Neuro Adaptive Methods for Biped Walking

Using tools of artificial intelligence, mainly artificial neural networks, this research focusses on development of an intelligent walking engine for humanoid robots. This engine uses dynamic neural networks with intelligent feedback for gait generation, a modified Zhang neural network for a singularity-robust inverse kinematics solver, and feed-forward neural networks for neuro-adaptive control. The Atlas humanoid robot model in simulation is used to test and verify the capabilities of the neuro-dynamic walking engine. We have been successful in demonstrating that the engine is capable of generating ZMP stable walking gaits and executing them using the Atlas robot in simulation.

Dissertation: Atmeh, Ghassan, "Novel Neuro Dynamic Methods for Robotic Planning and Control", December 2015

YouTube Link: Walking demonstration (Open in a new tab/window if the video doesn't play here)

Biped Model (DRCSim)

Pictures of the Biped Robot and Walking Snapshots

  • ATLAS Rendering
  • ATLAS Degrees of Freedom
  • Dynamic Neural Network based Trajectory Planner
  • Neuro-Adaptive Control System
  • Robot walking implemented in ROS
  • Relevant Publications


    Back to main research page.