Static and Dynamic Path Planning of Humanoids using an Advanced Regression Controller

摘要

With an ability to mimic the human behaviour, humanoid robots have become a topic of major interest among research fellows dealing with robotic investigation. The current work is focussed on the design of a novel navigational controller based on the logic of the regression analysis to be used in the path planning and navigation of humanoid robots. In the current investigation, static and dynamic path planning of humanoid NAOs are encountered. The static path planning represents a single NAO navigating through random static obstacles. The dynamic path planning represents multiple humanoid NAOs navigating through random static obstacles and acting as dynamic obstacles for each other. A Petri-Net controller is designed to avoid the collision among the multiple NAOs in dynamic path planning. To reduce the path length and time travel and to provide the shortest possible path, an advanced regression controller is implemented in the NAOs in both simulation and experimental environments. Finally, a comparison has been performed between the simulation and experimental results, and a good agreement is observed between both the results with a minimal percentage of error. The proposed navigational controller is also tested against other existing navigational technologies to validate better efficiency.