Limits...
Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant Robotics.

Burms J, Caluwaerts K, Dambre J - Front Neurorobot (2015)

Bottom Line: Our results demonstrate the universal applicability of reward-modulated Hebbian learning.Furthermore, they demonstrate the robustness of systems trained with the learning rule.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.

View Article: PubMed Central - PubMed

Affiliation: Computing Systems Laboratory (Reservoir Team), Electronics and Information Systems Department (ELIS), Ghent University , Ghent , Belgium.

ABSTRACT
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 optimize 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.

No MeSH data available.


Related in: MedlinePlus

Tensegrity structure used for the experiments. The top node of the center rod is used as an end-effector to draw in the XY plane. In this example, the robot draws an “S” as can be seen on the left. The right figure shows another perspective to demonstrate that the reward does not depend on the vertical position.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4538293&req=5

Figure 5: Tensegrity structure used for the experiments. The top node of the center rod is used as an end-effector to draw in the XY plane. In this example, the robot draws an “S” as can be seen on the left. The right figure shows another perspective to demonstrate that the reward does not depend on the vertical position.

Mentions: The tensegrity structure used for our experiments has four struts and is shown in Figure 5. It is based on the standard three strut tensegrity prism (Pugh, 1976) to which a shorter rod has been added that acts as a compliant end-effector. The bottom three nodes of the original prism have been fixed through ball-joints. The resulting structure has seventeen k = 20 N⋅m–1 springs, 14 of which are actuated (the lengths of the other three bottom springs are fixed). The controller time step was 50 ms and gravity was not modeled.


Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant Robotics.

Burms J, Caluwaerts K, Dambre J - Front Neurorobot (2015)

Tensegrity structure used for the experiments. The top node of the center rod is used as an end-effector to draw in the XY plane. In this example, the robot draws an “S” as can be seen on the left. The right figure shows another perspective to demonstrate that the reward does not depend on the vertical position.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4538293&req=5

Figure 5: Tensegrity structure used for the experiments. The top node of the center rod is used as an end-effector to draw in the XY plane. In this example, the robot draws an “S” as can be seen on the left. The right figure shows another perspective to demonstrate that the reward does not depend on the vertical position.
Mentions: The tensegrity structure used for our experiments has four struts and is shown in Figure 5. It is based on the standard three strut tensegrity prism (Pugh, 1976) to which a shorter rod has been added that acts as a compliant end-effector. The bottom three nodes of the original prism have been fixed through ball-joints. The resulting structure has seventeen k = 20 N⋅m–1 springs, 14 of which are actuated (the lengths of the other three bottom springs are fixed). The controller time step was 50 ms and gravity was not modeled.

Bottom Line: Our results demonstrate the universal applicability of reward-modulated Hebbian learning.Furthermore, they demonstrate the robustness of systems trained with the learning rule.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.

View Article: PubMed Central - PubMed

Affiliation: Computing Systems Laboratory (Reservoir Team), Electronics and Information Systems Department (ELIS), Ghent University , Ghent , Belgium.

ABSTRACT
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 optimize 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.

No MeSH data available.


Related in: MedlinePlus