Terrain-adaptive bipedal locomotion control

By Jia-Chi Wu, Zoran Popovic. 2010

107 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.”
Simulation-based design of dynamic controllers for humanoid balancing (2016, methodology): “CMA is a stochastic sampling-based optimization algorithm, which has been successfully applied to search for control parameters when the problem domain is highly discontinuous [30]–[32].”
Learning symmetric and low-energy locomotion (2018, background): “…states that are increasingly farther from a goal state [Florensa et al. 2017 Similarly, Wu et al. used helper forces to assist in optimizing a set of locomotion controllers, which are then used by a foot-step planner to controller the character to walk on uneven terrains [Wu and Popović 2010].”
DeepLoco (2017, background): “Wu and Popović [2010] proposed a hierarchical framework that incorporates a footstep planner and model-predictive control for bipedal locomotion across irregular terrain.”
Infinite-Horizon Model Predictive Control for Periodic Tasks with Contacts (2011, methodology): “Popović and Wu [27] presented a method where offline optimization (through Evolutionary Computation) was complemented by Quadratic Programming during runtime to generate robust locomotion behavior from motion-capture data.”
Optimizing Locomotion Controllers Using Biologically-Based Actuators and Objectives (2012, background): “One likely cause of these differences is the control force generation mechanism.”
Iterative Training of Dynamic Skills Inspired by Human Coaching Techniques (2014, background): “For example, a human coach typically uses high-level instructions, such as “extend the legs” or “push the ground”, rather than specific descriptions of joint angles.”