Lupine Publishers Robotics Mechanical Engineering Journal: November 2021

Wednesday 24 November 2021

Lupine Publishers | Whishing You A Happy Thanksgiving Day

Gratitude is the inward feeling of kindness received. Thankfulness is the natural impulse to express that feeling. Thanksgiving is the following of that impulse.

Lupine Publishers | Robotics in Education and Training

Lupine Publishers | Advances in Robotics & Mechanical Engineering

Introduction

In Finland, a new teacher called Elias at primary school who has endless patience for repetition and never creates a pupil feel humiliated for asking same question again and again and can even do “Gangnam Style” dance. Elias is also robot. The Artificial Intelligence language machine includes a humanoid robot at primary schools in southern city of Tampere. This robot can able to understand and speak 23 different languages and it also allows to understand student’s requirements and helps to inspire learning. It recognizes student’s skill levels and adjusts its questions accordingly and gives feedback to teachers about pupil’s possible problems. Below are some of few from many applications of robots that can be used in education, teaching and training. [1].

Teaching Robots are More Consistent Teammates

Scholars at U.S. Army Research Laboratory and Robotics Institute at Carnegie Mellon University have created completely a new design to teach robots with innovative traversal behaviors with very low human intervention. This kind of technology allows portable platforms to navigate autonomously in various environments. Researchers focused their initial research and development in learning robot traversal performance with respect to robot’s visual perception of territory and objects in the environment; robot was trained how to navigate from various stand point in the environment while staying near the edge of the road and to traverse covertly using buildings as cover. As per scholars, these robots were given various mission tasks, the most appropriate learned traversal behavior can be started during operation of the mission. This can be accomplished by leveraging optimal control that is referred as inverse reinforcement learning, it is a class of machine learning that looks to recover a reward function. If a robot acts as a teammate, then multiple tasks can be achieved faster with better precision and more situational awareness can be achieved.” was confirmed by Wigness [2] (Figure 1).

Figure 1: Illustrates a small unmanned Clear path Husky robot, which was used by ARL researchers to develop a new technique to quickly teach robots novel traversal behaviors with minimal human oversight. Image Credit: US Army [2].

Robots Can Boosts Children’s Education

Educational Robots play a vital role in educating young people but may not replace human teachers completely. As per researchers, scientist say that social robots are demonstrating effective in teaching certain narrow subjects, for instance vocabulary or prime numbers. This study collected in concurrence with academics and involved a review of more than 100 published articles which have shown robots to be effective at increasing outcomes because of their physical presence. However, it also says that leading social robots into the school course would face significant logistical challenges and may carry risks with some children been seen to rely completely on the robots rather than simply using them when they are in difficulty. Authors of study also add “Considering practical considerations of introducing robots in education also brings ethical issues. For example, how far do we want the education of our children to be delegated to machines?” [3,4] (Figure 2).

Figure 2: Illustrates one of the robots used in the University of Plymouth’s Robo21c program, which aims to complement to the school curriculum by developing teachers’ skills and understanding of robotics and programming. Image Credit: University of Plymouth [4].

Programming Robots Just by Casual Talking

Robots are getting smarter day by day, but they still need step by step instructions for tasks they didn’t implemented before. For example, before you tell your household robot “make me a bowl of ramen noodles” you may have to teach it how to do that. Since we are not all computer programmers, we would prefer to give instructions in English just like we talk to a person. The robot may have built in programming language with look (pan); use (pan); carry (pan, water tap); fill up (pan, water); carry (pan, heater) and so on. In this research, this software convert’s human sentences such as “Fill a pan with water, put it on the heater, heat the water. When it’s in boiling state, add the noodles” in the robot language. If you had notice you never said, “Turn on the heater.” The robot has to be smart enough to fill in that missing step. The robot accomplished correctly up to 64 percent of the time even when the commands were varied, or environment was different; it was able to perform missing steps. That was three to four times better than previous methods, the researchers reported, but there is still room for improvement [5] (Figure 3).

Figure 3: Illustrates a computer science professor is teaching robots to understand instructions in natural language from various speakers, account for missing information, and adapt to the environment at hand. Image Credit: Image courtesy of Cornell University [5].

Robots and Kids Learn Together

The Robotic software is based on learning by teaching. When children experience problems in writing they may easily lose confidence and gradually lose interest in learning process. Eventually, their complete education can be affected. When students put themselves in the place of instructor and pass on what they know to their peers, they can regain self-esteem and motivation. Researchers constructed an advanced writing algorithm and implemented them on an existing robot model. With all these algorithms, machine can draw words on demand and then eventually improve. But to do, it uses a very vast database of handwriting examples, which allows it to reproduce common mistakes made by young children while learning. It can also be possible to program the robot so that it addresses the specific difficulties of a student, for example by drawing that is barely readable and improving its form over time. The robotic system is still in the prototype stage that has already been used in primary school lessons with around seventy students ranging from six to eight years old and then individually with a six-year-old child for one hour per week over one month [6] (Figure 4).

Figure 4: Illustrates Kids and robots learning to write together. Image Credit: Image from video courtesy of Ecole Polytechnique Fédérale de Lausanne [6].

Robotic Help for Deaf Children

Swivel is tunable robot which is placed on a tablet or iPad. It is placed in the classroom and turns to follow people talking. It then uploads video to a secure cloud for streaming. This novel device was developed by University of Manchester and their team to help assess classroom training for students on its deaf education course. This program requires trainees to be assessed in the classroom. The Swivl technology has been used in three locations with five students. The footage is then uploaded to the cloud and forms part of the external, independent assessment process. Then students were able to use the recordings to review their own work in the classroom and imitate on their learning – something that they cannot do on traditional placements. The team is estimating the experiences of both the students and supervisors in order to understand how they can improve and extend the use of the technology [7] (Figure 5).

Figure 5: Illustrates one of the trainees using the technology. Image Credit: The University of Manchester [7].

Read More Lupine Publishers Robotics Journal Articles:

https://robotics-engineering-lupine-journal.blogspot.com/

Tuesday 16 November 2021

Lupine Publishers | Robotic Farmers in Agriculture

Lupine Publishers | Advances in Robotics & Mechanical Engineering

Introduction

Revolution of Robotic farmer is on the way, fruit picking machines are ready to roll into the fields and will replace human workers at one point of time. A Robot Farmer is just a one of the new technologies that will completely transform agriculture sector. Today’s agricultural technology helps farmers to plow and spray crops. In an improved automation and big data analytics with farming robot technology are pointing out to big benefits. Goldman Sachs estimates precision farming – the combination of agriculture and technology could be around $240 billion market by 2050. As per Euro monitor intersection of robotics, artificial intelligence, analytics and machines for precision farming is one of the top industry’s top opportunities. In Europe, Spanish company called Agrobot has developed a strawberry farming robot. It uses up to 24 robotic arms to pick fruit and is capable of autonomous navigation. In England, Dogtooth Technologies are developing its own series of autonomous robots capable of picking fruit. Dogtooth machines are proficient enough of autonomous navigation, locating and picking ripe fruit and grading its quality [1] (Figure 1).

Figure 1: Illustrates Harvesting CROO’s machine is headed for farms in Florida and California. Image Credit: Image courtesy of Harvest CROO Robotics [1].

Robotic Weeders

The increasing recognition of robotic weeders for specialty crops has grown – Specialty crops are vegetables like lettuce, broccoli, tomatoes and onions. These are not produced in mass like corn, soybeans and wheat. The reason for robotic weeders steams from two major issues. One is a deficiency of herbicides available for usage in specialty crops. Another issue; as a matter of fact hand-weeding has become more and more expensive. Without pesticides, growers have had to hire people to hand-weed vast fields. Hand weeding is very slow and increasing expensive, it can cost around $150-$30 per acre. That is one of the reasons some people look to robotic weeders. The robotic weeders are programmed to recognize a pattern and can differentiate between a plant and the soil. Although, they currently are having trouble to differentiate between a weed and a crop. The robotic weeders in the market cost between $120,000 and $175,000, it is a better longterm option than expensive hand weeding. Fennimore considers that robotic weeders are the future of weeding for specialty crops. The reason because of higher labor costs and more incentives to grow organically with less pesticides. European growers have been using robotic weeders for a while [2] (Figure 2).

Figure 2: Illustrates robotic weeder is operating in a field near Santa Maria, CA. Image Credit: Image courtesy of Steven Fennimore [2].

Harvesting Cucumbers Through Robots

In automation areas for instance, automotive industry are not the only ones to depend on robots. In agriculture, automation systems are surpassing strenuous manual labor. As a project, the Fraunhofer Institute for Production Systems and Design Technology developed and tested a dual arm robotic system for automated harvesting of cucumbers. In Germany, cucumbers are ordained for pickles that are harvested with the aid of “cucumber flyers” – a farm vehicles with wing like add-ons. Many of the country’s agricultural regions subsequently face an uncertain future; cucumber farming has already begun moving to Eastern Europe and India. Thus, there is a pressing requirement for improved harvesting technologies to maintain economic viability of cucumber farming in Germany. Experts developed a dual arm robot system consisting of inexpensive light modules. This system is used for automated cucumber farming and other agricultural applications. This Robotic cucumber picker is cost effective, high performance and dependable. Even in adverse weather, it is capable of first identifying ripe cucumbers and then using its two gripper arms to gently pick and store them. This novel method can also make it possible for to imitate human movements. Scientist want to make sure that it does not damage crops or pull to their roots out of the soil. This robotic cucumber harvester is as efficient as its experienced human counterpart, who can pick as many as 13 cucumbers per minute. Cucumber farmers and agricultural associations have expressed significant interest in the dual arm robot [3] (Figure 3).

Figure 3: Illustrates prototype of the dual-arm robot system during the first field tests. Image Credit: Fraunhofer IPK [3].

Harvesting Broccoli using Robots

This Project was jointly funded by BBSRC and create improvements in United Kingdom; in this 3D camera technology was used to recognize and select whether broccoli is ready for collecting. It is the key step towards the development of an automatic robotic harvesting system for broccoli, which will not only considerably decrease production costs but also decrease amount of labor cost. This project also addresses challenges associated with recognition, deterrence and management of disease by creating diagnostic tools for farm use and substitute to chemical pesticides. This will allow the major producers in these industries to rapidly analyze the existence of disease and enable earlier decision making. It is also expected that this development of project will create long-needed substitute to use of pesticides by mushroom and potato industries therefore ensuring future sustainability [4] (Figure 4).

Figure 4: Illustrates the TerraSentia robot that autonomously monitors crops earned the best systems paper award at Robotics: Science and Systems, the preeminent robotics conference held in Pittsburgh. Image Credit: TERRA-MEPP Project [6].

Counting Crop Using Robots

Crop breeders run large scale of trials comparing thousands of varieties of crops over hundreds of acres and measure key qualities, for instance emergence of plant, height, by hand. This task is expensive, inaccurate, time consuming and completely inadequate; team can only measure these manually by fraction of plants in a field. TerraSentia is a compact transportable robot weight about 24 pounds and 13 inch wide. It can capture each plant from to bottom using advanced suite of cameras, deep learning and complex algorithms. Using a method called learning method, experts taught TerraSentia to count corn plants with just 300 images. It is a TERRA-MEPP research task that is low cost phenotyping robot to recognize top performing crops. This research was controlled by the University of Illinois in collaboration with Cornell University and Signetron with sustenance from Advanced Research Project Agency – Energy [5,6].

Combatting Weeds by Laser Robots

Farmers who want rich harvest and need to drive weeds so that crops can cultivate better. In organic agriculture – herbicides are not considered as they are toxic chemicals and only unwanted plants should be arduously weeded out. This time-consuming work are taken care of laser robots. Computer Experts in Photogrammetry at University of Bonn have developed a new system using advanced cameras on all terrain robot vehicle or tractor add-on and unwanted wild weeds are automatically identified in various crops and taken out. Scientists are moving forward for their startup to develop the business plan for this novel technology and also working to buy the parts required for the project to construct a prototype. At University of Bonn, Chamber of Commerce and Industry, both founders won an award for the best novel technology. “The aim is to contribute in achieving more sustainable agriculture. The robot fires the leaves of unnecessary plants in the crops with short laser pulses, which weakens in their strength” [7].

https://lupinepublishers.com/robotics-mechanical-engineering-journal/pdf/ARME.MS.ID.000125.pdf

https://lupinepublishers.com/robotics-mechanical-engineering-journal/fulltext/robotic-farmers-in-agriculture.ID.000125.php

For more Lupine Publishers Open Access Journals Please visit our website: https://lupinepublishersgroup.com/

Lupine Publishers Robotics Mechanical Engineering Journal