Limits...
Distributed recurrent neural forward models with synaptic adaptation and CPG-based control for complex behaviors of walking robots.

Dasgupta S, Goldschmidt D, Wörgötter F, Manoonpong P - Front Neurorobot (2015)

Bottom Line: Biological study has revealed that such complex behaviors are a result of a combination of biomechanics and neural mechanism thus representing the true nature of embodied interactions.Inspired by these findings, we present here, an artificial bio-inspired walking system which effectively combines biomechanics (in terms of the body and leg structures) with the underlying neural mechanisms.Furthermore, we demonstrate that the newly developed recurrent network based approach to online forward models outperforms the adaptive neuron forward models, which have hitherto been the state of the art, to model a subset of similar walking behaviors in walking robots.

View Article: PubMed Central - PubMed

Affiliation: Institute for Physics - Biophysics, George-August-University Göttingen, Germany ; Bernstein Center for Computational Neuroscience, George-August-University Göttingen, Germany ; Laboratory for Neural Computation and Adaptation, Riken Brain Science Institute Saitama, Japan.

ABSTRACT
Walking animals, like stick insects, cockroaches or ants, demonstrate a fascinating range of locomotive abilities and complex behaviors. The locomotive behaviors can consist of a variety of walking patterns along with adaptation that allow the animals to deal with changes in environmental conditions, like uneven terrains, gaps, obstacles etc. Biological study has revealed that such complex behaviors are a result of a combination of biomechanics and neural mechanism thus representing the true nature of embodied interactions. While the biomechanics helps maintain flexibility and sustain a variety of movements, the neural mechanisms generate movements while making appropriate predictions crucial for achieving adaptation. Such predictions or planning ahead can be achieved by way of internal models that are grounded in the overall behavior of the animal. Inspired by these findings, we present here, an artificial bio-inspired walking system which effectively combines biomechanics (in terms of the body and leg structures) with the underlying neural mechanisms. The neural mechanisms consist of (1) central pattern generator based control for generating basic rhythmic patterns and coordinated movements, (2) distributed (at each leg) recurrent neural network based adaptive forward models with efference copies as internal models for sensory predictions and instantaneous state estimations, and (3) searching and elevation control for adapting the movement of an individual leg to deal with different environmental conditions. Using simulations we show that this bio-inspired approach with adaptive internal models allows the walking robot to perform complex locomotive behaviors as observed in insects, including walking on undulated terrains, crossing large gaps, leg damage adaptations, as well as climbing over high obstacles. Furthermore, we demonstrate that the newly developed recurrent network based approach to online forward models outperforms the adaptive neuron forward models, which have hitherto been the state of the art, to model a subset of similar walking behaviors in walking robots.

No MeSH data available.


Related in: MedlinePlus

Successfully navigating rough terrain with reservoir forward model. (A) The reservoir forward model predicted, expected foot contact signal. After a small initial transient the reservoir output quickly converges to the expect signal for normal walking condition. (B) The actual sensory feedback (foot contact signal) while walking on the rough surface (C) Accumulated error calculated from the instantaneous error (Δ(t)) after passing through the recurrent neuron in the searching and elevation control. (D) The searching and elevation action control system consisting of individual recurrent neurons as signal accumulators. After 4000 time steps, the robot successfully overcomes the rough terrain and continuous walking on a flat surface. As a result, there is zero accumulated error since the predicted foot contact signal almost exactly matches the actual signal. See the experiment Supplementary Video 3.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4585172&req=5

Figure 6: Successfully navigating rough terrain with reservoir forward model. (A) The reservoir forward model predicted, expected foot contact signal. After a small initial transient the reservoir output quickly converges to the expect signal for normal walking condition. (B) The actual sensory feedback (foot contact signal) while walking on the rough surface (C) Accumulated error calculated from the instantaneous error (Δ(t)) after passing through the recurrent neuron in the searching and elevation control. (D) The searching and elevation action control system consisting of individual recurrent neurons as signal accumulators. After 4000 time steps, the robot successfully overcomes the rough terrain and continuous walking on a flat surface. As a result, there is zero accumulated error since the predicted foot contact signal almost exactly matches the actual signal. See the experiment Supplementary Video 3.

Mentions: During testing of the learned behavior, while AMOSII walks under different environmental conditions and a specific gait, the output of each trained forward model (i.e., the predicted FC signal, Figure 6A) is used to compare it to the actual incoming FC signal of the leg (Figure 6B). The difference (instantaneous error signal Δ) between them determines the walking state where a positive value (+Δ) indicates losing ground contact during the stance phase and a negative value (−Δ) indicates stepping on or hitting obstacles during the swing phase.


Distributed recurrent neural forward models with synaptic adaptation and CPG-based control for complex behaviors of walking robots.

Dasgupta S, Goldschmidt D, Wörgötter F, Manoonpong P - Front Neurorobot (2015)

Successfully navigating rough terrain with reservoir forward model. (A) The reservoir forward model predicted, expected foot contact signal. After a small initial transient the reservoir output quickly converges to the expect signal for normal walking condition. (B) The actual sensory feedback (foot contact signal) while walking on the rough surface (C) Accumulated error calculated from the instantaneous error (Δ(t)) after passing through the recurrent neuron in the searching and elevation control. (D) The searching and elevation action control system consisting of individual recurrent neurons as signal accumulators. After 4000 time steps, the robot successfully overcomes the rough terrain and continuous walking on a flat surface. As a result, there is zero accumulated error since the predicted foot contact signal almost exactly matches the actual signal. See the experiment Supplementary Video 3.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4585172&req=5

Figure 6: Successfully navigating rough terrain with reservoir forward model. (A) The reservoir forward model predicted, expected foot contact signal. After a small initial transient the reservoir output quickly converges to the expect signal for normal walking condition. (B) The actual sensory feedback (foot contact signal) while walking on the rough surface (C) Accumulated error calculated from the instantaneous error (Δ(t)) after passing through the recurrent neuron in the searching and elevation control. (D) The searching and elevation action control system consisting of individual recurrent neurons as signal accumulators. After 4000 time steps, the robot successfully overcomes the rough terrain and continuous walking on a flat surface. As a result, there is zero accumulated error since the predicted foot contact signal almost exactly matches the actual signal. See the experiment Supplementary Video 3.
Mentions: During testing of the learned behavior, while AMOSII walks under different environmental conditions and a specific gait, the output of each trained forward model (i.e., the predicted FC signal, Figure 6A) is used to compare it to the actual incoming FC signal of the leg (Figure 6B). The difference (instantaneous error signal Δ) between them determines the walking state where a positive value (+Δ) indicates losing ground contact during the stance phase and a negative value (−Δ) indicates stepping on or hitting obstacles during the swing phase.

Bottom Line: Biological study has revealed that such complex behaviors are a result of a combination of biomechanics and neural mechanism thus representing the true nature of embodied interactions.Inspired by these findings, we present here, an artificial bio-inspired walking system which effectively combines biomechanics (in terms of the body and leg structures) with the underlying neural mechanisms.Furthermore, we demonstrate that the newly developed recurrent network based approach to online forward models outperforms the adaptive neuron forward models, which have hitherto been the state of the art, to model a subset of similar walking behaviors in walking robots.

View Article: PubMed Central - PubMed

Affiliation: Institute for Physics - Biophysics, George-August-University Göttingen, Germany ; Bernstein Center for Computational Neuroscience, George-August-University Göttingen, Germany ; Laboratory for Neural Computation and Adaptation, Riken Brain Science Institute Saitama, Japan.

ABSTRACT
Walking animals, like stick insects, cockroaches or ants, demonstrate a fascinating range of locomotive abilities and complex behaviors. The locomotive behaviors can consist of a variety of walking patterns along with adaptation that allow the animals to deal with changes in environmental conditions, like uneven terrains, gaps, obstacles etc. Biological study has revealed that such complex behaviors are a result of a combination of biomechanics and neural mechanism thus representing the true nature of embodied interactions. While the biomechanics helps maintain flexibility and sustain a variety of movements, the neural mechanisms generate movements while making appropriate predictions crucial for achieving adaptation. Such predictions or planning ahead can be achieved by way of internal models that are grounded in the overall behavior of the animal. Inspired by these findings, we present here, an artificial bio-inspired walking system which effectively combines biomechanics (in terms of the body and leg structures) with the underlying neural mechanisms. The neural mechanisms consist of (1) central pattern generator based control for generating basic rhythmic patterns and coordinated movements, (2) distributed (at each leg) recurrent neural network based adaptive forward models with efference copies as internal models for sensory predictions and instantaneous state estimations, and (3) searching and elevation control for adapting the movement of an individual leg to deal with different environmental conditions. Using simulations we show that this bio-inspired approach with adaptive internal models allows the walking robot to perform complex locomotive behaviors as observed in insects, including walking on undulated terrains, crossing large gaps, leg damage adaptations, as well as climbing over high obstacles. Furthermore, we demonstrate that the newly developed recurrent network based approach to online forward models outperforms the adaptive neuron forward models, which have hitherto been the state of the art, to model a subset of similar walking behaviors in walking robots.

No MeSH data available.


Related in: MedlinePlus