Visual Navigation and Obstacle Avoidance Control for Agricultural Robots via LiDAR and Camera

Abstract

Obstacle avoidance control and navigation in unstructured agricultural environments are key to the safe operation of autonomous robots, especially for agricultural machinery, where cost and stability should be taken into account. In this paper, we designed a navigation and obstacle avoidance system for agricultural robots based on LiDAR and a vision camera. The improved clustering algorithm is used to quickly and accurately analyze the obstacle information collected by LiDAR in real time. Also, the convex hull algorithm is combined with the rotating calipers algorithm to obtain the maximum diameter of the convex polygon of the clustered data. Obstacle avoidance paths and course control methods are developed based on the danger zones of obstacles. Moreover, by performing color space analysis and feature analysis on the complex orchard environment images, the optimal H-component of HSV color space is selected to obtain the ideal vision-guided trajectory images based on mean filtering and corrosion treatment. Finally, the proposed algorithm is integrated into the Three-Wheeled Mobile Differential Robot (TWMDR) platform to carry out obstacle avoidance experiments, and the results show the effectiveness and robustness of the proposed algorithm. The research conclusion can achieve satisfactory results in precise obstacle avoidance and intelligent navigation control of agricultural robots.

A review on positioning techniques of mobile robots

“…1), and it is possible to distinguish a subset of those that rely on the reproduction of a pre-programmed route, such as where a map that has been pre-designed and uploaded, or a route that is mapped by markers or lines [1][2][3]. A distinction can be drawn between those that rely on reference points, such as magnetic lines [4], RFID [5,6], QRCode [7,8], and others, and those that employ image recognition [9] and artificial intelligence techniques [10][11][12][13]. Another group uses sound (ultrasonic) waves [14,15] or electromagnetic waves, such as laser [16][17][18], infrared [19] technologies, and radio waves [20][21][22], such as Bluetooth [23] or UWB [24,25] technologies.…”

“…Global location determination and simple navigation thanks to extensive maps Limited range (mainly indoors) [12], [17], [28,29], [35], [47] Radio waves Medium Good accuracy, resistant to harsh environmental conditions Application of complex data processing algorithms [20][21][22][23][24][25][26], [49] Vision system High Very high accuracy, can be used virtually anywhere, ambient mapping Mainly based on artificial intelligence, so very sophisticated image recognition algorithms [9][10][11][12], [27], [41], [46] Follow Poor dirt resistance, complex information processing [9], [13], [45,46], [48] Other markers [-] Easy to find (self) robot, with known marker location High density of markers needed for decent work [10], [27], [48] 3. A review of the selected localization methods…”

An Improved Rotating Box Detection Model for Litchi Detection in Natural Dense Orchards

“…With the rapid development of deep learning technology, excellent target detection algorithms such as YOLO, SSD, and Faster R-CNN have been applied to fields such as fruit and vegetable detection [14][15][16][17][18][19]. For example, the k-means++ clustering algorithm has been used to optimize bounding box settings, reduce the number of network layers, and improve litchi detection in dense scenes [20].…”