Haptic Learning Towards Neural-Network-based adaptive Cobot Path-Planning for unstructured spaces

Abstract

Collaborative Robots, or Cobots, bring new possibilities for human-machine interaction within the fabrication process, allowing each actor to contribute with their specific capabilities. However creative interaction brings unexpected changes, obstacles, complexities and non-linearities which are encountered in real time and cannot be predicted in advance. This paper presents an experimental methodology for robotic path planning using Machine Learning. The focus of this methodology is obstacle avoidance. A neural network is deployed, providing a relationship between the robot's pose and its surroundings, thus allowing for motion planning and obstacle avoidance, directly integrated within the design environment. The method is demonstrated through a series of case-studies. The method combines haptic teaching with machine learning to create a task specific dataset, giving the robot the ability to adapt to obstacles without being explicitly programmed at every instruction. This opens the door to shifting to robotic applications for construction in unstructured environments, where adapting to the singularities of the workspace, its occupants and activities presents an important computational hurdle today.