Related Experiment Video
Updated: Jan 24, 2026
08:24
Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
Published on: August 30, 2016
10.7K
Implementation of Deep Deterministic Policy Gradients for Controlling Dynamic Bipedal Walking.
Chujun Liu1, Andrew G Lonsberry2, Mark J Nandor3
1Department of Mechanical and Aerospace Engineering, Case Western Reserve University, Cleveland, OH 44106, USA. cxl936@case.edu.
Biomimetics (Basel, Switzerland)
|May 21, 2019
Summary
A novel deep deterministic policy gradient (DDPG) controller enables stable bipedal walking in simulation. This advanced control system maintains balance against disturbances and adapts to varying human sizes.
Area of Science:
- Robotics
- Artificial Intelligence
- Biomechanics
Background:
- Developing stable bipedal locomotion is a key challenge in robotics.
- Simulations are crucial for testing and refining control systems before physical implementation.
Purpose of the Study:
- To develop and evaluate a robust control system for sagittal plane bipedal walking.
- To enhance stability against external disturbances and variations in robot size.
Main Methods:
- A deep deterministic policy gradient (DDPG) neural network was trained in the GAZEBO physics simulator.
- A distributed control system with optimized state variables was employed.
- Additional controllers were implemented for hip and ankle joints during specific walking phases.
Main Results:
- The simulated biped achieved stable walking at approximately 1 m/s.
- The system maintained stability against forward (30 kg·m/s) and rearward (40 kg·m/s) impulses.
- Stable locomotion was demonstrated with added loads (10 kg backpack, 25 kg front pack).
- The controller successfully stabilized biped models ranging from 1.4 to 2.3 m tall without modifications.
Conclusions:
- The DDPG-based control system provides robust and adaptable bipedal walking capabilities.
- The developed controller shows significant potential for real-world humanoid robot applications.
- The system's ability to generalize across different model heights is a key advancement.
Related Concept Videos
01:26What is an Electrochemical Gradient?
127.5K
Adenosine triphosphate, or ATP, is considered the primary energy source in cells. However, energy can also be stored in the electrochemical gradient of an ion across the plasma membrane, which is determined by two factors: its chemical and electrical gradients.
The chemical gradient relies on differences in the abundance of a substance on the outside versus the inside of a cell and flows from areas of high to low ion concentration. In contrast, the electrical gradient revolves around an...
The chemical gradient relies on differences in the abundance of a substance on the outside versus the inside of a cell and flows from areas of high to low ion concentration. In contrast, the electrical gradient revolves around an...
127.5K
01:15Nursing Implementation
6.0K
Implementation is the execution of the nursing care plan developed during the planning phase.
The five steps to implementing effective nursing care include reassessing the patient, reviewing and revising the existing nursing care plan, organizing the resources and care delivery, anticipating and preventing complications, and implementing nursing interventions.
The five steps to implementing effective nursing care include reassessing the patient, reviewing and revising the existing nursing care plan, organizing the resources and care delivery, anticipating and preventing complications, and implementing nursing interventions.
6.0K
01:27Energy Line and Hydraulic Gradient Line
2.1K
Based on Bernoulli's equation, the energy line (EL) and hydraulic grade line (HGL) provide graphical representations of energy distribution in a fluid flow system. For steady, incompressible, inviscid flows, Bernoulli's equation is expressed as:
2.1K
01:14Gradient and Del Operator
4.4K
In mathematics and physics, the gradient and del operator are fundamental concepts used to describe the behavior of functions and fields in space. The gradient is a mathematical operator that gives both the magnitude and direction of the maximum spatial rate of change. Consider a person standing on a mountain. The slope of the mountain at any given point is not defined unless it is quantified in a particular direction. For this reason, a "directional derivative" is defined, which is a vector...
4.4K
02:20Dynamic Equilibrium
62.0K
A reversible chemical reaction represents a chemical process that proceeds in both forward (left to right) and reverse (right to left) directions. When the rates of the forward and reverse reactions are equal, the concentrations of the reactant and product species remain constant over time and the system is at equilibrium. A special double arrow is used to emphasize the reversible nature of the reaction. The relative concentrations of reactants and products in equilibrium systems vary greatly;...
62.0K
01:21Electrochemical Gradient and Channel Proteins: An Overview
4.4K
An electrochemical gradient is a fundamental concept in biology and chemistry. It regulates the movement of ions across cell membranes. This movement is influenced by two factors:
The electrical gradient: The electrical gradient across cell membranes refers to the difference in electric charge between the inside and outside of a cell. This difference drives the movement of ions towards or away from the cells. For instance, if the inside of the cell is more negatively charged relative to...
The electrical gradient: The electrical gradient across cell membranes refers to the difference in electric charge between the inside and outside of a cell. This difference drives the movement of ions towards or away from the cells. For instance, if the inside of the cell is more negatively charged relative to...
4.4K