28 citations · 51 across the 8 of their papers we have counts for
8 papers
Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models
Pierre Schumacher, Thomas Geijtenbeek, Vittorio Caggiano +4
Humans excel at robust bipedal walking in complex natural environments. In each step, they adequately tune the interaction of biomechanical muscle dynamics and neuronal signals to…
Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks
Isabell Wochner, Pierre Schumacher, Georg Martius +3
Humans are able to outperform robots in terms of robustness, versatility, and learning of new tasks in a wide variety of movements. We hypothesize that highly nonlinear muscle dyna…
DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
Pierre Schumacher, Daniel Häufle, Dieter Büchler +2
Muscle-actuated organisms are capable of learning an unparalleled diversity of dexterous movements despite their vast amount of muscles. Reinforcement learning (RL) on large muscul…
Muscle pre-stimulation tunes viscous-like perturbation rejection in legged hopping
Fabio Izzi, An Mo, Syn Schmitt +2
Muscle fibres possess unique visco-elastic properties, capable of generating a stabilising zero-delay response to unexpected perturbations. This instantaneous response -- termed "p…
Biomechanical surrogate modelling using stabilized vectorial greedy kernel methods
Bernard Haasdonk, Tizian Wenzel, Gabriele Santin +1
Greedy kernel approximation algorithms are successful techniques for sparse and accurate data-based modelling and function approximation. Based on a recent idea of stabilization of…
External control strategies for self-propelled particles: optimizing navigational efficiency in the presence of limited resources
Daniel F B Haeufle, Tobias Bäuerle, Jakob Steiner +3
We experimentally and numerically study the dependence of different navigation strategies regarding the effectivity of an active particle to reach a predefined target area. As the…
Evaluating Morphological Computation in Muscle and DC-motor Driven Models of Human Hopping
Keyan Ghazi-Zahedi, Daniel F. B. Haeufle, Guido Montufar +2
In the context of embodied artificial intelligence, morphological computation refers to processes which are conducted by the body (and environment) that otherwise would have to be…
Comparing different muscle activation dynamics using sensitivity analysis
Robert Rockenfeller, Michael Guenther, Syn Schmitt +1
In this paper, we mathematically compared two models of mammalian striated muscle activation dynamics proposed by Hatze and Zajac. Both models are representative of a broad variety…