Neural Gaits: Learning Bipedal Locomotion via Control Barrier Functions and Zero Dynamics Policies

  title={Neural Gaits: Learning Bipedal Locomotion via Control Barrier Functions and Zero Dynamics Policies},
  author={Ivan Dario Jimenez Rodriguez and Noel Csomay-Shanklin and Yisong Yue and A. Ames},
This work presents Neural Gaits, a method for learning dynamic walking gaits through the enforce-ment of set invariance that can be refined episodically using experimental data from the robot. We frame walking as a set invariance problem enforceable via control barrier functions (CBFs) defined on the reduced-order dynamics quantifying the underactuated component of the robot: the zero dynamics. Our approach contains two learning modules: one for learning a policy that satisfies the CBF condition… 

Figures and Tables from this paper


Learning quadrupedal locomotion over challenging terrain
The presented work indicates that robust locomotion in natural environments can be achieved by training in simple domains.
Robust Feedback Motion Policy Design Using Reinforcement Learning on a 3D Digit Bipedal Robot
In this paper, a hierarchical and robust framework for learning bipedal locomotion is presented and successfully implemented on the 3D biped robot Digit built by Agility Robotics. We propose a
Episodic Learning for Safe Bipedal Locomotion with Control Barrier Functions and Projection-to-State Safety
The notion of projection-to-state safety paired with a machine learning framework is utilized in an attempt to learn the model uncertainty as it affects the barrier functions in the setting of bipedal locomotion.
Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition
A reward-specification framework based on composing simple probabilistic periodic costs on basic forces and velocities is proposed and instantiate this framework to define a parametric reward function with intuitive settings for all common bipedal gaits - standing, walking, hopping, running, and skipping.
Dynamic Locomotion in the MIT Cheetah 3 Through Convex Model-Predictive Control
This paper presents an implementation of model predictive control (MPC) to determine ground reaction forces for a torque-controlled quadruped robot, capable of robust locomotion at a variety of speeds.
Control barrier function based quadratic programs with application to bipedal robotic walking
The end result is the generation of stable walking satisfying physical realizability constraints for a model of the bipedal robot AMBER2.
MPC for Humanoid Gait Generation: Stability and Feasibility
An intrinsically stable Model Predictive Control framework for humanoid gait generation that incorporates a stability constraint in the formulation is presented and it is proved that recursive feasibility guarantees stability of the CoM/ZMP dynamics.
Optimization-based locomotion planning, estimation, and control design for the atlas humanoid robot
This paper describes a collection of optimization algorithms for achieving dynamic planning, control, and state estimation for a bipedal robot designed to operate reliably in complex environments and presents a state estimator formulation that permits highly precise execution of extended walking plans over non-flat terrain.
Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions
A novel reinforcement learning framework is proposed which learns the model uncertainty present in the CBF and CLF constraints, as well as other control-affine dynamic constraints in the quadratic program.