a model-based policy learning algorithm for closed-loop predictive control of a soft robotic manipulator. The forward dynamic model is represented using a recurrent neural network. The closed-loop policy is derived using trajectory optimization and supervised learning. The approach is verified first on a simulated piecewise constant strain model of a cable driven under-actuated soft manipulator. Furthermore, we experimentally demonstrate on a soft pneumatically actuated manipulator how closed-loop control policies can be derived that can accommodate variable frequency control and unmodeled external loads.</p>",
"title": "Model-Based Reinforcement Learning for Closed-Loop Dynamic Control of Soft Robotic Manipulators",
"type": "article-journal",
"id": "3759636"
}
21
127
views