Composable controllers for physics-based character animation

By Petros Faloutsos, Michiel van de Panne, Demetri Terzopoulos. International Conference on Computer Graphics and Interactive Techniques, 2001

397 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/c9a54c513552c88ea815232a4f377662c8e24ad8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Human-Computer Interaction

Citations in the corpus

SmartBody: behavior realization for embodied conversational agents (2008, neutral): “An approach based on selecting individual controllers for guiding a simulated character under dynamics has been proposed by Faloutsos et al [25], however it does not address our scheduling and hierarchical needs.”
Linear Bellman combination for control of character animation (2009, background): “Controllers can also be sequenced to create composite controllers that achieve new tasks [Burridge et al. 1999; Faloutsos et al. 2001].”
Interactive Character Animation Using Simulated Physics: A State‐of‐the‐Art Review (2012, background): “Faloutsos et al. [FvdPT01, Fal01] demonstrate controllers for sitting, falling, rolling over and getting back up.”
Dynamics filter - concept and implementation of online motion generator for human figures (2000, background): “[16] is an attempt to solve this problem.”
Style translation for human motion (2005, methodology): “Furthermore, the wealth of available control techniques indicates that our translation model could also be used in conjunction with robot controllers [Faloutsos et al. 2001].”
Hierarchical visuomotor control of humanoids (2018, background): “This ambition can be traced to the virtual stuntman (Faloutsos et al., 2001b;a) and has been advanced markedly in the work of Liu (Liu et al., 2012).”
Learning from observation using primitives (2001, methodology): “[40] present a framework for controlling animated characters using primitives that are pose-controllers.”
MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies (2019, background): “Standard hierarchical models [10, 41] often activate only a single primitive at each timestep, which can limit the diversity of behaviors that can be produced by the agent.”
Catch & Carry (2019, methodology): “…that we focus on here, employs physics-based simulation to control a virtual body and produce realistic movement [e.g. Van de Panne and Fiume 1993; Faloutsos et al. 2001], often also using motion capture as a reference for the controller [e.g. Yin et al. 2007; Liu et al. 2010; Peng et al. 2018].”
Envisioning the qualitative effects of robot manipulation actions using simulation-based projections (2017, background): “But other ﬁelds also recognize simulators as valuable tools and utilize them, e.g., for character animation (Faloutsos et al., 2001) and motion tracking (Vondrak et al., 2008).”