Over the last decade, Unmanned Aerial Vehicles (UAVs), also known as drones, have been broadly utilized in various agricultural fields, such as crop management, crop monitoring, seed sowing, and pesticide spraying. Nonetheless, autonomy is still a crucial limitation faced by the Internet of Things (IoT) UAV systems, especially when used as sprayer UAVs, where data needs to be captured and preprocessed for robust real-time obstacle detection and collision avoidance. Moreover, because of the objective and operational difference between general UAVs and sprayer UAVs, not every obstacle detection and collision avoidance method will be sufficient for sprayer UAVs. In this regard, this article seeks to review the most relevant developments on all correlated branches of the obstacle avoidance scenarios for agricultural sprayer UAVs, including a UAV sprayer’s structural details. Furthermore, the most relevant open challenges for current UAV sprayer solutions are enumerated, thus paving the way for future researchers to define a roadmap for devising new-generation, affordable autonomous sprayer UAV solutions. Agricultural UAV sprayers require data-intensive algorithms for the processing of the images acquired, and expertise in the field of autonomous flight is usually needed. The present study concludes that UAV sprayers are still facing obstacle detection challenges due to their dynamic operating and loading conditions.

https://www.mdpi.com/2073-4395/11/6/1069/pdf

A State-of-the-Art Analysis of Obstacle Avoidance Methods from the Perspective of an Agricultural Sprayer UAV’s Operation Scenario

In practical applications, an appropriate path planning algorithm needs to be selected according to the actual situation. Using the Cartographer algorithm based on graph optimization to build the map, and using AMCL positioning at the same time, the problem of low accuracy caused by its own defects has been successfully solved. A* algorithm original path trajectory inflection point, node redundancy phenomenon is obvious, longer running time, and even difficult to plan the optimal path An improved A* algorithm is proposed, which uses adding weight coefficient w, adaptively adjusting the step size algorithm and cubic Bezier curve make up for the lack of more turning points, larger turning angles and longer running time in the algorithm search. The hybrid path planning algorithm combining the improved A* algorithm and the dynamic window method solves the problem that the A* algorithm cannot avoid dynamic obstacles in complex environments, and prevents the mobile robot from falling into local optimum. Experiments show that the improved algorithm can effectively solve the problems of more turning points, larger turning angles and longer running time encountered by the mobile robot in the search.

A Novel Hybrid Path Planning Method for Mobile Robots

Future smart factories need to use intelligent transport devices like automated guided vehicles (AGVs) for connecting intelligent production and logistics. To address the lack of edge side functions in the current AGV systems, this paper proposes an agent-based system architecture for AGVs in cloud-edge computing environments. The system is divided into three main components: the cloud center, edge nodes, and AGV agents. The cloud center is largely responsible for AGV transport route planning, while the edge nodes are in charge of AGV transport control and equipment management. The driving function and executing commands are handled by AGV agents. AGV agents can communicate and collaborate with each other to address emergent issues. The proposed approach has been validated through simulations.

An Agent-based System Architecture for Automated Guided Vehicles in Cloud-Edge Computing Environments

In practical applications, an appropriate path planning algorithm needs to be selected according to the actual situation. Using the Cartographer algorithm based on graph optimization to build the map, and using AMCL positioning at the same time, the problem of low accuracy caused by its own defects has been successfully solved. A* algorithm original path trajectory inflection point, node redundancy phenomenon is obvious, longer running time, and even difficult to plan the optimal path An improved A* algorithm is proposed, which uses adding weight coefficient w, adaptively adjusting the step size algorithm and cubic Bezier curve make up for the lack of more turning points, larger turning angles and longer running time in the algorithm search. The hybrid path planning algorithm combining the improved A* algorithm and the dynamic window method solves the problem that the A* algorithm cannot avoid dynamic obstacles in complex environments, and prevents the mobile robot from falling into local optimum. Experiments show that the improved algorithm can effectively solve the problems of more turning points, larger turning angles and longer running time encountered by the mobile robot in the search. 

Perkembangan digitalisasi saat ini begitu pesat. Adanya digitalisasi menyebabkan proses pengukuran jarak dapat dilakukan tanpa menyentuh objek yang diukur. Salah satu komponen untuk pengukuran jarak yang banyak tersedia di pasaran adalah sensor light detection and ranging (LiDAR). Beberapa penelitian sebelumnya terkait penerapan sensor LiDAR sudah dilakukan, seperti untuk robot automated guided vehicle (AGV), quadcopter, dan pemetaan vegetasi tropis. Penelitian-penelitian sebelumnya berfokus pada penerapan sensor LiDAR dan belum menguji secara detail akurasi beserta karakteristiknya. Terdapat kemungkinan bahwa kinerja dari komponen kurang sesuai dengan spesifikasi data teknis yang dituliskan. Makalah ini menyajikan hasil pengujian kinerja sensor LiDAR jenis TF-Mini LiDAR untuk pengukuran jarak. Pengujian sensor TF-Mini LiDAR ini menggunakan metode eksperimen. Kinerja sensor dilihat berdasarkan pembacaan jarak maksimal, tingkat akurasi, pengaruh warna objek, kemiringan, dan jenis material objek yang dibaca. Hasil pengujian menunjukkan bahwa kinerja sensor TF-Mini LiDAR memiliki tingkat akurasi 3,17% pada rentang 0,3 m sampai 6 m serta 3,27% pada rentang 6 m sampai 12 m dengan jarak pembacaan maksimal hingga 10 m. Warna biru dan bahan besi merupakan warna serta bahan terbaik yang dapat dibaca oleh sensor, dengan rata-rata error masing-masing sebesar 2,78% dan 3,22%. Hasil pembacaan jarak pada objek datar dengan kemiringan 10° sampai 80° (kuadran 1) akan melebihi jarak sebenarnya seiring dengan bertambahnya sudut kemiringan objek dengan rata-rata error yang dihasilkan sebesar 7%. Untuk objek datar dengan kemiringan 100° sampai 170° (kuadran 2) diperoleh rata-rata error sebesar 2,75%. Selain itu, makin besar sudut kemiringan objek, makin akurat pembacaan jaraknya. Berdasarkan hasil pengujian tersebut, dapat diketahui bahwa sensor TF-Mini LiDAR dapat membaca jarak dengan lebih akurat ketika objek yang terdeteksi berada pada rentang jarak 0,5 m sampai 10 m dengan warna dan bahan objek yang tidak menyerap cahaya. Selain itu, posisi objek yang terdeteksi dalam keadaan lurus.

Analisis Kinerja Sensor TF-Mini LiDAR untuk Pengukuran Jarak

Automated Guided Vehicles are used to help the process of carrying materials from one place to another. AGVs are widely used in the materials handling process in different industries hence, the reasoning behind their extremely wide usage in industries such as Automotive, manufacturing, Medical, etc. This research deals with the obstacle avoidance of Automated Guided Vehicles (AGV). This paper propose an algorithm that helps to build obstacle-free trajectories for AGV that leave the original track and again get back to the original track by avoiding the obstacle. The new path also have to act according to the dynamic & kinematic constraints of the AGV. The proposed method will be validated using simulations.

R. Sivakumar

Papers

Intelligent Obstacle Avoiding AGV Using Vector Field Histogram and Supervisory Control

Yaw Moment Compensation by Actuator-Based Control of Brake System in Automobiles