Multi-­Robot Exploration and Planning in Limited Communication Environments

Distributed cooperative robots can be highly beneficial in mapping disaster environments and assisting with search and rescue operations. In most situations such environments only allow for only limited communication between robots. This thesis reports on simulation experiments conducted to test the impact of having only partial communication...

Evaluation of lane change predictions for schedule-driven intersection control

Optimization of traffic signal control has been widely investigated by means of model-based strategies. In 2012 a new model-based controller was published, named Schedule-driven Intersection Control (SCHIC). This controller uses a job-scheduling algorithm to minimize the cumulative delay for all observed vehicles. The algorithms of SCHIC are at...

Exploring the effects of conditioning Independent Q-Learners on the sufficient plan-time statistic for Dec-POMDPs

The Decentralized Partially Observable Markov Decision Process is a commonly used framework to formally model scenarios in which multiple agents must collaborate using local information. A key difficulty in a Dec-POMDP is that in order to coordinate successfully, an agent must decide on actions not only using its own information, but also by...

Learning What to Attend to: Using bisimulation metrics to explore and improve upon what a deep reinforcement learning agent learns

We analyze the internal representations that deep Reinforcement Learning (RL) agents form of their environments and whether these representations correspond to what such agents should ideally learn. The purpose of this comparison is both a better understanding of why certain algorithms or network architectures perform better than others and the...

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...

Traffic optimization using a novel traffic controller featuring distributed agents and forecasting

Using some sort of adaptive traffic light control system is becoming standard policy among metropolitan areas. However, controlling traffic lights efficiently on a city-wide scale is computationally intensive and theoretically complex. This paper aims to show a proof of concept of an efficient and modular traffic. light controller with...

A comparison between artificial neural networks and ARIMA models in traffic forecasting

Motivation: Traffic forecasting is becoming a vital component of our travel experience. It plays a key role in intelligent transportation systems that allow us to make smarter use of existing transportation networks. This study focuses on the possible role of artificial neural networks in these systems and what data can be best feed in to them...

Short-term forecasting of non-stationary time series using multiple feature selection methods

Time series forecasting has been proved to be relatively easier for stationary time series, compared to non-stationary time series. This research proposes a method to partially omit the non-stationarity of the data using prioritized sampling. Using multiple feature selection methods in combination with a random forest regressor (RFR), we aim to...