Robust physics-based locomotion using low-dimensional planning

By Igor Mordatch, Martin de Lasa, Aaron Hertzmann. 2010

205 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering, Reinforcement Learning

How researchers see this paper

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

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Reinforcement Learning

Citations in the corpus

Emergence of Locomotion Behaviours in Rich Environments (2017, background): “For instance, [24] show sophisticated skill sequencing for maneuvering obstacles on a parametric terrain, while [25, 26, 27] demonstrate how terrain adaptive behaviors or other skilled movements can emerge as the result of optimization problems.”
Combining model-based policy search with online model learning for control of physical humanoids (2016, background): “Some control approaches break up the control problem into a high-level and low-level components, as we do [3], [17], [22], but again”
Gait and Trajectory Optimization for Legged Systems Through Phase-Based End-Effector Parameterization (2018, result): “Many other variations of using these simplified models to generate impressive results have been shown by [10]–[17].”
Optimizing Locomotion Controllers Using Biologically-Based Actuators and Objectives (2012, methodology): “…Vol. 31, No. 4, Article 25, Publication Date: July 2012 ber of projects have since focused on expanding the controller repertoire for simulated bipeds [Jain et al. 2009; Coros et al. 2010; de Lasa et al. 2010] and on locomotion in complex environments [Mordatch et al. 2010; Wu and Popović 2010].”
Learning locomotion skills using DeepRL: does the choice of action space matter? (2016, background): “The resulting motions can be parameterized by specifying high-level objectives such as footstep positions and center of mass trajectories [Mordatch et al. 2010].”
Learning human behaviors from motion capture by adversarial imitation (2017, methodology): “Representative methods for producing terrestrial locomotion have made use of specialized gait controllers (for a quadruped [11]; for a biped [12]) or systems explicitly producing foot placements [13].”
DeepLoco (2017, background): “Planning for physics-based characters is often achieved with the help of abstract dynamic models in low-dimensional spaces [Mordatch et al. 2010; Ye and Liu 2010].”