Synthesis of biologically realistic human motion using joint torque actuation

Abstract

Using joint actuators to drive the skeletal movements is a common practice in character animation, but the resultant torque patterns are often unnatural or infeasible for real humans to achieve. On the other hand, physiologicallybased models explicitly simulate muscles and tendons and thus produce more human-like movements and torque patterns. This paper introduces a technique to transform an optimal control problem formulated in the muscleactuation space to an equivalent problem in the joint-actuation space, such that the solutions to both problems have the same optimal value. By solving the equivalent problem in the joint-actuation space, we can generate humanlike motions comparable to those generated by musculotendon models, while retaining the benefit of simple modeling and fast computation offered by joint-actuation models. Our method transforms constant bounds on muscle activations to nonlinear, state-dependent torque limits in the joint-actuation space. In addition, the metabolic energy function on muscle activations is transformed to a nonlinear function of joint torques, joint configuration and joint velocity. Our technique can also benefit policy optimization using deep reinforcement learning approach, by providing a more anatomically realistic action space for the agent to explore during the learning process. We take the advantage of the physiologically-based simulator, OpenSim, to provide training data for learning the torque limits and the metabolic energy function. Once trained, the same torque limits and the energy function can be applied to drastically different motor tasks formulated as either trajectory optimization or policy learning.

ALLSTEPS: Curriculum‐driven Learning of Stepping Stone Skills

“…[PALvdP18, MAP * 18]. In our experiments, we find, as in [JVWDGL19], that natural motion is easier to achieve with the use of realistic torque limits.…”

Efficient trajectory optimization for curved running using a 3D musculoskeletal model with implicit dynamics

“…Previously, it was shown that using algorithmic derivatives is faster than finite differences which are used by OpenSim 43 . Machine learning approaches were recently investigated in the field of computer graphics to speed up musculoskeletal simulation 44 , 45 . Jiang et al 44 learned a mapping from muscle-actuation space to joint-actuation space which would have to be retrained if model parameters are changing.…”

“…Machine learning approaches were recently investigated in the field of computer graphics to speed up musculoskeletal simulation 44 , 45 . Jiang et al 44 learned a mapping from muscle-actuation space to joint-actuation space which would have to be retrained if model parameters are changing. Lee et al 45 used a two-stage deep reinforcement learning approach to simulate a full-body 3D musculoskeletal model.…”

Characterizing Motor Control of Mastication With Soft Actor-Critic

“…In biomechanics, some RL-based solutions have been introduced for the motor control tasks either via muscle activations (Abdi et al, 2019b) or joint activations (Clegg et al, 2018). In human locomotion, most works have focused on arm movement (Golkhou et al, 2005;Jagodnik et al, 2016) and gait control (Peng et al, 2017;Kidziński et al, 2018;Jiang et al, 2019). Recent interdisciplinary collaborations have helped to bridge the gap between reinforcement learning and motor control in biomechanics using the OpenSim and ArtiSynth modeling environments (Kidziński et al, 2018;Abdi et al, 2019a).…”