Tag Archives: five

#436437 Why AI Will Be the Best Tool for ...

Dmitry Kaminskiy speaks as though he were trying to unload everything he knows about the science and economics of longevity—from senolytics research that seeks to stop aging cells from spewing inflammatory proteins and other molecules to the trillion-dollar life extension industry that he and his colleagues are trying to foster—in one sitting.

At the heart of the discussion with Singularity Hub is the idea that artificial intelligence will be the engine that drives breakthroughs in how we approach healthcare and healthy aging—a concept with little traction even just five years ago.

“At that time, it was considered too futuristic that artificial intelligence and data science … might be more accurate compared to any hypothesis of human doctors,” said Kaminskiy, co-founder and managing partner at Deep Knowledge Ventures, an investment firm that is betting big on AI and longevity.

How times have changed. Artificial intelligence in healthcare is attracting more investments and deals than just about any sector of the economy, according to data research firm CB Insights. In the most recent third quarter, AI healthcare startups raised nearly $1.6 billion, buoyed by a $550 million mega-round from London-based Babylon Health, which uses AI to collect data from patients, analyze the information, find comparable matches, then make recommendations.

Even without the big bump from Babylon Health, AI healthcare startups raised more than $1 billion last quarter, including two companies focused on longevity therapeutics: Juvenescence and Insilico Medicine.

The latter has risen to prominence for its novel use of reinforcement learning and general adversarial networks (GANs) to accelerate the drug discovery process. Insilico Medicine recently published a seminal paper that demonstrated how such an AI system could generate a drug candidate in just 46 days. Co-founder and CEO Alex Zhavoronkov said he believes there is no greater goal in healthcare today—or, really, any venture—than extending the healthy years of the human lifespan.

“I don’t think that there is anything more important than that,” he told Singularity Hub, explaining that an unhealthy society is detrimental to a healthy economy. “I think that it’s very, very important to extend healthy, productive lifespan just to fix the economy.”

An Aging Crisis
The surge of interest in longevity is coming at a time when life expectancy in the US is actually dropping, despite the fact that we spend more money on healthcare than any other nation.

A new paper in the Journal of the American Medical Association found that after six decades of gains, life expectancy for Americans has decreased since 2014, particularly among young and middle-aged adults. While some of the causes are societal, such as drug overdoses and suicide, others are health-related.

While average life expectancy in the US is 78, Kaminskiy noted that healthy life expectancy is about ten years less.

To Zhavoronkov’s point about the economy (a topic of great interest to Kaminskiy as well), the US spent $1.1 trillion on chronic diseases in 2016, according to a report from the Milken Institute, with diabetes, cardiovascular conditions, and Alzheimer’s among the most costly expenses to the healthcare system. When the indirect costs of lost economic productivity are included, the total price tag of chronic diseases in the US is $3.7 trillion, nearly 20 percent of GDP.

“So this is the major negative feedback on the national economy and creating a lot of negative social [and] financial issues,” Kaminskiy said.

Investing in Longevity
That has convinced Kaminskiy that an economy focused on extending healthy human lifespans—including the financial instruments and institutions required to support a long-lived population—is the best way forward.

He has co-authored a book on the topic with Margaretta Colangelo, another managing partner at Deep Knowledge Ventures, which has launched a specialized investment fund, Longevity.Capital, focused on the longevity industry. Kaminskiy estimates that there are now about 20 such investment funds dedicated to funding life extension companies.

In November at the inaugural AI for Longevity Summit in London, he and his collaborators also introduced the Longevity AI Consortium, an academic-industry initiative at King’s College London. Eventually, the research center will include an AI Longevity Accelerator program to serve as a bridge between startups and UK investors.

Deep Knowledge Ventures has committed about £7 million ($9 million) over the next three years to the accelerator program, as well as establishing similar consortiums in other regions of the world, according to Franco Cortese, a partner at Longevity.Capital and director of the Aging Analytics Agency, which has produced a series of reports on longevity.

A Cure for What Ages You
One of the most recent is an overview of Biomarkers for Longevity. A biomarker, in the case of longevity, is a measurable component of health that can indicate a disease state or a more general decline in health associated with aging. Examples range from something as simple as BMI as an indicator of obesity, which is associated with a number of chronic diseases, to sophisticated measurements of telomeres, the protective ends of chromosomes that shorten as we age.

While some researchers are working on moonshot therapies to reverse or slow aging—with a few even arguing we could expand human life on the order of centuries—Kaminskiy said he believes understanding biomarkers of aging could make more radical interventions unnecessary.

In this vision of healthcare, people would be able to monitor their health 24-7, with sensors attuned to various biomarkers that could indicate the onset of everything from the flu to diabetes. AI would be instrumental in not just ingesting the billions of data points required to develop such a system, but also what therapies, treatments, or micro-doses of a drug or supplement would be required to maintain homeostasis.

“Consider it like Tesla with many, many detectors, analyzing the behavior of the car in real time, and a cloud computing system monitoring those signals in real time with high frequency,” Kaminskiy explained. “So the same shall be applied for humans.”

And only sophisticated algorithms, Kaminskiy argued, can make longevity healthcare work on a mass scale but at the individual level. Precision medicine becomes preventive medicine. Healthcare truly becomes a system to support health rather than a way to fight disease.

Image Credit: Photo by h heyerlein on Unsplash Continue reading

Posted in Human Robots

#436218 An AI Debated Its Own Potential for Good ...

Artificial intelligence is going to overhaul the way we live and work. But will the changes it brings be for the better? As the technology slowly develops (let’s remember that right now, we’re still very much in the narrow AI space and nowhere near an artificial general intelligence), whether it will end up doing us more harm than good is a question at the top of everyone’s mind.

What kind of response might we get if we posed this question to an AI itself?

Last week at the Cambridge Union in England, IBM did just that. Its Project Debater (an AI that narrowly lost a debate to human debating champion Harish Natarajan in February) gave the opening arguments in a debate about the promise and peril of artificial intelligence.

Critical thinking, linking different lines of thought, and anticipating counter-arguments are all valuable debating skills that humans can practice and refine. While these skills are tougher for an AI to get good at since they often require deeper contextual understanding, AI does have a major edge over humans in absorbing and analyzing information. In the February debate, Project Debater used IBM’s cloud computing infrastructure to read hundreds of millions of documents and extract relevant details to construct an argument.

This time around, Debater looked through 1,100 arguments for or against AI. The arguments were submitted to IBM by the public during the week prior to the debate, through a website set up for that purpose. Of the 1,100 submissions, the AI classified 570 as anti-AI, or of the opinion that the technology will bring more harm to humanity than good. 511 arguments were found to be pro-AI, and the rest were irrelevant to the topic at hand.

Debater grouped the arguments into five themes; the technology’s ability to take over dangerous or monotonous jobs was a pro-AI theme, and on the flip side was its potential to perpetuate the biases of its creators. “AI companies still have too little expertise on how to properly assess datasets and filter out bias,” the tall black box that houses Project Debater said. “AI will take human bias and will fixate it for generations.”
After Project Debater kicked off the debate by giving opening arguments for both sides, two teams of people took over, elaborating on its points and coming up with their own counter-arguments.

In the end, an audience poll voted in favor of the pro-AI side, but just barely; 51.2 percent of voters felt convinced that AI can help us more than it can hurt us.

The software’s natural language processing was able to identify racist, obscene, or otherwise inappropriate comments and weed them out as being irrelevant to the debate. But it also repeated the same arguments multiple times, and mixed up a statement about bias as being pro-AI rather than anti-AI.

IBM has been working on Project Debater for over six years, and though it aims to iron out small glitches like these, the system’s goal isn’t to ultimately outwit and defeat humans. On the contrary, the AI is meant to support our decision-making by taking in and processing huge amounts of information in a nuanced way, more quickly than we ever could.

IBM engineer Noam Slonim envisions Project Debater’s tech being used, for example, by a government seeking citizens’ feedback about a new policy. “This technology can help to establish an interesting and effective communication channel between the decision maker and the people that are going to be impacted by the decision,” he said.

As for the question of whether AI will do more good or harm, perhaps Sylvie Delacroix put it best. A professor of law and ethics at the University of Birmingham who argued on the pro-AI side of the debate, she pointed out that the impact AI will have depends on the way we design it, saying “AI is only as good as the data it has been fed.”

She’s right; rather than asking what sort of impact AI will have on humanity, we should start by asking what sort of impact we want it to have. The people working on AI—not AIs themselves—are ultimately responsible for how much good or harm will be done.

Image Credit: IBM Project Debater at Cambridge Union Society, photo courtesy of IBM Research Continue reading

Posted in Human Robots

#436209 Video Friday: Robotic Endoscope Travels ...

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!):

DARPA SubT Urban Circuit – February 18-27, 2020 – Olympia, WA, USA
Let us know if you have suggestions for next week, and enjoy today's videos.

Kuka has just announced the results of its annual Innovation Award. From an initial batch of 30 applicants, five teams reached the finals (we were part of the judging committee). The five finalists worked for nearly a year on their applications, which they demonstrated this week at the Medica trade show in Düsseldorf, Germany. And the winner of the €20,000 prize is…Team RoboFORCE, led by the STORM Lab in the U.K., which developed a “robotic magnetic flexible endoscope for painless colorectal cancer screening, surveillance, and intervention.”

The system could improve colonoscopy procedures by reducing pain and discomfort as well as other risks such as bleeding and perforation, according to the STORM Lab researchers. It uses a magnetic field to control the endoscope, pulling rather than pushing it through the colon.

The other four finalists also presented some really interesting applications—you can see their videos below.

“Because we were so please with the high quality of the submissions, we will have next year’s finals again at the Medica fair, and the challenge will be named ‘Medical Robotics’,” says Rainer Bischoff, vice president for corporate research at Kuka. He adds that the selected teams will again use Kuka’s LBR Med robot arm, which is “already certified for integration into medical products and makes it particularly easy for startups to use a robot as the main component for a particular solution.”

Applications are now open for Kuka’s Innovation Award 2020. You can find more information on how to enter here. The deadline is 5 January 2020.

[ Kuka ]

Oh good, Aibo needs to be fed now.

You know what comes next, right?

[ Aibo ]

Your cat needs this robot.

It's about $200 on Kickstarter.

[ Kickstarter ]

Enjoy this tour of the Skydio offices courtesy Skydio 2, which runs into not even one single thing.

If any Skydio employees had important piles of papers on their desks, well, they don’t anymore.

[ Skydio ]

Artificial intelligence is everywhere nowadays, but what exactly does it mean? We asked a group MIT computer science grad students and post-docs how they personally define AI.

“When most people say AI, they actually mean machine learning, which is just pattern recognition.” Yup.

[ MIT ]

Using event-based cameras, this drone control system can track attitude at 1600 degrees per second (!).

[ UZH ]

Introduced at CES 2018, Walker is an intelligent humanoid service robot from UBTECH Robotics. Below are the latest features and technologies used during our latest round of development to make Walker even better.

[ Ubtech ]

Introducing the Alpha Prime by #VelodyneLidar, the most advanced lidar sensor on the market! Alpha Prime delivers an unrivaled combination of field-of-view, range, high-resolution, clarity and operational performance.

Performance looks good, but don’t expect it to be cheap.

[ Velodyne ]

Ghost Robotics’ Spirit 40 will start shipping to researchers in January of next year.

[ Ghost Robotics ]

Unitree is about to ship the first batch of their AlienGo quadrupeds as well:

[ Unitree ]

Mechanical engineering’s Sarah Bergbreiter discusses her work on micro robotics, how they draw inspiration from insects and animals, and how tiny robots can help humans in a variety of fields.

[ CMU ]

Learning contact-rich, robotic manipulation skills is a challenging problem due to the high-dimensionality of the state and action space as well as uncertainty from noisy sensors and inaccurate motor control. To combat these factors and achieve more robust manipulation, humans actively exploit contact constraints in the environment. By adopting a similar strategy, robots can also achieve more robust manipulation. In this paper, we enable a robot to autonomously modify its environment and thereby discover how to ease manipulation skill learning. Specifically, we provide the robot with fixtures that it can freely place within the environment. These fixtures provide hard constraints that limit the outcome of robot actions. Thereby, they funnel uncertainty from perception and motor control and scaffold manipulation skill learning.

[ Stanford ]

Since 2016, Verity's drones have completed more than 200,000 flights around the world. Completely autonomous, client-operated and designed for live events, Verity is making the magic real by turning drones into flying lights, characters, and props.

[ Verity ]

To monitor and stop the spread of wildfires, University of Michigan engineers developed UAVs that could find, map and report fires. One day UAVs like this could work with disaster response units, firefighters and other emergency teams to provide real-time accurate information to reduce damage and save lives. For their research, the University of Michigan graduate students won first place at a competition for using a swarm of UAVs to successfully map and report simulated wildfires.

[ University of Michigan ]

Here’s an important issue that I haven’t heard talked about all that much: How first responders should interact with self-driving cars.

“To put the car in manual mode, you must call Waymo.” Huh.

[ Waymo ]

Here’s what Gitai has been up to recently, from a Humanoids 2019 workshop talk.

[ Gitai ]

The latest CMU RI seminar comes from Girish Chowdhary at the University of Illinois at Urbana-Champaign on “Autonomous and Intelligent Robots in Unstructured Field Environments.”

What if a team of collaborative autonomous robots grew your food for you? In this talk, I will discuss some key advances in robotics, machine learning, and autonomy that will one day enable teams of small robots to grow food for you in your backyard in a fundamentally more sustainable way than modern mega-farms! Teams of small aerial and ground robots could be a potential solution to many of the serious problems that modern agriculture is facing. However, fully autonomous robots that operate without supervision for weeks, months, or entire growing season are not yet practical. I will discuss my group’s theoretical and practical work towards the underlying challenging problems in robotic systems, autonomy, sensing, and learning. I will begin with our lightweight, compact, and autonomous field robot TerraSentia and the recent successes of this type of undercanopy robots for high-throughput phenotyping with deep learning-based machine vision. I will also discuss how to make a team of autonomous robots learn to coordinate to weed large agricultural farms under partial observability. These direct applications will help me make the case for the type of reinforcement learning and adaptive control that are necessary to usher in the next generation of autonomous field robots that learn to solve complex problems in harsh, changing, and dynamic environments. I will then end with an overview of our new MURI, in which we are working towards developing AI and control that leverages neurodynamics inspired by the Octopus brain.

[ CMU RI ] Continue reading

Posted in Human Robots

#436184 Why People Demanded Privacy to Confide ...

This is part four of a six-part series on the history of natural language processing.

Between 1964 and 1966, Joseph Weizenbaum, a German American computer scientist at MIT’s artificial intelligence lab, developed the first-ever chatbot [PDF].

While there were already some rudimentary digital language generators in existence—programs that could spit out somewhat coherent lines of text—Weizenbaum’s program was the first designed explicitly for interactions with humans. The user could type in some statement or set of statements in their normal language, press enter, and receive a response from the machine. As Weizenbaum explained, his program made “certain kinds of natural-language conversation between man and computer possible.”

He named the program Eliza after Eliza Doolittle, the working-class hero of George Bernard Shaw’s Pygmalion who learns how to talk with an upper-class accent. The new Eliza was written for the 36-bit IBM 7094, an early transistorized mainframe computer, in a programming language that Weizenbaum developed called MAD-SLIP.

Because computer time was a valuable resource, Eliza could only be run via a time-sharing system; the user interacted with the program remotely via an electric typewriter and printer. When the user typed in a sentence and pressed enter, a message was sent to the mainframe computer. Eliza scanned the message for the presence of a keyword and used it in a new sentence to form a response that was sent back, printed out, and read by the user.

To encourage ongoing dialogue, Weizenbaum designed Eliza to simulate the type of conversational style used by a Rogerian psychoanalyst. The program would take something the user said and reflect it back with a question, as can be seen in the example below. (Notice how the program takes keywords like “boyfriend” and “depressed” and re-uses them.)

Human: Men are all alike.

Computer: IN WHAT WAY?

Human: They're always bugging us about something or other.

Computer: CAN YOU THINK OF A SPECIFIC EXAMPLE?

Human: Well, my boyfriend made me come here.

Computer: YOUR BOYFRIEND MADE YOU COME HERE

Human: He says I'm depressed much of the time.

Computer: I AM SORRY TO HEAR YOU ARE DEPRESSED

Human: It's true. I am unhappy.

Weizenbaum chose this mode of dialogue for Eliza because it gave the impression that the computer understood what was being said without having to offer anything new to the conversation. It created the illusion of comprehension and engagement in a mere 200 lines of code.

To test Eliza’s capacity to engage an interlocutor, Weizenbaum invited students and colleagues into his office and let them chat with the machine while he looked on. He noticed, with some concern, that during their brief interactions with Eliza, many users began forming emotional attachments to the algorithm. They would open up to the machine and confess problems they were facing in their lives and relationships.

During their brief interactions with Eliza, many users began forming emotional attachments to the algorithm.

Even more surprising was that this sense of intimacy persisted even after Weizenbaum described how the machine worked and explained that it didn’t really understand anything that was being said. Weizenbaum was most troubled when his secretary, who had watched him build the program from scratch over many months, insisted that he leave the room so she could talk to Eliza in private.

For Weizenbaum, this experiment with Eliza made him question an idea that Alan Turing had proposed in 1950 about machine intelligence. In his paper, entitled “Computing Machinery and Intelligence,” Turing suggested that if a computer could conduct a convincingly human conversation in text, one could assume it was intelligent—an idea that became the basis of the famous Turing Test.

But Eliza demonstrated that convincing communication between a human and a machine could take place even if comprehension only flowed from one side: The simulation of intelligence, rather than intelligence itself, was enough to fool people. Weizenbaum called this the Eliza effect, and believed it was a type of “delusional thinking” that humanity would collectively suffer from in the digital age. This insight was a profound shock for Weizenbaum, and one that came to define his intellectual trajectory over the next decade.

The simulation of intelligence, rather than intelligence itself, was enough to fool people.

In 1976, he published Computing Power and Human Reason: From Judgment to Calculation [PDF], which offered a long meditation on why people are willing to believe that a simple machine might be able to understand their complex human emotions.

In this book, he argues that the Eliza effect signifies a broader pathology afflicting “modern man.” In a world conquered by science, technology, and capitalism, people had grown accustomed to viewing themselves as isolated cogs in a large and uncaring machine. In such a diminished social world, Weizenbaum reasoned, people had grown so desperate for connection that they put aside their reason and judgment in order to believe that a program could care about their problems.

Weizenbaum spent the rest of his life developing this humanistic critique of artificial intelligence and digital technology. His mission was to remind people that their machines were not as smart as they were often said to be. And that even though it sometimes appeared as though they could talk, they were never really listening.

This is the fourth installment of a six-part series on the history of natural language processing. Last week’s post described Andrey Markov and Claude Shannon’s painstaking efforts to create statistical models of language for text generation. Come back next Monday for part five, “In 2016, Microsoft’s Racist Chatbot Revealed the Dangers of Conversation.”

You can also check out our prior series on the untold history of AI. Continue reading

Posted in Human Robots

#436149 Blue Frog Robotics Answers (Some of) Our ...

In September of 2015, Buddy the social home robot closed its Indiegogo crowdfunding campaign more than 600 percent over its funding goal. A thousand people pledged for a robot originally scheduled to be delivered in December of 2016. But nearly three years later, the future of Buddy is still unclear. Last May, Blue Frog Robotics asked for forgiveness from its backers and announced the launch of an “equity crowdfunding campaign” to try to raise the additional funding necessary to deliver the robot in April of 2020.

By the time the crowdfunding campaign launched in August, the delivery date had slipped again, to September 2020, even as Blue Frog attempted to draw investors by estimating that sales of Buddy would “increase from 2000 robots in 2020 to 20,000 in 2023.” Blue Frog’s most recent communication with backers, in September, mentions a new CTO and a North American office, but does little to reassure backers of Buddy that they’ll ever be receiving their robot.

Backers of the robot are understandably concerned about the future of Buddy, so we sent a series of questions to the founder and CEO of Blue Frog Robotics, Rodolphe Hasselvander.

We’ve edited this interview slightly for clarity, but we should also note that Hasselvander was unable to provide answers to every question. In particular, we asked for some basic information about Blue Frog’s near-term financial plans, on which the entire future of Buddy seems to depend. We’ve left those questions in the interview anyway, along with Hasselvander’s response.

1. At this point, how much additional funding is necessary to deliver Buddy to backers?
2. Assuming funding is successful, when can backers expect to receive Buddy?
3. What happens if the fundraising goal is not met?
4. You estimate that sales of Buddy will increase 10x over three years. What is this estimate based on?

Rodolphe Hasselvander: Regarding the questions 1-4, unfortunately, as we are fundraising in a Regulation D, we do not comment on prospect, customer data, sales forecasts, or figures. Please refer to our press release here to have information about the fundraising.

5. Do you feel that you are currently being transparent enough about this process to satisfy backers?
6. Buddy’s launch date has moved from April 2020 to September 2020 over the last four months. Why should backers remain confident about Buddy’s schedule?

Since the last newsletter, we haven’t changed our communication, the backers will be the first to receive their Buddy, and we plan an official launch in September 2020.

7. What is the goal of My Buddy World?

At Blue Frog, we think that matching a great product with a big market can only happen through continual experimentation, iteration and incorporation of customer feedback. That’s why we created the forum My Buddy World. It has been designed for our Buddy Community to join us, discuss the world’s first emotional robot, and create with us. The objective is to deepen our conversation with Buddy’s fans and users, stay agile in testing our hypothesis and validate our product-market fit. We trust the value of collaboration. Behind Buddy, there is a team of roboticists, engineers, and programmers that are eager to know more about our consumers’ needs and are excited to work with them to create the perfect human/robot experience.

8. How is the current version of Buddy different from the 2015 version that backers pledged for during the successful crowdfunding campaign, in both hardware and software?

We have completely revised some parts of Buddy as well as replaced and/or added more accurate and reliable components to ensure we fully satisfy our customers’ requirements for a mature and high-quality robot from day one. We sourced more innovative components to make sure that Buddy has the most up-to-date technologies such as adding four microphones, a high def thermal matrix, a 3D camera, an 8-megapixel RGB camera, time-of-flight sensors, and touch sensors.
If you want more info, we just posted an article about what is Buddy here.

9. Will the version of Buddy that ships to backers in 2020 do everything that that was shown in the original crowdfunding video?

Concerning the capabilities of Buddy regarding the video published on YouTube, I confirm that Buddy will be able to do everything you can see, like patrol autonomously and secure your home, telepresence, mathematics applications, interactive stories for children, IoT/smart home management, face recognition, alarm clock, reminder, message/photo sharing, music, hands free call, people following, games like hide and seek (and more). In addition, everyone will be able to create their own apps thanks to the “BuddyLab” application.

10. What makes you confident that Buddy will be successful when Jibo, Kuri, and other social robots have not?

Consumer robotics is a new market. Some people think it is a tough one. But we, at Blue Frog Robotics, believe it is a path of learning, understanding, and finding new ways to serve consumers. Here are the five key factors that will make Buddy successful.

1) A market-fit robot

Blue Frog Robotics is a consumer-centric company. We know that a successful business model and a compelling fit to market Buddy must come up from solving consumers’ frustrations and problems in a way that’s new and exciting. We started from there.

By leveraged existing research and syndicated consumer data sets to understand our customers’ needs and aspirations, we get that creating a robot is not about the best tech innovation and features, but always about how well technology becomes a service to one’s basic human needs and assets: convenience, connection, security, fun, self-improvement, and time. To answer to these consumers’ needs and wants, we designed an all-in-one robot with four vital capabilities: intelligence, emotionality, mobility, and customization.

With his multi-purpose brain, he addresses a broad range of needs in modern-day life, from securing homes to carrying out his owners’ daily activities, from helping people with disabilities to educating children, from entertaining to just becoming a robot friend.

Buddy is a disruptive innovative robot that is about to transform the way we live, learn, utilize information, play, and even care about our health.
2) Endless possibilities

One of the major advantages of Buddy is his adaptability. Beyond to be adorable, playful, talkative, and to accompany anyone in their daily life at home whether you are comfortable with technology or not, he offers via his platform applications to engage his owners in a wide range of activities. From fitness to cooking, from health monitoring to education, from games to meditation, the combination of intelligence, sensors, mobility, multi-touch panel opens endless possibilities for consumers and organizations to adapt their Buddy to their own needs.
3) An affordable price

Buddy will be the first robot combining smart, social, and mobile capabilities and a developed platform with a personality to enter the U.S. market at affordable price.

Our competitors are social or assistant robots but rarely both. Competitors differentiate themselves by features: mobile, non-mobile; by shapes: humanoid or not; by skills: social versus smart; targeting a specific domain like entertainment, retail assistant, eldercare, or education for children; and by price. Regarding our six competitors: Moorebot, Elli-Q, and Olly are not mobile; Lynx and Nao are in toy category; Pepper is above $10k targeting B2B market; and finally, Temi can’t be considered an emotional robot.
Buddy remains highly differentiated as an all-in-one, best of his class experience, covering the needs for social interactions and assistance of his owners at each stage of their life at an affordable price.

The price range of Buddy will be between US $1700 and $2000.

4) A winning business model

Buddy’s great business model combines hardware, software, and services, and provides game-changing convenience for consumers, organizations, and developers.

Buddy offers a multi-sided value proposition focused on three vertical markets: direct consumers, corporations (healthcare, education, hospitality), and developers. The model creates engagement and sustained usage and produces stable and diverse cash flow.
5) A Passion for people and technology

From day one, we have always believed in the power of our dream: To bring the services and the fun of an emotional robot in every house, every hospital, in every care house. Each day, we refuse to think that we are stuck or limited; we work hard to make Buddy a reality that will help people all over the world and make them smile.

While we certainly appreciate Hasselvander’s consistent optimism and obvious enthusiasm, we’re obligated to point out that some of our most important questions were not directly answered. We haven’t learned anything that makes us all that much more confident that Blue Frog will be able to successfully deliver Buddy this time. Hasselvander also didn’t address our specific question about whether he feels like Blue Frog’s communication strategy with backers has been adequate, which is particularly relevant considering that over the four months between the last two newsletters, Buddy’s launch date slipped by six months.

At this point, all we can do is hope that the strategy Blue Frog has chosen will be successful. We’ll let you know if as soon as we learn more.

[ Buddy ] Continue reading

Posted in Human Robots