This review article is an attempt to survey all recent AI based techniques used to deal with major functions in This review paper presents a comprehensive overview of end-to-end deep learning frameworks used in the context of autonomous navigation, including obstacle detection, scene perception, path planning, and control. The paper aims to bridge the gap between autonomous navigation and deep learning by analyzing recent research studies and evaluating the implementation and testing of deep learning methods. It emphasizes the importance of navigation for mobile robots, autonomous vehicles, and unmanned aerial vehicles, while also acknowledging the challenges due to environmental complexity, uncertainty, obstacles, dynamic environments, and the need to plan paths for multiple agents. The review highlights the rapid growth of deep learning in engineering data science and its development of innovative navigation methods. It discusses recent interdisciplinary work related to this field and provides a brief perspective on the limitations, challenges, and potential areas of growth for deep learning methods in autonomous navigation. Finally, the paper summarizes the findings and practices at different stages, correlating existing and future methods, their applicability, scalability, and limitations. The review provides a valuable resource for researchers and practitioners working in the field of autonomous navigation and deep learning.

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation - A Comprehensive Review

Throughout human history, agriculture has undergone a series of progressive transformations based on ever-evolving technologies in an effort to increase productivity and profitability. Over the years, farming methods have evolved significantly, progressing from Agriculture 1.0, which relied on primitive tools, to Agriculture 2.0, which incorporated machinery and advanced farming practices, and subsequently to Agriculture 3.0, which emphasized mechanization and employed intelligent machinery and technology to enhance productivity levels. To further automate and increase agricultural productivity while minimizing agricultural inputs and pollutants, a new approach to agricultural management based on the concepts of the fourth industrial revolution is being embraced gradually. This approach is referred to as “Agriculture 4.0” and is mainly implemented through the use of Internet of Things (IoT) technologies, enabling the remote control of sensors and actuators and the efficient collection and transfer of data. In addition, fueled by technologies such as robotics, artificial intelligence, quantum sensing, and four-dimensional communication, a new form of smart agriculture, called “Agriculture 5.0,” is now emerging. Agriculture 5.0 can exploit the growing 5G network infrastructure as a basis. However, only 6G-IoT networks will be able to offer the technological advances that will allow the full expansion of Agriculture 5.0, as can be inferred from the relevant scientific literature and research. In this article, we first introduce the scope of Agriculture 5.0 as well as the key features and technologies that will be leveraged in the much-anticipated 6G-IoT communication systems. We then highlight the importance and influence of these developing technologies in the further advancement of smart agriculture and conclude with a discussion of future challenges and opportunities.

/pdf/the-impact-of-6g-iot-technologies-on-the-development-of-3b0ymrcd.pdf

The Impact of 6G-IoT Technologies on the Development of Agriculture 5.0: A Review

With the advancement of robotics, the field of path planning is currently experiencing a period of prosperity. Researchers strive to address this nonlinear problem and have achieved remarkable results through the implementation of the Deep Reinforcement Learning (DRL) algorithm DQN (Deep Q-Network). However, persistent challenges remain, including the curse of dimensionality, difficulties of model convergence and sparsity in rewards. To tackle these problems, this paper proposes an enhanced DDQN (Double DQN) path planning approach, in which the information after dimensionality reduction is fed into a two-branch network that incorporates expert knowledge and an optimized reward function to guide the training process. The data generated during the training phase are initially discretized into corresponding low-dimensional spaces. An “expert experience” module is introduced to facilitate the model’s early-stage training acceleration in the Epsilon–Greedy algorithm. To tackle navigation and obstacle avoidance separately, a dual-branch network structure is presented. We further optimize the reward function enabling intelligent agents to receive prompt feedback from the environment after performing each action. Experiments conducted in both virtual and real-world environments have demonstrated that the enhanced algorithm can accelerate model convergence, improve training stability and generate a smooth, shorter and collision-free path.

/pdf/improved-robot-path-planning-method-based-on-deep-34xfutms.pdf

Improved Robot Path Planning Method Based on Deep Reinforcement Learning

Using object detection techniques on immature fruits to find out their quantity and position is a crucial step for intelligent orchard management. A yellow peach target detection model (YOLOv7-Peach) based on the improved YOLOv7 was proposed to address the problem of immature yellow peach fruits in natural scenes that are similar in color to the leaves but have small sizes and are easily obscured, leading to low detection accuracy. First, the anchor frame information from the original YOLOv7 model was updated by the K-means clustering algorithm in order to generate anchor frame sizes and proportions suitable for the yellow peach dataset; second, the CA (coordinate attention) module was embedded into the backbone network of YOLOv7 so as to enhance the network’s feature extraction for yellow peaches and to improve the detection accuracy; then, we accelerated the regression convergence process of the prediction box by replacing the object detection regression loss function with EIoU. Finally, the head structure of YOLOv7 added the P2 module for shallow downsampling, and the P5 module for deep downsampling was removed, effectively improving the detection of small targets. Experiments showed that the YOLOv7-Peach model had a 3.5% improvement in mAp (mean average precision) over the original one, much higher than that of SSD, Objectbox, and other target detection models in the YOLO series, and achieved better results under different weather conditions and a detection speed of up to 21 fps, suitable for real-time detection of yellow peaches. This method could provide technical support for yield estimation in the intelligent management of yellow peach orchards and also provide ideas for the real-time and accurate detection of small fruits with near background colors.

/pdf/yolov7-peach-an-algorithm-for-immature-small-yellow-peaches-283bfu9k.pdf

YOLOv7-Peach: An Algorithm for Immature Small Yellow Peaches Detection in Complex Natural Environments

Study of convolutional neural network-based semantic segmentation methods on edge intelligence devices for field agricultural robot navigation line extraction

Ai Shu

Papers

Study of convolutional neural network-based semantic segmentation methods on edge intelligence devices for field agricultural robot navigation line extraction