Autonomous Multi Robot Collaborative Exploration (Mapping)

Autonomous Multi Robot Collaborative Exploration (Mapping)


Overview :

  • Scanning process – 3D scanning is the process of capturing digital information about the shape of an object with equipment that uses a laser or light to measure the distance between the scanner and the object
  • Robotic Mapping - The goal for an autonomous robot is to be able to construct (or use) a map or floor plan and to localize itself in it. Robotic mapping is a branch that deals with the study and application of ability to construct such a map by an autonomous robot and to localize itself in it.

Project Definition :

We would like to perform a robust and autonomous mapping of a room or a set of rooms (e.g. an apartment). We are looking to do this scan as complete and fast as possible, without falling on the quality. We propose a project to create an autonomous scan using multiple (ground and/or aerial) robots, in order to achieve that goal.

Outputs

  • Proof of concept (POC) a single robot autonomously mapping an indoor area in a minimal time.
  • POC multi-robot scenario of mapping an indoor area and showing improvement in scan time.
  • Academic paper in a leading international conference (e.g. ICRA).

Logistics

  • The project will be initially for 1 semester, with a potential extension to a 2nd semester due its large scope and great potential
  • The project is offered both to undergraduate and graduate students with appropriate background

Prerequisites:

  • Strong programming skills (preferably Python or C++).
  • Background in (deep) reinforcement learning, computer vision, robotics is an advantage.
  • Path planning and Control theory – Advantage

Coordinated Multi-Robot Exploration

Autonomous Multi-Robot Exploration & Coverage

Collaborative Multi-Robot Localization

Academic supervisor:

  • Prof. Vadim Indelman mail

Duration: 1 or 2 semesters