Reward modulated Hebbian plasticity as leverage for partially embodied control in compliant robotics
In embodied computation (or morphological computation), part of the complexity of motor control is offloaded to the body dynamics. We demonstrate that a simple Hebbian-like learning rule can be used to train systems with (partial) embodiment, and can be extended outside of the scope of traditional n...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2015-08-01
|
| Series: | Frontiers in Neurorobotics |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fnbot.2015.00009/full |
| _version_ | 1818196910188527616 |
|---|---|
| author | Jeroen eBurms Ken eCaluwaerts Ken eCaluwaerts Joni eDambre |
| author_facet | Jeroen eBurms Ken eCaluwaerts Ken eCaluwaerts Joni eDambre |
| author_sort | Jeroen eBurms |
| collection | DOAJ |
| description | In embodied computation (or morphological computation), part of the complexity of motor control is offloaded to the body dynamics. We demonstrate that a simple Hebbian-like learning rule can be used to train systems with (partial) embodiment, and can be extended outside of the scope of traditional neural networks. To this end, we apply the learning rule to optimise the connection weights of recurrent neural networks with different topologies and for various tasks. We then apply this learning rule to a simulated compliant tensegrity robot by optimizing static feedback controllers that directly exploit the dynamics of the robot body. This leads to partially embodied controllers, i.e., hybrid controllers that naturally integrate the computations that are performed by the robot body into a neural network architecture. Our results demonstrate the universal applicability of reward-modulated Hebbian learning. Furthermore, they demonstrate the robustness of systems trained with the learning rule. This study strengthens our belief that compliant robots should or can be seen as computational units, instead of dumb hardware that needs a complex controller. This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics. |
| first_indexed | 2024-12-12T01:41:35Z |
| format | Article |
| id | doaj.art-e90faa04a388432193a7c0fb5841ff7c |
| institution | Directory Open Access Journal |
| issn | 1662-5218 |
| language | English |
| last_indexed | 2024-12-12T01:41:35Z |
| publishDate | 2015-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurorobotics |
| spelling | doaj.art-e90faa04a388432193a7c0fb5841ff7c2022-12-22T00:42:42ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182015-08-01910.3389/fnbot.2015.00009135673Reward modulated Hebbian plasticity as leverage for partially embodied control in compliant roboticsJeroen eBurms0Ken eCaluwaerts1Ken eCaluwaerts2Joni eDambre3Ghent UniversityGhent UniversityNASAGhent UniversityIn embodied computation (or morphological computation), part of the complexity of motor control is offloaded to the body dynamics. We demonstrate that a simple Hebbian-like learning rule can be used to train systems with (partial) embodiment, and can be extended outside of the scope of traditional neural networks. To this end, we apply the learning rule to optimise the connection weights of recurrent neural networks with different topologies and for various tasks. We then apply this learning rule to a simulated compliant tensegrity robot by optimizing static feedback controllers that directly exploit the dynamics of the robot body. This leads to partially embodied controllers, i.e., hybrid controllers that naturally integrate the computations that are performed by the robot body into a neural network architecture. Our results demonstrate the universal applicability of reward-modulated Hebbian learning. Furthermore, they demonstrate the robustness of systems trained with the learning rule. This study strengthens our belief that compliant robots should or can be seen as computational units, instead of dumb hardware that needs a complex controller. This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics.http://journal.frontiersin.org/Journal/10.3389/fnbot.2015.00009/fullmorphological computationrecurrent neural networksHebbian plasticitytensegrityCompliant robotics |
| spellingShingle | Jeroen eBurms Ken eCaluwaerts Ken eCaluwaerts Joni eDambre Reward modulated Hebbian plasticity as leverage for partially embodied control in compliant robotics Frontiers in Neurorobotics morphological computation recurrent neural networks Hebbian plasticity tensegrity Compliant robotics |
| title | Reward modulated Hebbian plasticity as leverage for partially embodied control in compliant robotics |
| title_full | Reward modulated Hebbian plasticity as leverage for partially embodied control in compliant robotics |
| title_fullStr | Reward modulated Hebbian plasticity as leverage for partially embodied control in compliant robotics |
| title_full_unstemmed | Reward modulated Hebbian plasticity as leverage for partially embodied control in compliant robotics |
| title_short | Reward modulated Hebbian plasticity as leverage for partially embodied control in compliant robotics |
| title_sort | reward modulated hebbian plasticity as leverage for partially embodied control in compliant robotics |
| topic | morphological computation recurrent neural networks Hebbian plasticity tensegrity Compliant robotics |
| url | http://journal.frontiersin.org/Journal/10.3389/fnbot.2015.00009/full |
| work_keys_str_mv | AT jeroeneburms rewardmodulatedhebbianplasticityasleverageforpartiallyembodiedcontrolincompliantrobotics AT kenecaluwaerts rewardmodulatedhebbianplasticityasleverageforpartiallyembodiedcontrolincompliantrobotics AT kenecaluwaerts rewardmodulatedhebbianplasticityasleverageforpartiallyembodiedcontrolincompliantrobotics AT joniedambre rewardmodulatedhebbianplasticityasleverageforpartiallyembodiedcontrolincompliantrobotics |