2023
Underwater localization and tracking is a challenging problem and Time-of-Arrival and Time-Difference-of-Arrival approaches are commonly used. However, the performance difference between these approaches is not well understood or analysed adequately. There are some analytical studies for terrestrial applications with the assumption that the signal arrival times are not correlated. However, this assumption is not valid for underwater propagation. To present the distinct nature of the problem under the water, a high-fidelity simulation is required. In this study, Time-of-Arrival and Time-Difference-of-Arrival approaches are compared using a ray tracing based propagation model. Moreover, basic methods to mitigate the multipath propagation problem are also implemented for Bernoulli filters. Since the Bernoulli filter is a joint detection and tracking filter, the detection performance is also analysed. Comparisons are done for all combinations of filter and measurement approaches. The results can help to design underwater localization systems better suited to the needs. [link]
Underwater localization and tracking is a challenging problem and Time-of-Arrival and Time-Difference-of-Arrival approaches are commonly used. However, the performance difference between these approaches is not well understood or analysed adequately. There are some analytical studies for terrestrial applications with the assumption that the signal arrival times are not correlated. However, this assumption is not valid for underwater propagation. To present the distinct nature of the problem under the water, a high-fidelity simulation is required. In this study, Time-of-Arrival and Time-Difference-of-Arrival approaches are compared using a ray tracing based propagation model. Moreover, basic methods to mitigate the multipath propagation problem are also implemented for Bernoulli filters. Since the Bernoulli filter is a joint detection and tracking filter, the detection performance is also analysed. Comparisons are done for all combinations of filter and measurement approaches. The results can help to design underwater localization systems better suited to the needs. [link]
Underwater localization and tracking is a challenging problem and Time-of-Arrival and Time-Difference-of-Arrival approaches are commonly used. However, the performance difference between these approaches is not well understood or analysed adequately. There are some analytical studies for terrestrial applications with the assumption that the signal arrival times are not correlated. However, this assumption is not valid for underwater propagation. To present the distinct nature of the problem under the water, a high-fidelity simulation is required. In this study, Time-of-Arrival and Time-Difference-of-Arrival approaches are compared using a ray tracing based propagation model. Moreover, basic methods to mitigate the multipath propagation problem are also implemented for Bernoulli filters. Since the Bernoulli filter is a joint detection and tracking filter, the detection performance is also analysed. Comparisons are done for all combinations of filter and measurement approaches. The results can help to design underwater localization systems better suited to the needs. [link]
Target tracking in transportation vehicles is important from both civilian and military perspectives. Objects that obstruct the sensor's field of view create occlusion regions in target tracking. The literature has developed dynamic solutions to address the problems arising from the target entering the sensor's occlusion spot behind an obstacle and detecting occlusion regions. In this study, target tracking using lidar is performed with a stationary vehicle obstacle and a moving vehicle in the Gazebo simulation environment. A solution is proposed for velocity disturbances during entry into the occlusion region in this environment. After comparing the performance of target tracking filters in the simulation environment, the algorithms are tested in a real-world scenario where a similar simulation environment is set up. Two different Bernoulli filters are implemented based on the nearest neighbor and probabilistic data association mechanisms. The results are evaluated using the Optimal SubPattern Assignment metrics. [link]
Ultrawideband range sensors are utilized for localization in varius application areas in autonomous systems. One of the most prominent sources of error is that the sensors are not in the line-of-sight of each other and the signals travel along different paths causing error. An approach to correct for this problem is the detection of line-of-sight and non-line-of-sight signals. In this work, non-line-of-sight signals are detected and eliminated using anomaly detection. In the proposed approach is tested using simulations and different probability distributions. The obtained results show that the localization errors are decreased. [link]
Sensor control provides a framework for the autonomous functioning of mobile sensors. The parameters of a target is estimated using a cost function. By optimizing the cost function, the actions to be taken by the vehicle is determined. In the literature, the vehicles are assumed as point robots so far and vehicle dynamics are ignored. In this work, the vehicle dynamics are involved in the equations for the first time. Performance of the systems with and without vehicle dynamics are analyzed in V-REP simulation environment and the results are presented. [link]
Mobile robot path planning is a vital problem in robotics that involves determining a collision-free path for a robot from a starting point to a goal point in environments populated with obstacles. In this paper, a comparative analysis of two path planning approaches for mobile robots is presented. Q-learning is used as a reinforcement learning (RL) approach, and A* as a graph search method. The performance of each technique is evaluated in Gazebo environment on a simulated Ackermann drive mobile robot that navigates through an environment containing obstacles. The generated paths are compared based on the path length, computational time, travel time, the robustness of the planning technique to changes in the environment, and path smoothness. The results show that Q-learning outperforms A* in terms of computation time. The computed paths by the Q-learning based approach are more smooth with fewer number of turns. Moreover, A* is not robust to environmental complexity because the computational time, and length of the computed path increases as the complexity of the environment increases. Hence, the acquired findings suggest that Q-learning can be a promising approach for mobile robot path planning, particularly in scenarios where path smoothness, robustness, and computational time are critical factors. [link]
2022
Selective agrochemical spraying is a highly intricate task in precision agriculture. It requires spraying equipment to distinguish between crop (plants) and weeds and perform spray operations in real-time accordingly. The study presented in this paper entails the development of two convolutional neural networks (CNNs)-based vision frameworks, i.e., Faster R-CNN and YOLOv5, for the detection and classification of tobacco crops/weeds in real time. An essential requirement for CNN is to pre-train it well on a large dataset to distinguish crops from weeds, lately the same trained network can be utilized in real fields. We present an open access image dataset (TobSet) of tobacco plants and weeds acquired from local fields at different growth stages and varying lighting conditions. The TobSet comprises 7000 images of tobacco plants and 1000 images of weeds and bare soil, taken manually with digital cameras periodically over two months. Both vision frameworks are trained and then tested using this dataset. The Faster R-CNN-based vision framework manifested supremacy over the YOLOv5-based vision framework in terms of accuracy and robustness, whereas the YOLOv5-based vision framework demonstrated faster inference. Experimental evaluation of the system is performed in tobacco fields via a four-wheeled mobile robot sprayer controlled using a computer equipped with NVIDIA GTX 1650 GPU. The results demonstrate that Faster R-CNN and YOLOv5-based vision systems can analyze plants at 10 and 16 frames per second (fps) with a classification accuracy of 98% and 94%, respectively. Moreover, the precise smart application of pesticides with the proposed system offered a 52% reduction in pesticide usage by spotting the targets only, i.e., tobacco plants. [link]
Reading the news from internet sites has become a common behavior. As a result, the internet news portals started to receive more traffic. The analysis of these readers' behavior is a difficult problem. However, internet provides the infrastructure to collect the required data. The behavior data of over one billion readers is obtained as a result. In this work, we analyzed the similarities and differences of the internet news readers from different cities based on the preferred news categories. The analysis indicates that the user behaviors in larger cities is different from the smaller cities. Moreover, the behaviors in smaller cities are also different from each other. [link]
Path planning is a critical function for autonomous vehicles. In military applications, the path planning algorithms must also be designed such that the vehicle is not detected. The stealth is even more important for the underwater vehicles. Detection of an underwater vehicle can be effected from various parameters. In this study, the relationship between these parameters and the resulting signal-to-noise ratio are modeled using sonar equations. Then, the probability of detection is calculated using the signal-to-noise ratio. A Q-learning based path planning approach is proposed where the rewards are calculated using the detection probabilities. The agent then chooses actions which minimize the probability of being detection along the whole planned path. Once trained and optimal policy is reached, the proposed algorithm yields more secure paths than the probabilistic roadmap method. Since it provides an optimal action per state, it is also more flexible in case the vehicle is drifted. The results show that the probability of being detected in the test scenario is 5% in average. [link]
With the transfer of the news sources to the internet and the traffic of the internet news sites also increase. The behavior of the users also differs from the traditional media. However, there are not enough studies regarding this topic. Another important property of internet for such studies is the availability of the real user behavior. The companies have behavior data of millions of users. These numbers cannot be reached using traditional methods and enables the true behaviors rather than opinions.The number of sociological studies using the digitally collected data is increasing in recent years. In this study, the reader habits are studied using the reader data of politics, sport, technology and magazine news categories from one of the top Turkish internet news web sites. This study is expected to provide a quantitative basis for future works. [link]