Learning optimal gait parameters and impedance profiles for legged locomotion

Heijmink, Elco; Radulescu, Andreea; Ponton, Brahayam; Barasuol, Victor; Caldwell, Darwin G.; Semini, Claudio

doi:10.1109/humanoids.2017.8246895

Cited by 11 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We are also interested in using sampling-based approaches to make probabilistic estimates. There has been keen interest recently in applying machine learning techniques to tune control parameters directly in hardware [10], [74]- [76]. In these situations, safe exploration of the state-action space is particularly important.…”

Section: Discussionmentioning

confidence: 99%

“…Recently, there have been attempts to combine these approaches with machine learning to improve robustness and adaptability [10]- [12]; however, it is notoriously difficult to apply learning directly in hardware. We are motivated by the question 'how should a legged robot be designed, such that it is easier to apply model-free learning directly in hardware?'.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Beyond Basins of Attraction: Quantifying Robustness of Natural Dynamics

Heim

Spröwitz

2019

IEEE Trans. Robot.

View full text Add to dashboard Cite

Properly designing a system to exhibit favorable natural dynamics can greatly simplify designing or learning the control policy. However, it is still unclear what constitutes favorable natural dynamics and how to quantify its effect. Most studies of simple walking and running models have focused on the basins of attraction of passive limit-cycles and the notion of self-stability. We instead emphasize the importance of stepping beyond basins of attraction. We show an approach based on viability theory to quantify robust sets in state-action space. These sets are valid for the family of all robust control policies, which allows us to quantify the robustness inherent to the natural dynamics before designing the control policy or specifying a control objective. We illustrate our formulation using spring-mass models, simple low dimensional models of running systems. We then show an example application by optimizing robustness of a simulated planar monoped, using a gradient-free optimization scheme. Both case studies result in a nonlinear effective stiffness providing more robustness.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Beyond Basins of Attraction: Quantifying Robustness of Natural Dynamics

Heim

Spröwitz

2019

IEEE Trans. Robot.

View full text Add to dashboard Cite

show abstract

“…Because only the real hardware was used for all experiments, we expect a considerable wear-off of the robot. On the other hand, Heijmink et al [12] proposed a method to learn gait parameters and impedance profiles in simulation for a quadruped robot. This was accomplished by using the PI 2 algorithm with a cost function consisting of speed tracking, energy consumption, joint limits, and torques.…”

Section: Related Workmentioning

confidence: 99%

Combining Simulations and Real-Robot Experiments for Bayesian Optimization of Bipedal Gait Stabilization

Rodríguez

Brandenburger

Behnke

2019

RoboCup 2018: Robot World Cup XXII

View full text Add to dashboard Cite

Walking controllers often require parametrization which must be tuned according to some cost function. To estimate these parameters, simulations can be performed which are cheap but do not fully represent reality. Real-robot experiments, on the other hand, are more expensive and lead to hardware wear-off. In this paper, we propose an approach for combining simulations and real experiments to learn gait stabilization parameters. We use a Bayesian optimization method which selects the most informative points in parameter space to evaluate based on the entropy of the cost function to optimize. Experiments with the igus Humanoid Open Platform demonstrate the effectiveness of our approach. * Both authors contributed equally.

show abstract

“…Many methods have been used to improve energy efficiency, such as compliant actuation design [2], [3], human walking learning [4], and gait parameters optimization [5], [6]. Generally, optimization-based approaches first evaluate a set of nominal step parameters and then update them following the gradient that minimizes the energetic cost of a desired travel distance.…”

Section: Introductionmentioning

confidence: 99%

Energy-Efficient Bipedal Gait Pattern Generation via CoM Acceleration Optimization

Ding

Zhou

Xiao

2018

2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)

View full text Add to dashboard Cite

Energy consumption for bipedal walking plays a central role for a humanoid robot with limited battery capacity. Studies have revealed that exploiting the allowable Zero Moment Point region (AZR) and Center of Mass (CoM) height variation (CoMHV) are strategies capable of improving energy performance. In general, energetic cost is evaluated by integrating the electric power of multi joints. However, this Joint-Power-based Index requires computing joint torques and velocities in advance, which usually requires time-consuming iterative procedures, especially for multi-joints robots. In this work, we propose a CoM-Acceleration-based Optimal Index (CAOI) to synthesize an energetically efficient CoM trajectory. The proposed method is based on the Linear Inverted Pendulum Model, whose energetic cost can be easily measured by the input energy required for driving the point mass to track a reference trajectory. We characterize the CoM motion for a single walking cycle and define its energetic cost as Unit Energy Consumption. Based on the CAOI, an analytic solution for CoM trajectory generation is provided. Hardware experiments demonstrated the computational efficiency of the proposed approach and the energetic benefits of exploiting AZR and CoMHV strategies.

show abstract

Learning optimal gait parameters and impedance profiles for legged locomotion

Cited by 11 publications

References 17 publications

Beyond Basins of Attraction: Quantifying Robustness of Natural Dynamics

Beyond Basins of Attraction: Quantifying Robustness of Natural Dynamics

Combining Simulations and Real-Robot Experiments for Bayesian Optimization of Bipedal Gait Stabilization

Energy-Efficient Bipedal Gait Pattern Generation via CoM Acceleration Optimization

Contact Info

Product

Resources

About