Master thesis topics

To have more information on any of the proposals, please contact either Prof. Ville Kyrki or one of the advisors indicated in the proposal of interest.

At present, the following master thesis proposals are available in the group:

Master Thesis on “Interactive Bayesian Multiobjective Evolutionary Optimization in Reinforcement Learning Problems with Conflicting Reward Functions”

In many real-world problems, there are multiple conflicting objective functions that need to be optimized simultaneously. For example, an investment company wants to create an optimum portfolio of stocks to maximize profits and minimize risk simultaneously. However, most reinforcement learning (RL) problems do not explicitly consider the tradeoff between multiple conflicting reward functions and assume a scalarized single objective reward function to be optimized. Multiobjective evolutionary optimization algorithms (MOEAs) can be used to find Pareto optimal policies by considering multiple reward functions as objectives.

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.

Master Thesis on “Deep Imitative Models for Safe Planning of Autonomous Driving”

The goal of this thesis is to devise an algorithm that combines the advantage of both IL and MBRL for robust and safe planning for autonomous driving. In this context, the thesis is expected to include implementations of IL and MBRL algorithms and fuse them for planning tasks.

Master Thesis on “Inverse Reinforcement Learning for Driving Behavior Modeling”

The goal of this thesis is to formulate driving behavior modeling as an inverse reinforcement learning (IRL) problem. In this context, the thesis is expected to include implementations of different IRL methods and compare them concerning prediction capabilities.

Master Thesis on “Interaction Modeling for Autonomous Driving Using Graph Neural Networks”

The goal of this thesis is to model the interactions among autonomous agents in dense traffic using GNN. In this context, the thesis is expected to include an ablation study to identify which input features (such as velocity, distance to other vehicles, etc.) has the maximum effect on prediction and the effects of changing the graph structure on the interactions among the vehicles.

Master Thesis on “Model-based Dynamic Manipulation of Deformable Objects”

The goal of this thesis is to develop model-based approaches for the dynamic manipulation of a deformable object. Particularly, the focus will be on the task of throwing a lasso around a target (a bollard) with a robotic arm.

Master Thesis on “Adversarial Robotic Cloth Manipulation”

This thesis will focus on how to use adversarial learning for improving existing methods in robotic cloth manipulation.

Energy-Efficiency of Reinforcement Learning

This thesis will investigate the energy consumption of such reinforcement learning algorithms for both training and inference using monitoring capabilities. The goal is to find out how different algorithms compare in performance vs energy consumption on practical applications and if there are ways to reduce energy consumption by trading performance for low computational complexity, for example.

Robustify Behaviour and Morphology of Robots against Future Damage

This project is aimed at developing new methodologies and frameworks for learning behaviours and designs of robots with the goal of making them robust to mechanical failures or stark environmental changes impacting the performance of the robot.

Meta-Learning Embeddings for Reinforcement Learning

Meta-Learning of ‘learning-how-to-learn’ has been immensely popular in the deep learning community in recent years. In this thesis, we will investigate the problem of using meta-learning approaches and ideas to learn latent policy embeddings for use in reinforcement learning. A potential approach for this is hyper networks, ie networks which can generate other networks (see references). The thesis will investigate the application of these approaches and evaluate their usefulness in robot learning and continuous control tasks. Currently, the use of policy embeddings and hyper networks is an active area in research with potential applications to real-world robotics. This is a research-oriented thesis where the student will have the possibility to work on state-of-the-art problems and propose novel methods and algorithms for their use in robot learning.

Creating tool-boxes for the Co-Design of Robots in Simulation

This is a more engineering and software-development oriented thesis, aiming at providing open-source implementations for the research community. However, the thesis student will get some exposuire to the use of Deep Leanring algorithms and their application to practical research problems.

Improving Co-Design with Imitation Learning

This research thesis will investigate further how the use of imitation learning methods and algorithms can be used to improve existing Co-Design algorithms. The aim of this thesis is to develop systems developing both the body and mind of robots.

Evolutionary Imitation Learning for Continous Control

The thesis will start with an initial literature review to identify the space of potential hypothesis to investigate and apply the developed method to continous control tasks. This thesis is well suited for students interested in a research oriented master thesis with some possibilities to develop your own idea.

Master Thesis on the Co-Adaptation of Robots

The goal of this Master thesis is to develop simulation tools necessary to evaluate co-adaptation techniques, and to develop new approaches for learning the behaviour and design of robots using deep learning and deep reinforcement learning.

Master Thesis on “Safe Constrained Differential Dynamic Programming”

In this thesis, an extensive investigation of constrained DDP methods will be performed and the major selected ones will be implemented in simulation environment for trajectory optimizations of different robots such as a simple point robot, 2D car-like robot, 3D quadrotor robot and cart-pole system. In this context, the methods will be compared in terms of convergence speed, computational complexity, sensitivity to initializations and parameter selections.

Master thesis on “Hybrid learning and control for human-robot interaction: an imitation learning perspective”

The goal of this project is to exploit more comprehensive information from humans, in order to learn as many skill patterns from humans as possible according to the tasks at hand.