Body Randomization Reduces the Sim-to-Real Gap for Compliant Quadruped Locomotion

Vandesompele, Alexander; Urbain, Gabriel; Mahmud, Hossain; wyffels, Francis; Dambre, Joni

doi:10.3389/fnbot.2019.00009

Cited by 10 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, our investigations demonstrate the need for a mechanism of stability and gravity compensation to handle this task. Successful applications in robot locomotion using neural networks generally rely on position control either of stiff robots [33], [34], either of small and light compliant robot [15]. On a heavy torque-controlled compliant robot, in contrast, the lift-off cannot be easily guaranteed in the absence of a gravity compensation mechanism.…”

Section: Discussionmentioning

confidence: 99%

“…It has been shown that the model could also handle disturbance and small obstacles by naturally generating recovery foot trajectories [13]. Pure reflex-based locomotion has also been achieved in robotics where embodied walking, trotting and bounding gaits were implemented on small compliant quadruped robots using only proprioceptive feedback with no timing information [14] [15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stance Control Inspired by Cerebellum Stabilizes Reflex-Based Locomotion on HyQ Robot

Urbain

Barasuol

Semini

et al. 2020

2020 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Advances in legged robotics are strongly rooted in animal observations. A clear illustration of this claim is the generalization of Central Pattern Generators (CPG), first identified in the cat spinal cord, to generate cyclic motion in robotic locomotion. Despite a global endorsement of this model, physiological and functional experiments in mammals have also indicated the presence of descending signals from the cerebellum, and reflex feedback from the lower limb sensory cells, that closely interact with CPGs. To this day, these interactions are not fully understood. In some studies, it was demonstrated that pure reflex-based locomotion in the absence of oscillatory signals could be achieved in realistic musculoskeletal simulation models or small compliant quadruped robots. At the same time, biological evidence has attested the functional role of the cerebellum for predictive control of balance and stance within mammals. In this paper, we promote both approaches and successfully apply reflex-based dynamic locomotion, coupled with a balance and gravity compensation mechanism, on the state-of-art HyQ robot. We discuss the importance of this stability module to ensure a correct foot lift-off and maintain a reliable gait. The robotic platform is further used to test two different architectural hypotheses inspired by the cerebellum. An analysis of experimental results demonstrates that the most biologically plausible alternative also leads to better results for robust locomotion.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Stance Control Inspired by Cerebellum Stabilizes Reflex-Based Locomotion on HyQ Robot

Urbain

Barasuol

Semini

et al. 2020

2020 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The main contribution of the paper is investigating the advantages of using a learning control module during the optimization of the locomotion patterns for a quadruped robot rather than employ it when the optimal locomotion patterns have already been found (as it is usually done in already existing approaches, Urbain et al, 2018; Vandesompele et al, 2019). This idea comes from nature since evolution has always been acting on plastic and learning systems.…”

Section: Discussionmentioning

confidence: 99%

“…Robots might evolve to match the specificities of the simulation, which differ from the real-world constraints. To prevent this problem, many approaches can be possible, such as adding independent noise to the values of the sensors or changing the robot dynamic model and its interaction with the environment (Nolfi et al, 2000; Vandesompele et al, 2019). In comparison to the classical approach where this simulation variability is added during the evolutionary optimization, in this research, the possibility of overcoming the reality gap and the transferability of the approach is demonstrated afterwards.…”

Section: Introductionmentioning

confidence: 99%

Combining Evolutionary and Adaptive Control Strategies for Quadruped Robotic Locomotion

et al. 2019

Self Cite

View full text Add to dashboard Cite

In traditional robotics, model-based controllers are usually needed in order to bring a robotic plant to the next desired state, but they present critical issues when the dimensionality of the control problem increases and disturbances from the external environment affect the system behavior, in particular during locomotion tasks. It is generally accepted that the motion control of quadruped animals is performed by neural circuits located in the spinal cord that act as a Central Pattern Generator and can generate appropriate locomotion patterns. This is thought to be the result of evolutionary processes that have optimized this network. On top of this, fine motor control is learned during the lifetime of the animal thanks to the plastic connections of the cerebellum that provide descending corrective inputs. This research aims at understanding and identifying the possible advantages of using learning during an evolution-inspired optimization for finding the best locomotion patterns in a robotic locomotion task. Accordingly, we propose a comparative study between two bio-inspired control architectures for quadruped legged robots where learning takes place either during the evolutionary search or only after that. The evolutionary process is carried out in a simulated environment, on a quadruped legged robot. To verify the possibility of overcoming the reality gap, the performance of both systems has been analyzed by changing the robot dynamics and its interaction with the external environment. Results show better performance metrics for the robotic agent whose locomotion method has been discovered by applying the adaptive module during the evolutionary exploration for the locomotion trajectories. Even when the motion dynamics and the interaction with the environment is altered, the locomotion patterns found on the learning robotic system are more stable, both in the joint and in the task space.

show abstract

“…The continuation of this work has three main directions: improve the controller, incorporate visual information and integrate arm motion. To improve the controller, the network parameters can be pre-trained with domain randomization in simulation as in [39], [19] to fine tune the adaptive controller. To increase the performance of the controller the SNN can be executed with neuromorphic hardware such as SpiNNaker [40] or Loihi [41] to take advantage of the efficient real time execution of SNN [42].Neuromorphic hardware can also be used to directly use the spike activity of the network to control the motors [43] or by using event-based touch sensors [44] to further exploit the characteristics of SNN in terms of energy consumption and information processing [4].…”

Section: Parameters Finger Primitivesmentioning

confidence: 99%

Soft-Grasping With an Anthropomorphic Robotic Hand Using Spiking Neurons

Tieck

Secker

Kaiser

et al. 2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Evolution gave humans advanced grasping capabilities combining an adaptive hand with efficient control. Grasping motions can quickly be adapted if the object moves or deforms. Soft-grasping with an anthropomorphic hand is a great capability for robots interacting with objects shaped for humans. Nevertheless, most robotic applications use vacuum, 2-finger or custom made grippers. We present a biologically inspired spiking neural network (SNN) for soft-grasping to control a robotic hand. Two control loops are combined, one from motor primitives and one from a compliant controller activated by a reflex. The finger primitives represent synergies between joints and hand primitives represent different affordances. Contact is detected with a mechanism based on inter-neuron circuits in the spinal cord to trigger reflexes. A Schunk SVH 5-finger hand was used to grasp objects with different shapes, stiffness and sizes. The SNN adapted the grasping motions without knowing the exact properties of the objects. The compliant controller with online learning proved to be sensitive, allowing even the grasping of balloons. In contrast to deep learning approaches, our SNN requires one example of each grasping motion to train the primitives. Computation of the inverse kinematics or complex contact point planning is not required. This approach simplifies the control and can be used on different robots providing similar adaptive features as a human hand. A physical imitation of a biological system implemented completely with SNN and a robotic hand can provide new insights into grasping mechanisms.

show abstract

Body Randomization Reduces the Sim-to-Real Gap for Compliant Quadruped Locomotion

Cited by 10 publications

References 25 publications

Stance Control Inspired by Cerebellum Stabilizes Reflex-Based Locomotion on HyQ Robot

Stance Control Inspired by Cerebellum Stabilizes Reflex-Based Locomotion on HyQ Robot

Combining Evolutionary and Adaptive Control Strategies for Quadruped Robotic Locomotion

Soft-Grasping With an Anthropomorphic Robotic Hand Using Spiking Neurons

Contact Info

Product

Resources

About