Difference between revisions of "Unmanned Autonomous Vehicles"

Revision as of 00:47, 4 October 2015

Recent news you should be aware of ...
 * 01/10/2015: Detailed schedule will be online soon
 

This is a description page for the PhD course on Unmanned Autonomous Vehicles in Air, Land and Sea. This 5 CFU course can be taken also by Master students from Computer Engineering, i.e., students enrolled in the Laurea Magistrale track.

Course Aim & Organization

The course is aimed at providing students (with basic knowledge about robotics and control) with theoretical and practical instruments, related to modelling and identification, perception, control, path/trajectory and mission planning, required to understand this evolution, and set up unmanned autonomous vehicles in the air, land and sea domains.

Teachers

The course is held by (in order of appearance)

• Luca Bascetta, Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano
• Matteo Matteucci, Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano
• Marco Farina, Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano
• Marco Lovera, Dipartimento di Ingegneria Aerospaziale, Politecnico di Milano
• Alfredo Martins, Instituto Superior de Engenharia do Porto
• ...

Course Program

The course presents the knowledge required to better understand the commonalities and specificities of unmanned autonomous vehicles design in the different domains of air, land, and sea.

To provide a common base to better understand the specificities induced by the particular domain, the course will provide basic knowledge about the general tools and common components that are involved in the design of an unmanned autonomous vehicle. After an initial introduction of the current state of the art and potential applications of unmanned autonomous vehicles, the course will introduce:

• the most common vehicle kinematic and dynamic models;
• the fundamentals on path/trajectory and mission planning;
• the fundamentals on vehicle model identification and state estimation;
• the most common sensors for vehicle localization, control, obstacle avoidance;
• fundamentals of model predictive control applied to vehicle trajectory tracking, stabilization and obstacle avoidance.

The previous topics will be complemented by a description of a complete application case study for each domain (air, marine and land) with the purpose to highlight how each of the components has been applied or it has required some specific adaptation to cope with its peculiarity. In particular, we will discuss applications in the following domain

• air: fixed wing and rotary unmanned aerial vehicles;
• land: off-road unmanned vehicles;
• sea: surface and underwater unmanned vehicles.

Current trends and future applications will be presented and discussed in a final panel with people from academia and industry.

Course Schedule

The course schedule for this year edition foresees 36 hours of lectures from 9:00 to 18:00 (slight adjustments in time might happen according to participants needs) held in a single week at the beginning of June 2016. The room for all the lectures will be communicated with the exact dates.

Course Material & Referencies

The following is some suggested material to follow the course lectures.

Slides and lecture notes

• Correspondence analysis and RANSAC (2011-2012 ed.)
• Camera geometry, single view, and two view geometry material
• Two view geometry and visual odometry material
• Optical flow tracking and egomotion estimation
• Structure from Motion
• Bayesian Filtering, Kalman Filtering, and SLAM
• Simultaneous Localization and Mapping a.k.a. SLAM!
• Monocular SLAM
• Stereo and Omnidirectional SLAM
• Panoramic Visual Odomentry
• Parallel Tracking and Mapping

Suggested Bibliography

• R. Hartley, A. Zisserman. Multiple View Geometry in Computer Vision, Cambridge University Press, March 2004.
• S. Thrun, W. Burgard, D. Fox. Probabilistic Robotics, MIT Press, September 2005.
• Papers you might find useful to deepen your study:
  • Simultaneous Localization and Mapping (SLAM): Part I The Essential Algorithms. H. Durrant-Whyte, T. Bailey [1]
  • Unified Inverse Depth Parametrization for Monocular SLAM by J.M.M. Montiel, Javier Civera, and Andrew J. Davison [2]
  • Parallel Tracking and Mapping for Small AR Workspaces by Georg Klein and David Murray [3]
  • FrameSLAM: from Bundle Adjustment to Realtime Visual Mappping by Kurt Konolige and Motilal Agrawal [4]

Course Evaluation