The boom in the electronics industry has made a variety of credit card-sized computer systems and plenty of accompanying sensing and acting elements widely available, at continuously diminishing cost and size levels. The benefits of this situation for agriculture are not left unexploited and thus, more accurate, efficient and environmentally-friendly systems are making the scene. In this context, there is an increasing interest in affordable, small-scale agricultural robots. A key factor for success is the balanced selection of innovative hardware and software components, among the plethora being available. This work describes exactly the steps for designing, implementing and testing a small autonomous electric vehicle, able to follow the farmer during the harvesting activities and to carry the fruits/vegetables from the plant area to the truck location. Quite inexpensive GPS and IMU units, assisted by hardware-accelerated machine vision, speech recognition and networking techniques can assure the fluent operation of a prototype vehicle exhibiting elementary automatic control functionality. The whole approach also highlights the challenges for achieving a truly working solution and provides directions for future exploitation and improvements.

No abstract

No abstract

Inspired by the mobile phone market boost, several low cost credit card-sized computers have made the scene, able to support educational applications with artificial intelligence features, intended for students of various levels. This paper describes the learning experience and highlights the technologies used to improve the function of DIY robots. The paper also reports on the students’ perceptions of this experience. The students participating in this problem based learning activity, despite having a weak programming background and a confined time schedule, tried to find efficient ways to improve the DIY robotic vehicle construction and better interact with it. Scenario cases under investigation, mainly via smart phones or tablets, involved from touch button to gesture and voice recognition methods exploiting modern AI techniques. The robotic platform used generic hardware, namely arduino and raspberry pi units, and incorporated basic automatic control functionality. Several programming environments, from MIT app inventor to C and python, were used. Apart from cloud based methods to tackle the voice recognition issues, locally running software alternatives were assessed to provide better autonomy. Typically, scenarios were performed through Wi-Fi interfaces, while the whole functionality was extended by using LoRa interfaces, to improve the robot’s controlling distance. Through experimentation, students were able to apply cutting edge technologies, to construct, integrate, evaluate and improve interaction with custom robotic vehicle solutions. The whole activity involved technologies similar to the ones making the scene in the modern agriculture era that students need to be familiar with, as future professionals.

SUMMARYThe paper focuses on the concept of the vertical handover (VHO) among collaborative wireless networks, which is the necessary driver for seamless mobility and thus for the ability of the user to be always best connected. The paper discusses the required enabling architecture for distributed VHO decision making that is based on the principles of the IEEE 1900.4 standard and on the key media-independent signaling procedure related to the IEEE 802.21 standard. The proposed framework combines the 'lower-layer' and 'higher layer' intelligence in a unified and media-independent way, to drive handover decisions based on rich terminal and network context information. The paper provides a detailed description of the VHO framework and of the key interactions between its key functional blocks. Additionally, the paper includes a series of validation results corresponding to an implementation of the presented framework. Furthermore, the paper includes a discussion comparing the capabilities offered by the proposed framework with those proposed by other similar proposals, which shows the potential benefits and tradeoffs of the introduced concepts.

Biomimetics is the interdisciplinary cooperation of biology and technology that offers solutions to practical problems by analyzing biological systems and transferring their principles into applications. This review article focused on biomimetic innovations, including bio-inspired soft robots and swarm robots that could serve multiple functions, including the harvesting of fruits, pest control, and crop management. The research demonstrated commercially available biomimetic innovations, including robot bees by Arugga AI Farming and the Robotriks Traction Unit (RTU) precision farming equipment. Additionally, soft robotic systems have made it possible to mitigate the risk of surface bruises, rupture, the crushing destruction of plant tissue, and plastic deformation in the harvesting of fruits with a soft rind such as apples, cherries, pears, stone fruits, kiwifruit, mandarins, cucumbers, peaches, and pome. Even though the smart farming technologies, which were developed to mimic nature, could help prevent climate change and enhance the intensification of agriculture, there are concerns about long-term ecological impact, cost, and their inability to complement natural processes such as pollination. Despite the problems, the market for bio-inspired technologies with potential agricultural applications to modernize farming and solve the abovementioned challenges has increased exponentially. Future research and development should lead to low-cost FEA robotic grippers and FEA-tendon-driven grippers for crop harvesting. In brief, soft robots and swarm robotics have immense potential in agriculture.

No abstract

No abstract