English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Using joint actuators to drive the skeletal movements is a common practice incharacter animation, but the resultant torque patterns are often unnatural orinfeasible for real humans to achieve. On the other hand, physiologically-basedmodels explicitly simulate muscles and tendons and thus produce more human-likemovements and torque patterns. This paper introduces a technique to transforman optimal control problem formulated in the muscle-actuation space to anequivalent problem in the joint-actuation space, such that the solutions toboth problems have the same optimal value. By solving the equivalent problem inthe joint-actuation space, we can generate human-like motions comparable tothose generated by musculotendon models, while retaining the benefit of simplemodeling and fast computation offered by joint-actuation models. Our methodtransforms constant bounds on muscle activations to nonlinear, state-dependenttorque limits in the joint-actuation space. In addition, the metabolic energyfunction on muscle activations is transformed to a nonlinear function of jointtorques, joint configuration and joint velocity. Our technique can also benefitpolicy optimization using deep reinforcement learning approach, by providing amore anatomically realistic action space for the agent to explore during thelearning process. We take the advantage of the physiologically-based simulator,OpenSim, to provide training data for learning the torque limits and themetabolic energy function. Once trained, the same torque limits and the energyfunction can be applied to drastically different motor tasks formulated aseither trajectory optimization or policy learning. Codebase:https://github.com/jyf588/lrle and https://github.com/jyf588/lrle-rl-examples

Synthesis of Biologically Realistic Human Motion Using Joint Torque Actuation