Environment Representation: Antecedents and Directions

Abstract :

Environment perception is a key functionality for the robot to navigate across unknown environments. Stateof- the-Art representations of such environments are suitable for the robot to navigate and construct the environment while driving (e.g.: SLAM). However the interchange of such information among robotic subsystems is mostly limited or some cases impossible. The robot collects and generates rich amount of perceptive data while driving across the terrain. When performing isolated or complicated tasks like localization and mapping the same environment representation might be used with almost zero cost. Conversely, when robots perform complex mission scenarios other subsystems (i.e.: perception, planning, internal simulation, telemetry, etc.) have the requirements to actively inter and exchange information in an effective manner. Environment Representation (EnviRe) technologies are meant to close the gap and provide techniques to store, operate and interchange information within a robotic system. The application of EnviRe mainly focus to support navigation, simulation and operations and simplify the interchange of algorithms among software components.