The deployment of a group of robots equipped with sensors for monitoring, also known as a robotic sensor network, is a promising technological solution to solve time-critical societal and environmental issues. This paper considers the problem of deploying a robotic sensor network to persistently and effectively monitor multiple locations of interest in a large field represented by grids. To this end, we propose a novel two-layer control framework where the first layer (i.e., task allocation strategy) encapsulates the targeted grids into a set of tasks (small regions of interest) followed by optimally allocating the robots to each task based on their initial position (location of their base stations) and sensing capabilities. The second layer (i.e., persistent monitoring algorithm) generates each robot’s motion control input to ensure persistent monitoring over the designated region of interest. The proposed framework is demonstrated and evaluated via numerical simulations. It is shown that the proposed control framework improves real-time monitoring in terms of both the coverage performance and travel distance of the robots.

This paper presents the thorough evaluation and analysis on the direct inverse neural networks based controller systems for a double-propeller boat model. Two direct inverse controller systems that were designed with and without feedback were implemented on a double propeller boat model using two neural networks based control approaches, namely the back-propagation based neural controller (BPNN-controller) and the self-organizing maps based neural controller (SOM-controller). Then, the resulted control errors of the systems were compared. Simulation results revealed that the direct inverse control without feedback produced lower error compared to the direct inverse control with feedback. Another important finding from the study was that the SOM-controller is superior to the BPNN-controller in terms of control error and training computational cost.

Path planning is an essential algorithm in autonomous mobile robots, including agricultural robots, to find the shortest path and to avoid collisions with obstacles. Q-Learning algorithm is one of the reinforcement learning methods used for path planning. However, for multi-robot system, this algorithm tends to produce the same path for each robot. This research modifies the Q-Learning algorithm in order to produce path variations by utilizing the motivation model, i.e. achievement motivation, in which different motivation parameters will result in different optimum paths. The Motivated Q-Learning (MQL) algorithm proposed in this study was simulated in an area with three scenarios, i.e. without obstacles, uniform obstacles, and random obstacles. The results showed that, in the determined scenario, the MQL can produce 2 to 4 variations of optimum path without any potential of collisions (Jaccard similarity = 0%), in contrast to the Q-Learning algorithm that can only produce one optimum path variation. This result indicates that MQL can solve multi-robots path planning problems, especially when the number of robots is large, by reducing the possibility of collisions as well as decreasing the problem of queues. However, the average computational time of the MQL is slightly longer than that of the Q-Learning.

This paper considers the problem of task allocation where the goal is to find a coalition of UAVs (agents) to complete on-farm agricultural tasks. In this study, Ant Colony Optimization (ACO) algorithm is employed to find the best coalition of agents. The performance of the basic ACO algorithm for solving task allocation is improved by modifying the efficiency factor. In the proposed algorithm, the efficiency factor is defined as a function that relates not only to the capability of the agents and the distance between the agents, but also to the distance between the agents and the target. To solve the task allocation problem, the capability list of the agents was also adjusted using common UAV capabilities in agricultural application. Simulation results showed that the proposed ACO algorithm with the modified efficiency factor improved the performance of basic ACO algorithm for solving task allocation problem in terms of the average total travel cost for each agent. The optimum number of ants and agents in the proposed algorithm was also analysed for robust performance. Simulation results revealed that the addition of the numbers of agents and ants increases the average efficiency of the algorithm. In this study, we have also added a function to calculate the system capability utilization. By employing such a function, simulation results show that the total resource used by the agents and total communication cost can be optimized. In addition, a simple experiment using five ground robots with a centralized control was also carried out as a proof of concept for the proposed algorithm.

Penelitian ini dilakukan untuk mengembangkan robot otonom yang dikendalikan dengan pendekatan matematika inverse kinematics. Robot yang digunakan pada penelitian ini adalah robot beroda nonholonomic differential drive. Metode penelitian yang digunakan terdiri atas empat tahapan, yaitu: penentuan parameter robot beroda, pengembangan kontrol inverse kinematics, pembuatan data lintasan (trajectory) berupa garis lurus, dan pengujian sistem kendali. Pada pengujian, data trajectory yang dibangkitkan dibandingkan dengan pengukuran berdasarkan observasi di lapangan. Pengukuran data gerakan robot di lapangan dilakukan dengan dua alat, yaitu dengan global positioning system (GPS) yang terpasang pada robot dan GPS smartphone. Hasil pengujian menunjukkan bahwa robot beroda dapat dikendalikan dengan inverse kinematics dengan rata-rata nilai galat sebesar 0.9 meter. Kata Kunci: inverse kinematics, kendali, otonom, robot beroda.