Hypermaps: Beyond Occupancy Grids

Hypermaps aim at improving how robots manage data about the environment they inhabit. The most common way for robots to handle environmental information is by using maps. At present, each kind of data is hosted on a separate map, which complicates planning because a robot attempting to perform a tasks needs to access and process information from many different maps.

The use of maps for humans have moved away from single-purpose maps (such as geographical, political, and road map) to favor multi-layer maps (like Google Maps or OpenStreetMap) which store different information on each layer. We propose that in robotics a similar shift has the potential to revolutionize the way robots interact with knowledge about their environment.

One of the immediate benefits of the proposed framework is simplifying the interaction between the robot and the underlying maps, treated in the framework as layers. The framework works as an interface for the robot, that will receive information about the map content only by communicating with the framework. However many new possibilities open when all maps are managed together, and the long term plan of this project is to demonstrate this potential.

People involved

Project updates

Master thesis on “People flow maps for indoor robot navigation”

This thesis goal is to develop a probabilistic approach for building and updating people flow maps able to help the robot being socially-aware while navigating by predicting people movement.

Hypermaps at PAL ICRA 2020 workshop

We presented the core idea behind the Hypermaps project at the ICRA 2020 workshop on Perception, Action, Learning (PAL)

Source code for the Hypermaps project

The source code for the article “Hypermap Mapping Framework and its Application to Autonomous Semantic Exploration” is available on github.