Example PhD Research Projects in Intelligent Robotics

Project 1

Title: Adaptive Sensor Networks using Bio-inspired Power and Data Management.

Description: The robots that operate autonomously for extended periods in remote environments are often limited to gather only small amounts of power through photovoltaic solar panels. Such limited power budgets make power management critical to the success of the robot's mission. Artificial endocrine controllers, inspired by the mammalian endocrine system, have shown potential as a method for managing competing demands, gradually switching between behaviors, synchronizing behavior with external events, and maintaining a stable internal state of the robot. This project is about using these methods to manage power in an autonomous robot.

Reference to a paper
C. Sauze, M. Neal (2013) Artificial Endocrine Controller for Power Management in Robotic Systems. IEEE Transactions on Neural Networks and Learning 24 (12) pp. 1973-1985. 

Project 2

Title: Automatic driving on ill-defined roads

Description: The project concern the design of control system to allow an autonomous mobile robots to drive on its own on mountain tracks using as only input a camera.  The difficulty in driving mountain tracks is that they are not well defined and therefore difficult 
to identify and being driveable.

Reference to a paper

Automatic Driving on Ill-defined Roads: An Adaptive, Shape-constrained, Color-based Method. Marek Ososinski and Frédéric Labrosse. Journal of Field Robotics, 27 DEC 2013, DOI: 10.1002/rob.21494 http://dx.doi.org/10.1002/rob.21494

Project 3

Title: Dynamic Task-Allocation in Swarm of Robots

Description: Swarm robotics is a particular approach to the design of multi-robot systems that finds its theoretical roots in recent studies in animal societies, such as ants and bees. Despite noise in the environment, errors in processing information and performing tasks, and no global information, social insects are quite successful at performing group-level tasks. Based on the social insect metaphor, swarm robotics emphasises aspects such as decentralisation of the control, limited communication abilities among robots, use of local information, emergence of global behaviour and robustness. These properties are meant to facilitate the design of artificial systems scalable to group size, robust to noise, and adaptive to environmental changes.

Research in swarm robotics has been focusing on mechanisms to enhance the efficiency of the group through some form of cooperation among the individual agents. Complex forms of group cooperative responses are based on task-partitioning (i.e., division of a collective task into individual sub-tasks) and task-allocation (i.e., allocation of sub-tasks to different individuals). The latter can be a dynamic and

flexible process, in that the number of individuals engaged in any given task may need to continually change, as circumstances require. Hereafter, we use the term task-switching to refer to the process in which one or more agents leave their current activity to join a different one for the benefit of the team. In spite of its significance for the adaptability of the swarm, the autonomous and dynamic re-distribution of robots to tasks is still a design challenge. The aim of this project is to study the conditions for the emergence of dynamic task-allocation and task-switching behaviour in large robot teams.

Reference to a paper

Tuci E., Trianni V., On the Evolution of Homogeneous Multi-Robot Teams: Clonal versus Aclonal Approaches. Neural Computing & Applications Journal (Springer), Vol. 25, pp 1063-1076, 2014.