COCoMoPL: A Novel Approach for Humanoid Walking Generation Combining Optimal Control, Movement Primitives and Learning and its Transfer to the Real Robot HRP-2

Clever, Debora; Harant, Monika; Mombaur, Katja; Naveau, Maximilien; Stasse, Olivier; Endres, Dominik

doi:10.1109/lra.2017.2657000

Cited by 31 publications

(17 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Achieving transferable solutions is the central focus of many recent works in robotics, [15], [16], [17]. For example, optimal control and movement primitives are combined in [17] to find solutions which can be easily deployed on the real robot. However, they strongly rely on the accuracy of the simulated model to ensure the transferability of solutions.…”

Section: A Related Workmentioning

confidence: 99%

Learning Robust Task Priorities and Gains for Control of Redundant Robots

Penco

Hoffman

Modugno

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Generating complex movements in redundant robots like humanoids is usually done by means of multitask controllers based on quadratic programming, where a multitude of tasks is organized according to strict or soft priorities. Time-consuming tuning and expertise are required to choose suitable task priorities, and to optimize their gains. Here, we automatically learn the controller configuration (soft and strict task priorities and Convergence Gains), looking for solutions that track a variety of desired task trajectories efficiently while preserving the robot's balance. We use multiobjective optimization to compare and choose among Paretooptimal solutions that represent a trade-off of performance and robustness and can be transferred onto the real robot. We experimentally validate our method by learning a control configuration for the iCub humanoid, to perform different whole-body tasks, such as picking up objects, reaching and opening doors.

show abstract

Section: A Related Workmentioning

confidence: 99%

Learning Robust Task Priorities and Gains for Control of Redundant Robots

Penco

Hoffman

Modugno

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Mukovskiy et al [33] learned movement primitives from human motion captures, and combined them with model predictive control and planning to generate whole body motions on the HRP-2 robot. Clever et al [34] used motion generated in simulation with a QP-based WBC to learn motion primitives, which can then be employed instead of the QP-based WBC while having a lower computational cost. Overall, these papers use learning in simulation only and aim at making whole body control more reliable and less computationally demanding.…”

Section: B Learning With Humanoid Robotsmentioning

confidence: 99%

Trial-and-error learning of repulsors for humanoid QP-based whole-body control

Spitz

Bouyarmane²,

Ivaldi

et al. 2017

2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)

View full text Add to dashboard Cite

Abstract-Whole body controllers based on quadratic programming allow humanoid robots to achieve complex motions. However, they rely on the assumption that the model perfectly captures the dynamics of the robot and its environment, whereas even the most accurate models are never perfect. In this paper, we introduce a trial-and-error learning algorithm that allows whole-body controllers to operate in spite of inaccurate models, without needing to update these models. The main idea is to encourage the controller to perform the task differently after each trial by introducing repulsors in the quadratic program cost function. We demonstrate our algorithm on (1) a simple 2D case and (2) a simulated iCub robot for which the model used by the controller and the one used in simulation do not match.

show abstract

“…We therefore investigate whether MPs are candidates for such a shared representation. Their suitability for complex movement production has already been demonstrated (Clever et al 2017;Giszter 2015;Ijspeert et al 2013;, we would like to determine how close human perceptual performance is to an "ideal observer" comprised of MPs.…”

Section: Introductionmentioning

confidence: 99%

Untitled

2019

ACM Trans. Appl. Percept.

View full text Add to dashboard Cite

We compared the perceptual validity of human avatar walking animations driven by six different representations of human movement using a graphics Turing test. All six representations are based on movement primitives (MPs), which are predictive models of full-body movement that differ in their complexity and prediction mechanism. Assuming that humans are experts at perceiving biological movement from noisy sensory signals, it follows that these percepts should be describable by a suitably constructed Bayesian ideal observer model. We build such models from MPs and investigate if the perceived naturalness of human animations are predictable from approximate Bayesian model scores of the MPs. We found that certain MP-based representations are capable of producing movements that are perceptually indistinguishable from natural movements. Furthermore, approximate Bayesian model scores of these representations can be used to predict perceived naturalness. In particular, we could show that movement dynamics are more important for perceived naturalness of human animations than single frame poses. This indicates that perception of human animations is highly sensitive to their temporal coherence. More generally, our results add evidence for a shared MP-representation of action and perception. Even though the motivation of our work is primarily drawn from neuroscience, we expect that our results will be applicable in virtual and augmented reality settings, when perceptually plausible human avatar movements are required.

show abstract

COCoMoPL: A Novel Approach for Humanoid Walking Generation Combining Optimal Control, Movement Primitives and Learning and its Transfer to the Real Robot HRP-2

Cited by 31 publications

References 22 publications

Learning Robust Task Priorities and Gains for Control of Redundant Robots

Learning Robust Task Priorities and Gains for Control of Redundant Robots

Trial-and-error learning of repulsors for humanoid QP-based whole-body control

Untitled

Contact Info

Product

Resources

About