Towards Corrective Deep Imitation Learning in Data Intensive Environments: Helping robots to learn faster by leveraging human knowledge

Interactive imitation learning refers to learning methods where a human teacher interacts with an agent during the learning process providing feedback to improve its behaviour. This type of learning may be preferable with respect to reinforcement learning techniques when dealing with real-world problems. This fact is especially true in the case...

3D Object Detection For Intelligent Vehicles

This master thesis presents an experimental study on 3D person localization (i.e., pedestrians, cyclists)in traffic scenes, using monocular vision and Light Detection And Ranging (LiDAR) data. The performance of two top-ranking methods is analyzed on the 3D object detection KITTI dataset. In this evaluation, the effect of the Intersection over...

Online Learning of Tire Behaviour combined with MPC for Autonomous Racing

In this project, a unique method of combining online learning with model predictive control is applied to autonomous racing. A concern in autonomous racing is that accurate models that encapsulate the dynamics of the vehicle are complex, nonlinear, and difficult to identify. In order to make this more practical for control purposes, the...

Uncertainty-based Interactive Machine Learning

Interactive machine learning describes a collection of methodologies in which a human user actively participates in a novice agent’s learning process, through providing corrective or evaluate feedback or demonstrative actions. A primary assumption in these methods is that user input is at worst nearoptimal, however a realistic set of...

Correct-by-Design Synthesis of Neural Network Controllers

The use of artificial neural networks is becoming ever more ubiquitous as the computational power available to use grows. The widespread implementation of neural networks as controllers in the field of systems and control is however being hindered by the lack of verifiability of these controllers. One type of controller that does not lack...

Implementing Symbolic Controllers into FPGAs

Embedded control systems are processor-based systems that need to run an application for an extended amount of time, such as months or years. Typically, they implement a realtime function to control a system. Embedded systems are implemented using hardware and software to perform an specific task. This is why they can be optimized to reduce its...

Binary Neural Networks for Object Detection

In the past few years, convolutional neural networks (CNNs) have been widely utilized and shown state-of-the-art performances on computer vision tasks. However, CNN based approaches usually require a large amount of storage, run-time memory, as well as computation power in both training and inference time, which are usually used on GPU based...

Efficient Neural Architecture Search for Language Modeling

Neural networks have achieved great success in many difficult learning tasks like image classification, speech recognition and natural language processing. However, neural architectures are hard to design, which requires lots of knowledge and time of human experts. Therefore, there has been a growing interest in automating the process of designing...

Online Reinforcement Learning for Flight Control: An Adaptive Critic Design without prior model knowledge

Online Reinforcement Learning is a possible solution for adaptive nonlinear flight control. In this research an Adaptive Critic Design (ACD) based on Dual Heuristic Dynamic Programming (DHP) is developed and implemented on a simulated Cessna Citation 550 aircraft. Using an online identified system model approximation, the method is independent...

Adaptive Observer for Automated Emergency Maneuvers: Fusing cost-efficient onboard sensors with computer vision into a robust estimate of sideslip angle using online covariance calculation

One of the most promising ideas in autonomous vehicle control systems is letting the vehicle drive autonomously outside the normal, linear, operating region and letting it "drift". By doing so, the maneuverability of the vehicle could be enhanced. To enable systems that can control this behaviour, estimation of certain vehicle states is needed...

Informative Path Planning for Search and Rescue using a UAV

Target search in an obstacle filled environment is a practically relevant challenge in robotics that has a huge impact in the society. The wide range of applications include searching for victims in a search and rescue operation, detecting weeds in precision agriculture, patrolling borders for military and navy, automated census of endangered...

Sensor Data Fusion of Lidar and Camera for Road User Detection

Object detection is one of the most important research topics in autonomous vehicles. The detection systems of autonomous vehicles nowadays are mostly image-based ones which detect target objects in the images. Although image-based detectors can provide a rather accurate 2D position of the object in the image, it is necessary to get the accurate...