| Macaco — Merging Social and Navigation Behaviors into a Head (2008) | |||||||||||||||
Abstract | |||||||||||||||
| The Problem: This research derives from the evolution of the Macaco project- head and brain development for a mobile robot in joint collaboration with the MIT Leg Lab. Macaco is a 7DOF small and light robotic head, with four color CMOS cameras and one thermal camera. This head will be incorporated into a moving body. The merging of social competencies with navigation capabilities requires an architecture that integrates all the modules coherently, such that Macaco is given a personality demarcated by curiosity and a wish of interacting with people, together with a strong instinct for safety. Motivation: One approach of AI is the development of robots whose embodiment and situatedness in the world evoke behaviors that obviate constant human supervision [2]. With this in mind, Macaco was designed for navigation in unstructured environments. Thus, its vision system must comprise methods of assessing the constantly changing terrain. Navigation for obstacle and potentially treacherous landscape avoidance, slope detection, and gaze stabilization are all requisites for such competence. Furthermore, in order to be a convincing social participant, the vision system must also allow for person detection and inference of human gaze direction. All of these vision modules must also be accessible to each other and concurrent with other sensor input from the rest of the body. Previous Work: There has been much machine vision work done involving the many different visual modules. However, most of this work has been applied to slow or stationary unintegrated systems with less complex motility requirements. | |||||||||||||||
Publication details | |||||||||||||||
| |||||||||||||||