Рубрика: Robotics

The chaotic itinerancy is a closed-loop pathway through high-dimensional state space of neural activity, directing cortex in sequence with quasi-attractors.

Over the years researchers have created robotic models with attributes, similar to humans. Robotic models which can hear, sense, emotionally support, blink and fight against abuse, are getting heavily researched and deployed in the industry. To expand the further horizon of neuro-robotics, the researchers at the University of Tokyo have created a model that gives robotic AI spontaneous behavior through the chaotic itinerary, a neural process to find in humans and animals. The research paper titled “Designing Spontaneous Behavioural Switching via Chaotic itinerancy” states that the chaotic itinerancy is a high-dimensional non-linear dynamical system, which addresses the pre-existing challenges of cognitive architecture in robotics.

What is Chaotic Itinerancy?

The chaotic itinerancy is a closed-loop pathway through high-dimensional state space of neural activity, directing cortex in sequence with quasi-attractors. The quasi attractor is a region of the brain which has convergent flows as attractants and absorbents actions, and divergent flows, involve repellent and dispersive actions. These flows give ordered periodic activity and disordered chaotic activity between the regions of the brain.

Furthermore, experts have associated quasi-attractors with perception, thoughts, memories, thinking, speaking and writing. Researchers cite that robotics has applied a dynamical systems approach to analyze and control agents associated with training of robots. This approach collaborates the functional hierarchy and the elementary motion by expressing the physical constraints of the agent as the temporal lobe of the brain develops. Following this approach, CI is integrated into model spontaneous behaviors. Moreover, the researchers have proposed an algorithm that designs the properties of CI characterized by neuro-robotics context. This model addresses the challenges of designing a cognitive agent in the conventional context of robotics and artificial intelligence.

Structure of the Model

Researchers prepared a high-dimensional chaotic model, by embedding target quasi-attractors. They used an echo state network which is a form of Recurrent Neural Network and is heavily controlled by reservoir computing. Consequently, internal parameters were added to the model to generate intrinsic complex trajectories. These trajectories are generated by the initial chaotic system also known as innate trajectories which correspond to the types of the discrete input. Parallel to this, researchers trained a linear regression model which is named as readout that result in the designated trajectories known as output dynamics. These output dynamics is a resultant of exploiting the embedded innate trajectory.

Researchers say that this process can be applied to the other chaotic dynamical systems which are not limited to RNN in silicon since neither module nor hierarchical structures are required. Also, this embedding process is accomplished by modifying fewer parameters using the method of reservoir computing. The reservoir computing is an approach for making machine learning algorithms run faster, to expedite the computing process. Researches find this scheme to be more stable and less computationally expensive than conventional methods of back propagation to train the network parameters. Additionally, they added feedback classifier to the trained chaotic systems to autonomously generate specific symbolic systems.

Researchers suggest that two mechanisms are required for the successful designing of a CI model. The first is the differences among the trajectories are sufficiently enlarged through the temporal development to realize the stochastic symbol transition. A stochastic matrix is a square matrix that describes the transition of a Markov chain. A Markov chain is used to describe the sequence of possible events, where the probability of each event depends upon the state attained in the previous event. The second mechanism involves creating a spatiotemporal pattern to analyse the computing processes of the model. The Spatio-temporal pattern collects data across space and time and is utilized for by humans for solving multi-step problems by analysing the movement of objects in space and time.

Conclusion

Researchers say that this model will be helpful to understand the underlying mechanism of the brain’s information processing from a certain perspective. Furthermore, as the high-dimensional chaos has the rich expressive capability to design CI, henceforth, this model will aid in understanding the mechanism of the contribution of the high-dimensional chaos to the information processing in animal brains.

The post Synthesizing Robotic AI Spontaneous Behavior via Chaotic Itinerancy appeared first on Analytics Insight.

The global market for healthcare robots is estimated to increase by US$11.4 billion by 2020

Everyday technology is driving innovation in the healthcare sector. From inducing artificial intelligence into the diagnosis and detection of diseases to implementing machine learning algorithm for faster drug discovery, healthcare infrastructure is moving parallel to technological innovation. Robotics has become the heavily explored technology by healthcare professionals and MedTech executives to deliver the desired outcomes. Since, the evolution of the first robotic surgeon ‘da Vinci’ that performs general surgery, the global healthcare system is amplifying techniques where robotics can be deployed. Due to its accuracy and precision in performing surgical procedures, it has been favored over the conventional laparoscopic surgeries. Additionally, robotic surgeries explore the area and manoeuvre minute arteries and veins which is not possible to do in traditional surgeries. Henceforth, the demand for robotic surgeries has expedited over the years. For example, the utilization of robotics in performing inguinal hernia repair has surged over 38.1% from 2012 to 2018. As per a report by PwC, the global robot market including ‘care-bots’ could reach US$17.4 billion by 2020. Moreover, the market for healthcare robots is estimated to increase by US$11.4 billion by 2020. According to IndustryARC, surgical robots contribute as the largest component for medical robotics market.

Japan is listed as the top country heavily deploying robotics in the healthcare infrastructure. A report by PwC estimates the Japanese ‘care-bot’ market to grow from US$155 million in 2015 to US$3.8 billion by 2035.

Due to the success rate of robotic surgeries, many medtech enterprises and renowned healthcare organizations are exploring the possibility to induce robotic in other healthcare procedures. Medtech companies like Johnson and Johnson, Medtronic and Stryker, and Big techs like Apple and IBM have already entered the competitive race of robotic infrastructure in healthcare innovation. Moreover, the utilization of robotics is exceeded beyond the scope of surgical procedures. In medtech industry, robotics is heavily deployed to manufacture medical tools which are precise and accurate in carrying out pre-clinical procedures, labs, performing repetitive tasks, rehabilitation and aiding in patients’ care having long-term conditions. For example, RoBear is a robot which performs the task of lifting and moving the patients in and out of bed, in a wheelchair and prevents bedsores in patients who are advised for long term bed rest.

Additionally, there are many robots which aid the healthcare system. For example, KASPAR is a child humanoid robot that aids teachers and parents to support patients with autism. Giraff is another mobile communication robot that assists chronically ill-patients in dining. Toyota has created robots which aid immobilized patients to walk. Veebot is another robot that draws blood safely than a human.

Companies investing in Healthcare robots

Johnson and Johnson- This medtech organization has recently acquired Auris for innovations in bronchoscopic surgery. The company is also creating a robot that can perform orthopaedic surgical procedures. It is also working with Verb Surgical and Alphabet Inc to create a general robot with advanced visualization, machine learning, data analytics and connectivity.

MZOR- The Company is developing a robotic surgical guidance system known as Mazon Robotics Renaissance to transform free-hand spine surgery into the robotic guided procedure.

Titan Medical- The company is developing a robotic system known as Single Port Orifice Robotic Technology (SPORT) with 3D vision and instrument control technology which aids in minimally invasive procedures for general, abdominal, gynecologic and urologic surgeries.

Hensen Medical- The company is investing to develop a robotic system known as the Magellan Robotic System that aids in controlling, monitoring, manipulating and positioning the catheter in the patients.

Challenges for Healthcare infrastructure

While medical robots are heavily researched and developed, certain challenges are hindering the medtech and healthcare sector to fully utilize these robots.

1. Cost-effectiveness: Apart from the dearth of highly skilled individuals, lack of funds is listed amongst the biggest challenge for healthcare and medTech infrastructure, to fully utilize the benefits of robotics. Most hospitals are seeking cost-effectiveness. As the cost of this new-edge technology is significantly high, medium and low-budgeted healthcare institutes covet from deploying robotics in operations.

2. Data sharing- Data sharing is another concern which paralyses the scope of robotics in healthcare infrastructure. A PwC report points out that more than 30 trillion gigabytes of unexplored medical data is generated every year. This data is in the form of published articles, research, and patient’s demographic data. However, the utilization of this data is limited, due to the strict data regularization policies in many institutes.

3. Highly skilled Individuals- Like mentioned earlier, healthcare infrastructure is plagued with the challenge to have sufficient professionals in working. The COVID 19 pandemic has revealed this bitter reality to the world. Though robotics is utilized in medical surgeries and pre-clinical procedures, the dearth of medical professionals is significantly impacting the utilization of technologically-advanced resources.

Future of Robotics in Healthcare Institutes

Undoubtedly, the scope of healthcare in medical institutes is positive. But the global healthcare systems must address the challenges hindering the deployment and utilization of robotics in medical procedures. Creating awareness about these procedures amongst healthcare professionals and patients will aid in seeking maximum benefits from this new-edge technology.

The post How Robotics is Refurnishing the MedTech and Healthcare Sector? appeared first on Analytics Insight.

The approach used by three universities conflates magnetic fields and robotics to transport drugs across human body.

Robotics is a technology, heavily explored by the healthcare sector. Due to its robust system, it has become the most desired and favored technology for medical inputs in the 21st century. From introducing the first robot ‘da vinci’ for performing the general surgical procedures to incorporating robots for assisting the patients, diagnosing the disease, and performing laboratory procedures, robotics has expanded the scope of medical care. The global healthcare robotics market is expected to grow from US$11.4 billion by 2020. A report by PwC states that surgical robots own the largest contribution for the robotics-driven healthcare market. Additionally, a report by the Frost & Sullivan points out that the global ‘robots for personal care’ market could reach US$17.4 billion by 2024.

Purdue University

In a potential breakthrough, the researchers at Purdue University have created tiny bots that can travel across human body through tumbling. The research paper titled “A Tumbling Magnetic Microbot System for Biomedical Applications” is published in MDPI.

The research paper states that the robotic system comprises of untethered magnetic microbot, a two-degree-of-freedom rotating permanent magnet, and an ultrasound imaging system for in vitro and in vivo biomedical applications. The tiny robot functions through an external magnetic field so that it can safely penetrate different mediums across different organs. The researchers cite that the microrobot tumbles end-over-end in a net forward motion due to applied magnetic torque from the rotating magnet. By turning the rotational axis of the magnet, two-dimensional directional control is possible and the microrobot gets steered along various trajectories, including a circular path and P-shaped path.

David Cappalleri, a Purdue associate professor of mechanical engineering states, “When we apply a rotating external magnetic field to these robots, they rotate just like a car tire would to go over rough terrain. The magnetic field also safely penetrates different types of mediums, which is important for using these robots in the human body.”

The research is initially carried out in mice for transporting medicines to the colon, where the robot is used as a drug-transport tool. Through this, the drugs get directly delivered to the desired organ, without penetrating other organs, thus eliminating adverse reaction or side-effects due to drugs. The research paper states that the microrobot is capable of moving over the unstructured terrain within murine colon in vitro, in situ, and in vivo conditions, as well as a porcine colon in ex vivo conditions.

Additionally, high-frequency ultrasound imaging allows for real-time determination of the microrobot’s position while it is optically occluded by animal tissue. The robot is coated with a fluorescein payload, to release the majority of the payload over a 1-h time period in phosphate-buffered saline. The tests such as Cytotoxicity which were performed to determine the adverse affects of robots on human body, did not show a statistically significant difference in toxicity to murine fibroblasts from the negative control, even when the materials were doped with magnetic neodymium microparticles. Furthermore, when seeded with murine fibroblasts, all material variants of the microrobot exhibited cell proliferation, with no statistically significant difference in toxicity compared to the negative control sample collected by the researchers. Hence, the microrobot system’s capabilities make it promising for targeted drug delivery and other in vivo biomedical applications.

Researchers say that this approach can be used to perform minimally invasive procedures, where the target location is far from the point of entry.

Ohio State University and Georgia Tech

However, this is not the first time that microbots were incorporated into human body for performing biomedical procedures. Researchers from the Ohio State University and the George Institute of Technology have discovered a way through which tiny robots can transport across human body for treatments of colon polyps, stomach cancer, and aortic artery blockages. The study titled, “Untethered Control of Functional Origami Microbots with Distributed Actuation”, is published in the proceedings of the National Academy of Sciences. Researchers have created a soft robot made with magnetic polymer, a soft composite material embedded with magnetic particles that can be controlled remotely.

Reena Zhao, the corresponding author of the paper and assistant professor of Mechanical and aerospace engineering states, “The robot is like a small actuator, but because we can apply magnetic fields, we can send it into the body without a tether, so it’s wireless. That makes it significantly less invasive than our current technologies.”

She further adds, “In biomedical engineering, we want things as small as possible, and we don’t want to build things that have motors, controllers, tethers, and things like that. And an advantage of this material is that we don’t need any of those things to send it into the body and get it where it needs to go.”

Researchers cite that the soft origami robots have the capability to conduct multiple treatments, while independently controlling the folding and deploying of the origami units. The origami units unfurl and release the drugs at the necessary site of the body. Though the research is not performed in the human body, the researchers are positive that this approach will allow the doctors to perform minimally invasive procedures through robotics.

Conclusion

Minimally invasive procedures are the most favored surgical approach among healthcare professionals. However, due to limited resources, this area has been less explored by scientists and experts. Additionally, earlier the scope of the magnetic field in medicine was confined to conducting MRI and CT-scan. By integrating the magnetic field with robotics, researchers have opened the doors for surgical procedures.

The post Three International Universities Drive Breakthrough in Minimally Invasive Robotics Surgical Procedures appeared first on Analytics Insight.

Robots to enable the next Disruptive Tech Wave in Recycling

The world is a gigantic landfill! Everyday tons of waste are generated from various households, hospitals, industries, construction and demolition sites and more. While today we have numerous ways to get rid of the accumulated waste, it still ends up affecting the safety and sustainability of the ecological system. Therefore, the best alternative is to reuse and recycle as much waste as possible. And offering an extra pair of hand in this are waste sorting and recycling robots.

Robotics led-automation has seeped through every industrial sector and routine tasks. Now robots are rapidly disrupting recycling industry too. These robots are adept at multitasking, scalable and have integrated learning systems that can function tirelessly 24/7. This implies they can be extensively deployed for waste processing and recycling in a cohort of industries. These recycling robots are fast, accurate, and can process a heavy load of waste material. Moreover, they have a high number of picks per hour, and can work in different shifts with the same accuracy.

The Pioneers

In 2011, the Finnish company ZenRobotics ventured into the automated waste management with their robotic waste sorter. The company’s system uses robotic arms suspended from a framework above conveyor belts. This system is equipped with an assortment of computer vision, machine learning, artificial intelligence (AI) to run synchronized robotic arms to sort and pick recycled materials from moving conveyor belts. Each arm has a pincher to grab and toss material into chutes after sorting items using real-time data from metal sensors, 3D laser cameras and spectroscopic cameras.

Appingedam, Netherlands-based Bollegraaf Recycling Solutions, which started experimenting with concept of recycling robots in 1990s, also uses a combination of near-infrared and height cameras to identify items by material and through 3-D detection.

AMP Robotics’s Clarke

In US, the first waste sorting robot Clarke was installed in 2016, by Denver-based AMP Robotics who had trial tested its robot at Alpine Waste & Recycling’s Altogether MRF (Materials Recovery Facility) near Denver. Clarke leverages AI software (AMP Neuron platform) to distinguish a wide variety of food and beverage cartons so it can grab and separate them from the rest of the recycling. By the following year Clarke had improved its recycling skills, grabbing approximately 60 cartons per minute with near perfect accuracy.

MIT ROCycle

Since then the trend of recycling robots continues to build. And behind this milestone, is a combined effort of researchers bridging mechanical, magnetic and laser-optical techniques to achieve this end goal. Last year, MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) developed a recycling robot, ROCycle, which relies on sensors in its Teflon hand to determine the nature of an item and sort it accordingly. The inspiration behind ROCycle was born out of a preoccupation for the human workers sorting through rubbish on dirty and, often, unsafe conveyor belts. ROCycle’s tactile strain sensor gauges an object’s size, while two pressure sensors determine how squishy that object may be, whether it’s easily-crushed paper or more rigid plastic. Due to the conductive nature of the sensors, it can also detect the presence of metal.

As per official sources of MIT, ROCycle has an 85% success rate when objects are stationary, however if the conveyor belt is in motion, it drops to 63%. Further, when set to differentiate between hard and soft objects, ROCycle has a 78% pass rate. On the other hand, ROCycle is almost completely resistant to sharp materials since it displayed negligible structural damage during the trial period.

Current Market

Today, apart from ZenRobotics, companies BHS with its MaxAI systems, Machinex with its SamurAI line of sorting machinery have achieved huge success rates with a healthy ROI. These companies are moving with impressive speed toward improving capabilities, deploying machinery and boosting revenue. Forbes estimates that revenue of AMP Robotics will reach US$20 million by year end, which is double of its US$10 million revenue, last year. Recently, it received its largest purchase order (24 machine learning-enabled robotic recycling systems) from the publicly traded North American waste handling company Waste Connections. These robots will be used on container, fiber and residue lines across numerous materials recovery facilities.

Apple’s Dave and Daisy

Meanwhile, the recycling robots are not only concentrated at MRFs, some are also deployed at disassembly lines and manufacturing industries too. For, e.g., Apple’s Dave and Daisy. Dave is a new robot recycler announced this year, while Daisy is a disassembly robot which launched in April 2018. A single Dave robot can process up to 800 modules per hour. It disassembles iPhone’s Taptic Engine, which is the part of the device responsible for the touch screen sensations and vibrations users feel when using their iPhone. Daisy, is tasked to break apart iPhones to extract minerals (like aluminum, gold, silver, copper, tin, cobalt, and other rare earth elements) for recycling from the iPhone Battery. Daisy robots can deconstruct 15 total iPhone models, and take apart up to 200 iPhones per hour.

The post How Recycling Robots are Transforming the Waste Management Industry appeared first on Analytics Insight.

Behavioral teleporting consists of real-time transfer of the complete ethogram of live specie onto a remotely-located robotic replica.

Researchers at the NYU Tandon School of Engineering are working on an approach called Behavioral Teleporting for understanding the social and behavioral interactions between different species, especially humans and robots. The research titled ‘Behavioral Teleporting of Individual Ethograms onto inanimate robots: experiments on social interactions in live Zebrafish” is published in the Cell Press Journal/iScience.

What is Behavioral Teleporting?

Professor Maurizio Porfiri of NYU Tandon has devised the new approach of interaction between two separated Zebrafish so that insight regarding influence in social behavior can get drawn. The researchers have used behavioral teleporting as a solution to manipulate underpinning social interactions. Behavioral teleporting consists of real-time transfer of the complete ethogram of live specie onto a remotely-located robotic replica. Researchers have chosen Zebrafish, freshwater specie, for its amenable behavior and to disentangle the gene and environment interactions, whereby their genome is fully sequenced and modifiable through gene-editing procedures. Likewise, Zebrafish has displayed well-documented performance in pharmacological treatments targeting a given biological pathway. Within the field of social interactions, Zebrafish are employed to investigate both normal behaviors and abnormal derailments.

The researchers cite that biologically-inspired robots offer a promising alternative to virtual reality by affording the delivery of physical, easily controllable, three-dimensional stimuli. The new approach is related to two breakthroughs of social interactions. The first one by Bonnet and collaborators demonstrated a link of remote interaction between Zebrafish and honeybees by controlling the zebrafish replica through the spatial density of honeybees and the bee-robot through the swimming direction of Zebrafish. The second demonstration by Larch and Baier explored the possibility of establishing remote social interactions between Zebrafish within a virtual reality setup, wherein projected dots instantaneously replicated the motion of independent subjects located in different tanks.

The System

The researchers have established a setup consisting of two separate tanks, each containing one fish and one robotic replica. An automated tracking system tracked each of the live subjects’ locomotory patterns, which controlled the robotic replica swimming in the other tank. The complete ethogram of each fish was transferred across tanks within a fraction of a second, thus establishing a complex robotics-mediated interaction between two remotely-located live animals. An ethogram is a table of all distinct and independent behaviors of interest observed in the study species so that data collected can be accurate.

Results

Researchers say that they were able to achieve the primary aim of the experiment to demonstrate the capability to transfer the motion of a live fish onto a robotic replica. The new approach was able to maneuver the replica located at the separate tank through an in-house developed robotic platform. The success of the replica mirroring the motion of a live animal was assessed by cross-correlating their trajectories. The results indicated the success of 85% with 95% accuracy at a maximum time-lag smaller than 0.2 s. The high accuracy in replicating fish trajectory was confirmed by equivalent analysis on speed, turn rate, and acceleration. The researchers conclude that behavioral teleporting can preserve natural interaction between two live animals while allowing fine control over morphological features that modulate social behavior.

Maurizio Porfiri states, “Since existing approaches involve the use of a mathematical representation of social behavior for controlling the movements of the replica, they often lead to unnatural behavioral responses of live animals. But because behavioral teleporting ‘copy/pastes’ the behavior of a live fish onto robotic proxies, it confers a high degree of precision with respect to such factors as position, speed, turn rate, and acceleration.”

The post Understanding Social Interaction in Robots through Behavioral Teleporting appeared first on Analytics Insight.

Automation empowers machines to play out specific operations. This chops down the amount of human work required.

Disruptive technologies like advanced analytics, advanced robotics, big data, learning machines, the internet of things, 3D printing, and wearables are finding their way into production lines.

Notwithstanding the sluggishness of progress on today’s plant floors, the digital wave is gradually changing assembling, adding to significant productivity improvements and the rise of innovative production paradigms that deliver more customized and proficient solutions.

In the interim, automation is the innovation that empowers machines to play out specific operations. This chops down the amount of human work required.

“A few jobs are unhygienic and dangerous, and they are not appropriate for laborers,” clarifies Crystal Fok, an Associate Director of MPE Cluster and Robotics Platform. A robotic arm or machine, then again, can do menial tasks significantly more productively than a common human laborer.

However, don’t freeze. Robots may have favorable advantages over human workers in certain zones, yet they won’t supplant people totally. When we consider robots taking our positions, we layer on a dream of humanoid androids in a real sense managing the responsibilities we’re doing. While there is a lot of theory around this sort of usurping, we should think somewhat a bit smaller in scale. From an actual perspective (a robotic arm), robotics and artificial intelligence have already been woven into businesses like healthcare and retail. This has changed the workforce, as it has moved around the execution of robotic assistance.

The smaller-scale applications of robotics, for example, AI-upgraded call centers, are the ones wherein a large portion of us will be working. Inside these call centers, AI can fill in as chatbots, voice routing systems and customer-service-enhanced servicing. It will empower customer service agents to be human when required, while directing and analyzing information to serve both the customer and client. It will be the same for some businesses integrating AI systems to deal with large sets of data and monotonous undertakings once in the past taken care of by groups of people.

Practically every robotic process or automation makes a new job for a human. The new typical demands human oversight for automated implementation as well as correlative jobs that will see human positions made to work related to these alleged robots. Artificial intelligence should be trained, delivery robots should be kept up, etc. It is not necessarily the case that the jobs robots will be taking over are not worth the human effort to keep for as long as possible.

To appropriately handoff task-oriented and functional jobs to automation, they should be contemplated, rehearsed and broken down into singular bits of information that could then be automatically trained to an AI framework or actual robot. With an AI framework, that training would advance into machine learning that should be checked and documented for future use cases and applications.

There are numerous positions that actually require human administrators,” guarantees Terry Chang, Engineering Director at New World CAD/CAM Development Ltd. Machines will just be utilized to do the truly difficult work or work under high temperatures, forestalling any possible wounds to human workers.

Later on, Fok adds, work environments will concentrate more on robot-human collaboration instead of robots that can only do similar guidelines over and over. The expectation is that androids and people will have the option to work together.

New innovation may supplant some human jobs, yet it likewise makes new job opportunities. Numerous organizations are needing engineers and IT experts. To plan new generations for the sorts of jobs that people will do later on, Wu trusts it is “truly critical to pull together education [towards] things that humans value culturally rather than only the drilling of technical skills”.

“The greater innovativeness a job requires, or the more it has to do with human experience, the more outlandish that it will be relegated to a robot”, says Wu Dekai, Professor of Computer Science and Technology at the Hong Kong University of Science and Technology. So regarding profession pathways, occupations, for example, artist, songwriter, and actor are bound to last more than an assembly line laborer. Yet, different jobs include creativity, as well. Advertising, for instance, requires a comprehension of human needs constantly.

The post Don’t Worry If Robots Will Take Our Jobs. Here’s Why? appeared first on Analytics Insight.

The new system addresses the existing challenges of reinforcement learning in robots.

Researchers at the University of Southern California (USC) have developed a system that can perform complicated tasks with only a few demonstrations. The research paper titled, “Learning from Demonstration Using Signal Temporal Logic”, was presented at the Conference of Robot Learning last week.

The research paper cites that the system addresses the existing limitations of reinforcement learning in robots such as imperfections, safety, and interpretability. Researchers have used Signal Temporal logic-so that robot can learn tasks such as driving a car and cooking the food from only a few demonstrations.

Aniruddh Puranic, a PhD student in computer science at the USC Viterbi School of Engineering and the lead author of the research says, “Many machine learning and reinforcement learning systems require large amounts of data and hundreds of demonstrations—you need a human to demonstrate over and over again, which is not feasible,”

Limitations of the existing Learning from Demonstration (LfD) model

The existing learning-from-demonstration-model in robots involves reinforcement learning. Over the years existing LfD has enabled researchers to draw insights on specifications of the robot. However, there are certain limitations to this model:

• The control policy of the existing LfD model is unsafe and lacks robustness.
• Not all demonstrations are equal. While some demonstrations can indicate desired results, others need human-assistance to deliver quality results.
• Lack of required metrics to evaluate the quality of demonstrations or tasks adds to the third challenge of LfD.
• Since demonstrations do not have specific safety conditions for the robot, the demonstrations get optimized to achieve a particular objective.

Features of the new system

Introduced by Arthur Prior under the name Tense Logic in 1960, the Signal Temporal Logic is a mathematical language that enables robotic reasoning about current and future outcomes.

Researchers have earlier used STL in cyber-physical system applications such as robots and self-driving cars, to evaluate the logic and reasoning during an emergency. The existing STL system delivers positive outcomes for evaluating the temporal behaviour in robots such as the multi-dimensional signal consisting of the robot’s position, joint angles, angular velocities, and linear velocity, amongst others.

It also evaluates and automatically rank demonstrations based on their fitness of the specific task performed, and enhance the control policy in robots. This system also estimates the quality of demonstrations so that robots cannot learn from undesired examples.

The researchers states that “The key insight of this work is that the use of even partial STL specifications can help in a mechanism to automatically evaluate and rank demonstrations, leading to learning robust control policies and inferring rewards to be used in a model-free RL setting.”

Unlike the traditional model, this system enables the robot to learn from both its success and failure, with only a few demonstrations. Through this system, the robots can learn and perform the task without requiring logic and can draw out its conclusion about the performance.

The researchers conclude that this approach will provide new directions for safety and interpretability of robot control policies and verification of model-free learning methods. It is also well suited for applications where the maps are known beforehand but there exist dynamic obstacles in the map, such as for robots in household and warehouse environments, space exploration rovers, etc.

The post Can Robots Learn Complicated Tasks from Few Demonstrations? appeared first on Analytics Insight.

As the COVID-19 pandemic has altered the organizational workflow, automation has acted as a savior for the industry.

Robotic Process Automation is a technology which learns and mimics human tasks and integrates the tasks across digital systems so that the business process gets automated. An RPA bot accumulates the data through the user interface and interprets responses for performing repetitive tasks. Due to its non-intrusive nature and capability to not disrupt while processing, the RPA is utilized heavily across various industries. It also increases and efficiency in performing the tasks.

Gartner defines RPA as “A productivity tool that allows a user to configure one or more scripts or bots to activate specific keystrokes in an automated fashion.”

The global RPA market size is estimated to reach US$2.5 billion by 2022 at a CAGR of 30.14% between 2017-2022. A report by PwC states that automation will be the most trending technology for the coming decade. As the pandemic has altered operations in organizations, automation has acted as a savior for the industry.

RPA in Banking and Finance

In Banking and Finance, the RPA bots integrated into the software are performing redundant tasks, thus enabling humans to focus on tasks demanding their skills. With increasing COVID cases, the demand for financial assistance has also soared. As the world is already witnessing economical uncertainty, many people are reaching out to banks for financial aid which has piled the loan and insurance applications across banks and insurance companies. Since pandemic has pushed most banks to have a limited workforce, automation is assisting in relieving the workload. By embedding RPA bots across the complex business calculations in loan processing, banks can reduce the period of loan cycles and loan decisions. This means that loans that earlier used to take months to be approved can now be approved faster by analyzing the automated details of the customer.

Additionally, automation is also helping with customer services. Through KYC, the banks are now able to validate the customer’s data with the previous records. This is specifically useful in tax collection, insurance claims and underwriting.

RPA in Supply Chain

The supply chain is listed as amongst the most impacted sector due to COVID 19 outbreak. As organizations stalled their operations, a significant impact is observed across the global supply chain. By integrating the RPA robots, the supply chain companies have automated the order processing and payment. Companies like Greif and Ascension health have already deployed RPA to sustain the impact of coronavirus.

Additionally, RPA across the supply chain is also crucial in monitoring the procurement risk, scheduling transportation, managing the logistics and managing the inventory tools. Organizations are now deploying automation tools, to minimize the risk, improve product performance and eliminating procurement costliness.

RPA in Healthcare

Due to COVID, the healthcare sector has witnessed an increase in demand for a manual workforce. This means that every individual across healthcare institutes are required to contribute to strategically sailing through the crisis. At this time, maintaining and monitoring the data is observed as a task that demanded efficiency and accuracy. Henceforth, many healthcare institutes have resorted to automation for managing inventory, digitizing patients file, carrying out the billing process and scheduling appointments.

The post Robotic Process Automation is Driving Enterprises during COVID-19 Pandemic appeared first on Analytics Insight.

Demand for robotics experts is skyrocketing year over year

With the world entering the industrial revolution age, the use of automation and advanced technologies are surging exponentially. This increase in usage is not only delivering convenience but also creating new job opportunities. Robotics emerges as one of the vital fields to pursue a career. According to a report, the global robotics market is expected to reach US$210 billion by 2025, up from US$100 billion in 2020, growing at a CAGR of around 26%. The market is growing largely thanks to its implementation in industries including healthcare, retail, defence, aerospace, automotive and infrastructure, among others.

Such usage of robots would significantly intensify the number of robotics job opportunities available for the human workforce.

Let’s have a look at the list of top robotics jobs in India in December 2020.

Accenture

Job Role: Microsoft Robotic Process Automation Application Developer

Location: Pune

Job Description:

Candidates for this role will be responsible for UiPath Process Automation Development; infrastructure setup and management for the UiPath application; interacting with BAs, PM and business to understand the processes to be automated. They will require performing technical feasibility check for the process to be automated; and providing design and development estimations for the processes to be developed.

Requirements:

• 4 years of experience in RPA UiPath development

• In-depth knowledge and exposure of RPA and UiPath tool

• Experience throughout the entire RPA project lifecycle

• Good Communication skills

• Minimum of 15 years of Education

Apply here

NICE Actimize

Job Role: Robotic Automation Engineer

Location: Pune

Job Description:

Robotic Automation Engineers will be responsible for understanding detailed requirements for functional and flow to automate web applications and backend services. They will require to review stories in detail to participate in grooming, sprint planning, and assess automation efforts; performing hands-on automation execution; work closely with PM and Developers to deliver high-quality releases for production.

Requirements:

• Demonstrated ability to design and configure automation using a variety of technical skills (e.g. Pure webservices, SQL-based data conversions, UI, etc.).

• Experience working as part of a team on large scale IT customization and implementation projects.

• Experience in Java, JavaScript and Python programming language will be an added advantage

• Prior experience working with Selenium & Robot Framework will help

• BE/BTech in CS or equivalent with overall 7+ years of experience and recent track record in Automation planning and execution of mission-critical multi-tenant SaaS applications.

• Hands-on project experience of one of the leading Robotic Process Automation (RPA) tools like Automation Anywhere, UI Path, Blue Prism, APA, etc.

Apply here

IBM

Job Role: Automation Engineer

Location: Bangalore

Job Description:

The Automation Engineer will work for the Local Apps Squad in CIO Network Engineering Deploy ISA, with a particular focus on development, deployment and rollout of Local and Global CIO programs as necessary in support of Network Engineering initiatives deployment for the ISA/APJ Market.

Requirements:

• Total experience of 8 to 10 years with minimum 5 years of relevant experience in Application Development using Python, Flask Framework, Docker Containers, REST APIs

• Working knowledge of Agile Framework

• Knowledge of Networks Infrastructure which includes, but not limited to, LAN / WAN and other Voice and Data networking technologies

• Along with technical skills, knowledge and experience in Relational and NoSQL Databases, Structured Query Language, UI Development, IBM standards for application development, ITSS Security Compliance Standards are beneficial.

• Working knowledge of Agile project management and experience in using Project Management/Agile Tools like Jira

Apply here

Rapyuta Robotics

Job Role: Software Engineer I – Robotics

Location: Bangalore

Job Description:

For this role, candidates’ responsibilities include, but are not limited to, collaborate in a team to design, develop, integrate and maintain a robust team of autonomous robots in semi-structured and dynamic environments. They will need to contribute to the deployment and testing of system; identify bottlenecks and bugs, and devise solutions to these problems; and contribute to software design reviews, architecture reviews, and best practices.

Requirements:

• Bachelor’s degree in Computer Science, or a similar technical field of study, or equivalent practical experience with an outstanding track record

• Demonstrated ability to design, implement, and test scalable and highly available software systems in a fast-paced environment

• Strong proficiency in C++, with a fair knowledge of the language specification and at least 1-2 years of hands-on experience

• Computer Science fundamentals in algorithm design, problem-solving, and complexity analysis

• Strong communication skills and ability to work well in a team environment

Apply here

NVIDIA

Job Role: Senior System Software Engineer

Location: Pune

Job Description:

As a part of NVIDIA’s GRID Software team, the candidate will require to design, architect, prototype and implement complex Windows services and applications. They will work closely with partners, UX and UI designers on new products or features/improvements of existing products. They will also need to deliver solid code and working features that provide the appropriate level of security, performance, reliability and scalability, and provide technical leadership to fellow engineers, designers, and partners to develop, review and maintain the product.

Qualifications:

• 7+ years of proven experience in C / C++ / VC++, Windows API (Win32 Programming), Windows Socket Programming, Multi-threading, COM / DCOM-ATL, STL.

• Proven track record of work on Windows OS with in-depth knowledge of Windows Internals.

• 7+ years of hands-on experience in Windows Programming & debugging Windows applications using various debugging tools (e.g. WinDbg, Visual Studio, Sysinternals Suite, etc).

• Strong knowledge of Data Structures, Algorithm Design, Design Patterns and OOP concepts.

• Strong knowledge of user space application concepts such as multi-threading, synchronization, IPC/RPC, etc.

Apply here

SAP

Job Role: Developer (Java and JavaScript), SAP Intelligent Robotic Process Automation

Location: Bangalore

Job Description:

As a developer, the candidate will be responsible for designing, coding and testing specific product features in a development team. He/she has to take full responsibility for accepted tasks and demonstrate a high level of quality, speed, reliability and efficiency. They will need to analyze and solve issues in existing and new code while working closely with the team to ensure team success. They will also need to develop a functional knowledge of the overall product and support customers and partners when required.

Qualifications:

• University Degree in Computer Science or related technical areas with a minimum of 3 years of experience

• Proficiency with Java and fundamental front-end languages such as HTML, CSS and JavaScript

• Good understanding of object-oriented design principles and design patterns

• Familiarity with RESTful web-services using Java Spring Boot or similar frameworks/tools /Familiarity with Node.js

• Familiarity with Cloud Foundry and/or SAP Cloud Platform

• Good to have some knowledge of database technology such as MySQL, PostgreSQL and MongoDB.

Apply here

The post Top Robotics Job Opportunities in India for December 2020 appeared first on Analytics Insight.

Tunable flexibility permits a robot to change its stiffness dependent on the job needing to be done

Examinations in robotics have been essentially coordinated toward the design of robots with a huge degree of knowledge, capable of high adaptability. Nonetheless, almost no examination has been done on the design of a robot manipulator as an executive mechanism of the intelligent control system, whose top-notch configuration will permit the modern capacities forced by the control framework.

Exploratory examinations of robot precision show unsatisfactory outcomes which limit their future wider application. This is the reason behind why the off-life programming of robots has not been generally utilized, without which it is difficult to envision a more significant integration of robots in the CIM environment.

Reasons for the low degree of robot precision are underscoring the non-corresponding choice of the robot coordinate system, algorithmic and computational mistakes and drive and transmission element design. Comparison with corresponding results picked up from examinations of CNC machine tools can’t be dodged on account of the way that robots are additionally machines from which precision is required. What is absent in robotics today, however which unavoidably is required, is the foundation of a standard methodology for testing robot accuracy and other performance.

New research shows that curved origami structures have dramatic ramifications in the improvement of robotics going ahead, giving tunable adaptability, the capacity to change stiffness based on the function that verifiably has been hard to accomplish utilizing a simple plan.

The research by Arizona State University exhibits how curved origami structures can prompt tunable flexibility in robots. Tunable flexibility permits a robot to change its stiffness dependent on the job needing to be done, which in the past has demonstrated to be hard to execute with simple designs.

Hanqing Jiang is a mechanical engineering professor at the college and lead creator of the paper named “In Situ Stiffness Manipulation Using Elegant Curved Origami.” The work was published in Science Advances.

“The consolidation of curved origami structures into robotic design gives a surprising chance in tunable flexibility, or solidness, as its complementary idea,” Jiang said. “High flexibility, or low stiffness, is similar to the delicate landing navigated by a cat. Low flexibility, or high stiffness, is like executing a hard bounce in a pair of stiff boots.”

Robotics technology requires an assortment of stiffness modes: high inflexibility is important for lifting loads; high flexibility is required for impact retention, and negative firmness, or the capacity to rapidly deliver stored energy like a spring, is required for run.

Generally, the mechanics of obliging inflexibility variances can be massive with ostensible territory, while curved origami can minimalistically uphold an extended stiffness scale with on-demand flexibility. The structures shrouded in Jiang and team’s research consolidate the collapsing energy at the origami wrinkles with the bending of the panel, tuned by switching among numerous curved creases between two points.

Curved origami empowers a single robot to achieve a variety of movements. A pneumatic, swimming robot created by the team can achieve a scope of nine distinct movements, including quick, medium, slow, straight and rotational developments, by essentially changing which creases are utilized.

The team’s exploration centered around joining the folding energy at origami creases with the board bending, which is tuned by moving along various creases between two points. With curved origami, a single robot is equipped for undertaking different movements. For instance, the team built up a swimming robot that had nine unique movements, for example, quick, slow, medium, straight, and rotational. To achieve any of these, the creases simply should be changed.

Other than robotics technology, the standards spread out in exploration could help design mechanical metamaterials in electromagnetic, automobile, and aerospace industries. It could likewise end up being valuable in the formation of biomedical devices.

“The excellence of this work is that the design of curved creases, and each curved crease corresponds to a particular flexibility,” Jiang said.

The study was funded by the Mechanics of Materials and Structures program of the National Science Foundation. Creators added to the paper are Hanqing Jiang, Zirui Zhai and Lingling Wu from the School for Engineering, Matter, Transport and Energy, Arizona State University, and Yong Wang, Ken Lin from the Department of Engineering Mechanics at Zhejiang University, China.

The post Robots Can Now Have Tunable Flexibility and Improved Performance appeared first on Analytics Insight.