Generalizing locomotion style to new animals with inverse optimal regression

Wampler, Kevin; Popović, Zoran

doi:10.1145/2601097.2601192

Cited by 41 publications

(19 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In computer animation, trajectory optimization, or spacetime constraints [Witkin and Kass 1988], provides a general mathematical tool for motion synthesis [Fang and Pollard 2003;Liu and Popović 2002;Mordatch et al 2012;Popović and Witkin 1999;Rose et al 1996;Safonova et al 2004], character retargeting [Gleicher 1998;Wampler et al 2014], or style editing [Kass and Anderson 2008;Liu et al 2005;Min et al 2010]. Using the same optimization framework, this paper shows that by replacing the conventional energy term and the box torque limits, our method can reduce the need for parameter tuning and improve the quality of the motion.…”

Section: Related Workmentioning

confidence: 99%

Synthesis of biologically realistic human motion using joint torque actuation

et al. 2019

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

Synthesis of biologically realistic human motion using joint torque actuation

et al. 2019

View full text Add to dashboard Cite

show abstract

“…An alternative approach to obtain natural character motions is to incorporate motion data such as videos [Wampler et al 2014] or motion capture data [da Silva et al 2008;Lee et al 2010Lee et al , 2014Liu et al 2005;Muico et al 2009;Sok et al 2007;Ye and Liu 2010]. Despite the high fidelity motion this approach can generate, the requirement of motion data does not allow its application to arbitrary character morphologies as well as generalization to novel control tasks.…”

Section: Related Work 21 Physically-based Character Controlmentioning

confidence: 99%

Learning symmetric and low-energy locomotion

2018

View full text Add to dashboard Cite

Fig. 1. Locomotion Controller trained for different creatures. (a) Biped walking. (b) Quadruped galloping. (c) Hexapod Walking. (d) Humanoid running.Learning locomotion skills is a challenging problem. To generate realistic and smooth locomotion, existing methods use motion capture, finite state machines or morphology-specific knowledge to guide the motion generation algorithms. Deep reinforcement learning (DRL) is a promising approach for the automatic creation of locomotion control. Indeed, a standard benchmark for DRL is to automatically create a running controller for a biped character from a simple reward function [Duan et al. 2016]. Although several different DRL algorithms can successfully create a running controller, the resulting motions usually look nothing like a real runner. This paper takes a minimalist learning approach to the locomotion problem, without the use of motion examples, finite state machines, or morphology-specific knowledge. We introduce two modifications to the DRL approach that, when used together, produce locomotion behaviors that are symmetric, low-energy, and much closer to that of a real person. First, we introduce a new term to the loss function (not the reward function) that encourages symmetric actions. Second, we introduce a new curriculum learning method that provides modulated physical assistance to help the character with left/right balance and forward movement. The algorithm automatically computes appropriate assistance to the character and gradually relaxes this assistance, so that eventually the character learns to move entirely without help. Because our method does not make use of motion capture data, it can be applied to a variety of character morphologies. We demonstrate locomotion controllers for the lower half of a biped, a full humanoid, a quadruped, and a hexapod. Our results show that learned policies are able to produce symmetric, low-energy gaits. In addition,

show abstract

“…Abdul-Massih et al [28] explored this path and worked on style transfer applied to morphologically different characters: human, T-Rex, dragon, three-headed creature and snake. Note that Wampler [77] focused only on animals.…”

Section: Analysis Of Stylistic Motion Generation Methodsmentioning

confidence: 99%