PhD

Our open and ongoing projects in this area are listed below, together with a selection of completed projects where relevant.

Fast map learning with mobile robots

Mobile robots often need to learn an initially uknown map of a position-dependent parameter from sampled values. Examples include learning radio transmission rates, the density of litter at each point, forest density, etc. Moreover, learning this map is often only one part of the robot's task -- the robot may also have a navigation objective, low energy consumption goals, etc. In this project, we aim to design and study a robot motion control strategy that optimally takes into account both map learning and the other objectives of the robot.

Reinforcement learning and planning for nonlinear control applications

Planning methods for optimal control use a model of the system and the reward function to derive an optimal control strategy. Here we will consider in particular optimistic planning, a predictive approach that optimistically explores  possible action sequences from the current state. Due to generality in the dynamics and objective functions that it can address, it has a wide range of potential applications to problems in nonlinear control.

Assistive robot arms

Robots that assist elderly or disabled persons in their day-to-day tasks can lead to a huge improvement in quality of life. At ROCON we are pursuing assistive manipulators, as well as UAVs for monitoring at-risk persons. This project focuses on the first direction, and presents a wide range of opportunities for a team of students, starting from low-level control design and vision tasks, to high-level control using artificial intelligence tools. Each student will work on one well-defined subtopic in these areas. Specific tasks include:

Assistive autonomous UAVs

Robots that assist elderly or disabled persons in their day-to-day tasks can lead to a huge improvement in quality of life. This project employs UAVs to monitor at-risk persons, and research challenges range from real-time observation and observation to high-level vision and control for person monitoring. The project is appropriate for a team of students, each of them working on a well-defined subtask, such as:

Nonlinear control for commercial drones in autonomous railway maintenance

Drones are getting widespread and low-cost platforms already offer good flight and video recording experience. This project intends to use such drones in the context of railway maintenance by developing applications for autonomous navigation in railway environment.

Relative Pose Estimation of Objects using 3D Cameras

The challenging problem of fusing the data from central cameras such as 3D depth, infrared, omnidirectional or plain perspective camera is a must in the recent mobile robotics perception systems. Also the active perception task, i.e. the ability of getting the most information from a scene is getting into focus, thus this project aims to tackle this novel problem in the near future.

One of the main application of this approach is the 3D object recognition in dynamic space (e.g. production line, people tracking, etc).

Ppossible track within this project include:

Shape Based Active Perception

Perception for artificial systems is increasingly gaining importance especially for systems with multiple sensors. For example, the autonomous vehicles equipped with camera, lidar, inertial measurement units, positioning systems etc are becoming popular. More importantly they are using the information from the multiple sources in the mean time, in the same coordinate system in order to gain information about the environment. Thus, the need for fusing the information from several sources in a common space for reasoning purposes is crucial.

Subscribe to PhD