The agricultural and farming industries have been widely influenced by the disruption of the Internet of Things. The impact of the IoT is more limited in countries with less penetration of mobile internet such as sub-Saharan countries, where agriculture commonly accounts for 10 to 50% of their GPD. The boom of low-power wide-area networks (LPWAN) in the last decade, with technologies such as LoRa or NB-IoT, has mitigated this providing a relatively cheap infrastructure that enables low-power and long-range transmissions. Nonetheless, the benefits that LPWAN technologies enable have the disadvantage of low-bandwidth transmissions. Therefore, the integration of Edge and Fog computing, moving data analytics and compression near end devices, is key in order to extend functionality. By integrating artificial intelligence at the local network layer, or Edge AI, we present a system architecture and implementation that expands the possibilities of smart agriculture and farming applications with Edge and Fog computing and LPWAN technology for large area coverage. We propose and implement a system consisting on a sensor node, an Edge gateway, LoRa repeaters, Fog gateway, cloud servers and end-user terminal application. At the Edge layer, we propose the implementation of a CNN-based image compression method in order to send in a single message information about hundreds or thousands of sensor nodes within the gateway's range. We use advanced compression techniques to reduce the size of data up to 67% with a decompression error below 5%, within a novel scheme for IoT data.

Autonomous harvesting and transportation is a long-term goal of the forest industry. One of the main challenges is the accurate localization of both vehicles and trees in a forest. Forests are unstructured environments where it is difficult to find a group of significant landmarks for current fast feature-based place recognition algorithms. This paper proposes a novel approach where local point clouds are matched to a global tree map using the Delaunay triangularization as the representation format. Instead of point cloud based matching methods, we utilize a topology-based method. First, tree trunk positions are registered at a prior run done by a forest harvester. Second, the resulting map is Delaunay triangularized. Third, a local submap of the autonomous robot is registered, triangularized and matched using triangular similarity maximization to estimate the position of the robot. We test our method on a dataset accumulated from a forestry site at Lieksa, Finland. A total length of 200 m of harvester path was recorded by an industrial harvester with a 3D laser scanner and a geolocation unit fixed to the frame. Our experiments show a 12 cm s.t.d. in the location accuracy and with real-time data processing for speeds not exceeding 0.5 m/s. The accuracy and speed limit are realistic during forest operations.

LiDAR-based simultaneous localization and mapping (SLAM) approaches have obtained considerable success in autonomous robotic systems. This is in part owing to the high accuracy of robust SLAM algorithms and the emergence of new and lower-cost LiDAR products. This study benchmarks the current state-of-the-art LiDAR SLAM algorithms with a multi-modal LiDAR sensor setup, showcasing diverse scanning modalities (spinning and solid state) and sensing technologies, and LiDAR cameras, mounted on a mobile sensing and computing platform. We extend our previous multi-modal multi-LiDAR dataset with additional sequences and new sources of ground truth data. Specifically, we propose a new multi-modal multi-LiDAR SLAM-assisted and ICP-based sensor fusion method for generating ground truth maps. With these maps, we then match real-time point cloud data using a normal distributions transform (NDT) method to obtain the ground truth with a full six-degrees-of-freedom (DOF) pose estimation. These novel ground truth data leverage high-resolution spinning and solid-state LiDARs. We also include new open road sequences with GNSS-RTK data and additional indoor sequences with motion capture (MOCAP) ground truth, complementing the previous forest sequences with MOCAP data. We perform an analysis of the positioning accuracy achieved, comprising ten unique configurations generated by pairing five distinct LiDAR sensors with five SLAM algorithms, to critically compare and assess their respective performance characteristics. We also report the resource utilization in four different computational platforms and a total of five settings (Intel and Jetson ARM CPUs). Our experimental results show that the current state-of-the-art LiDAR SLAM algorithms perform very differently for different types of sensors. More results, code, and the dataset can be found at GitHub.

Three-dimensional representations and maps are the key behind self-driving vehicles and many types of advanced autonomous robots. Localization and mapping algorithms can achieve much higher levels of accuracy with dense 3D point clouds. However, the cost of a multiple-channel three-dimensional lidar with a 360°field of view is at least ten times the cost of an equivalent single-channel two-dimensional lidar. Therefore, while 3D lidars have become an essential component of self-driving vehicles, their cost has limited their integration and penetration within smaller robots. We present an FPGA-based 3D lidar built with multiple inexpensive RPLidar A1 2D lidars, which are rotated via a servo motor and their signals combined with an FPGA board. A C++ package for the Robot Operating System (ROS) has been written, which publishes a 3D point cloud. The mapping of points from the two-dimensional lidar output to the three-dimensional point cloud is done at the FPGA level, as well as continuous calibration of the motor speed and lidar orientation based on a built-in landmark recognition. This inexpensive design opens a wider range of possibilities for lower-end and smaller autonomous robots, which can be able to produce three-dimensional world representations. We demonstrate the possibilities of our design by mapping different environments.

Odometry during forest operations is demanding, involving limited field of vision (FOV), back-and-forth work cycle movements, and occasional close obstacles, which create problems for state-of-the-art systems. We propose a two-phase on-board process, where tree stem registration produces a sparse point cloud (PC) which is then used for simultaneous location and mapping (SLAM). A field test was carried out using a harvester with a laser scanner and a global navigation satellite system (GNSS) performing forest thinning over a 520 m strip route. Two SLAM methods are used: The proposed sparse SLAM (sSLAM) and a standard method, LeGO-LOAM (LLOAM). A generic SLAM post-processing method is presented, which improves the odometric accuracy with a small additional processing cost. The sSLAM method uses only tree stem centers, reducing the allocated memory to approximately 1% of the total PC size. Odometry and mapping comparisons between sSLAM and LLOAM are presented. Both methods show 85% agreement in registration within 15 m of the strip road and odometric accuracy of 0.5 m per 100 m. Accuracy is evaluated by comparing the harvester location derived through odometry to locations collected by a GNSS receiver mounted on the harvester.