Selahattin Kosunalp

Application of reinforcement learning to medium access control for wireless sensor networks

This paper presents a novel approach to medium access control for single-hop wireless sensor networks. The ALOHA-Q protocol applies Q-Learning to frame based ALOHA as an intelligent slot selection strategy capable of migrating from random access to perfect scheduling. Results show that ALOHA-Q significantly outperforms Slotted ALOHA in terms of energy-efficiency, delay and throughput. It achieves comparable performance to S-MAC and Z-MAC with much lower complexity and overheads. A Markov model is developed to estimate the convergence time of its simple learning process and to validate the simulation results.

Approaches of Road Boundary and Obstacle Detection Using LIDAR

Abstract This paper introduces an overview of the studies of two problems; (1) road boundary detection and (2) obstacle detection, in order to allow the movement of autonomous vehicles. Light Detection and Ranging (LIDAR) is the most used technology for solving these two problems. It is thoroughly described with its operating mechanism and its use in other areas. We explore comprehensively the methods used in the literature to solve the detection of road boundaries and the obstacles as well as the recent trends in the relevant area. Furthermore, the solutions based on the previous works and suggested future works will be described.

Use of Q-learning approaches for practical medium access control in wireless sensor networks

This paper studies the potential of a novel approach to ensure more efficient and intelligent assignment of capacity through medium access control (MAC) in practical wireless sensor networks. Q-Learning is employed as an intelligent transmission strategy. We review the existing MAC protocols in the context of Q-learning. A recently-proposed, ALOHA and Q-Learning based MAC scheme, ALOHA-Q, is considered which improves the channel performance significantly with a key benefit of simplicity. Practical implementation issues of ALOHA-Q are studied. We demonstrate the performance of the ALOHA-Q through extensive simulations and evaluations in various testbeds. A new exploration/exploitation method is proposed to strengthen the merits of the ALOHA-Q against dynamic the channel and environment conditions.

Detection of road boundaries and obstacles using LIDAR

This paper proposes a novel approach to detecting road boundaries and obstacles for robust urban navigation of unmanned ground vehicles (UGVs). In this method, a 2-D Light Detection and Ranging (LIDAR) sensor mounted at a given pitch angle is used to extract the road surface. The information obtained about the road is evaluated by filters to detect whether the area scanned is a road or an obstacle. The proposed method is implemented through simulation and a real-life test vehicle called AKAY01.

Harvesting solar energy for limited-energy problem in wireless sensor networks

The major problem in wireless sensor networks (WSNs) is the limited-energy source, typically small batteries, employed by sensors. In order to prolong the lifetime of the WSNs, a lot of approaches have taken the limited-energy problem as a primarily design criterion. However, inevitable energy depletion will eventually disturb the operation of the WSNs. Recent studies have shown that renewable energy sources would potentially provide an infinite energy source for powering WSNs. Solar energy is the most effective energy source for WSNs as it has the largest power intensity. Therefore, each sensor which requires a small amount of energy for efficient operation can harvest sufficient energy from solar. In this study, a platform is designed in order to allow sensors to exploit solar energy. The performance of the sensors in terms of the lifetime is practically studied. The results demonstrate that sensors can also survive when there is no energy available through storing energy in a super-capacitor. IRIS nodes are used in experiments as they are very popular in WSNs domain.

Medium access control protocols for wireless sensor networks with ambient energy

Wireless sensor networks (WSNs) have recently been a popular research area with a broad range of applications. One of the most significant constraints of WSNs is energy limitation of sensor nodes. Therefore, energy-efficiency has been considered as primarily design criterion in many medium access control (MAC) protocols developed. In order to solve the issue of limited-energy sources, various recent protocols have focused on energy harvesting from surrounding environment, such as solar, wind and vibration energy, resulting in providing unlimited energy source. Ambient energy exhibits a characteristic of unlimited energy source but not available always due to environmental changes. The focus is now being placed on effective utilization of the time-varying ambient energy. This study aims to provide a review of recently proposed MAC protocols for energy-harvesting WSNs describing their operating principles and underlying features.