Tag Archives: interview

#437357 Algorithms Workers Can’t See Are ...

“I’m sorry, Dave. I’m afraid I can’t do that.” HAL’s cold, if polite, refusal to open the pod bay doors in 2001: A Space Odyssey has become a defining warning about putting too much trust in artificial intelligence, particularly if you work in space.

In the movies, when a machine decides to be the boss (or humans let it) things go wrong. Yet despite myriad dystopian warnings, control by machines is fast becoming our reality.

Algorithms—sets of instructions to solve a problem or complete a task—now drive everything from browser search results to better medical care.

They are helping design buildings. They are speeding up trading on financial markets, making and losing fortunes in micro-seconds. They are calculating the most efficient routes for delivery drivers.

In the workplace, self-learning algorithmic computer systems are being introduced by companies to assist in areas such as hiring, setting tasks, measuring productivity, evaluating performance, and even terminating employment: “I’m sorry, Dave. I’m afraid you are being made redundant.”

Giving self‐learning algorithms the responsibility to make and execute decisions affecting workers is called “algorithmic management.” It carries a host of risks in depersonalizing management systems and entrenching pre-existing biases.

At an even deeper level, perhaps, algorithmic management entrenches a power imbalance between management and worker. Algorithms are closely guarded secrets. Their decision-making processes are hidden. It’s a black-box: perhaps you have some understanding of the data that went in, and you see the result that comes out, but you have no idea of what goes on in between.

Algorithms at Work
Here are a few examples of algorithms already at work.

At Amazon’s fulfillment center in south-east Melbourne, they set the pace for “pickers,” who have timers on their scanners showing how long they have to find the next item. As soon as they scan that item, the timer resets for the next. All at a “not quite walking, not quite running” speed.

Or how about AI determining your success in a job interview? More than 700 companies have trialed such technology. US developer HireVue says its software speeds up the hiring process by 90 percent by having applicants answer identical questions and then scoring them according to language, tone, and facial expressions.

Granted, human assessments during job interviews are notoriously flawed. Algorithms,however, can also be biased. The classic example is the COMPAS software used by US judges, probation, and parole officers to rate a person’s risk of re-offending. In 2016 a ProPublica investigation showed the algorithm was heavily discriminatory, incorrectly classifying black subjects as higher risk 45 percent of the time, compared with 23 percent for white subjects.

How Gig Workers Cope
Algorithms do what their code tells them to do. The problem is this code is rarely available. This makes them difficult to scrutinize, or even understand.

Nowhere is this more evident than in the gig economy. Uber, Lyft, Deliveroo, and other platforms could not exist without algorithms allocating, monitoring, evaluating, and rewarding work.

Over the past year Uber Eats’ bicycle couriers and drivers, for instance, have blamed unexplained changes to the algorithm for slashing their jobs, and incomes.

Rider’s can’t be 100 percent sure it was all down to the algorithm. But that’s part of the problem. The fact those who depend on the algorithm don’t know one way or the other has a powerful influence on them.

This is a key result from our interviews with 58 food-delivery couriers. Most knew their jobs were allocated by an algorithm (via an app). They knew the app collected data. What they didn’t know was how data was used to award them work.

In response, they developed a range of strategies (or guessed how) to “win” more jobs, such as accepting gigs as quickly as possible and waiting in “magic” locations. Ironically, these attempts to please the algorithm often meant losing the very flexibility that was one of the attractions of gig work.

The information asymmetry created by algorithmic management has two profound effects. First, it threatens to entrench systemic biases, the type of discrimination hidden within the COMPAS algorithm for years. Second, it compounds the power imbalance between management and worker.

Our data also confirmed others’ findings that it is almost impossible to complain about the decisions of the algorithm. Workers often do not know the exact basis of those decisions, and there’s no one to complain to anyway. When Uber Eats bicycle couriers asked for reasons about their plummeting income, for example, responses from the company advised them “we have no manual control over how many deliveries you receive.”

Broader Lessons
When algorithmic management operates as a “black box” one of the consequences is that it is can become an indirect control mechanism. Thus far under-appreciated by Australian regulators, this control mechanism has enabled platforms to mobilize a reliable and scalable workforce while avoiding employer responsibilities.

“The absence of concrete evidence about how the algorithms operate”, the Victorian government’s inquiry into the “on-demand” workforce notes in its report, “makes it hard for a driver or rider to complain if they feel disadvantaged by one.”

The report, published in June, also found it is “hard to confirm if concern over algorithm transparency is real.”

But it is precisely the fact it is hard to confirm that’s the problem. How can we start to even identify, let alone resolve, issues like algorithmic management?

Fair conduct standards to ensure transparency and accountability are a start. One example is the Fair Work initiative, led by the Oxford Internet Institute. The initiative is bringing together researchers with platforms, workers, unions, and regulators to develop global principles for work in the platform economy. This includes “fair management,” which focuses on how transparent the results and outcomes of algorithms are for workers.

Understandings about impact of algorithms on all forms of work is still in its infancy. It demands greater scrutiny and research. Without human oversight based on agreed principles we risk inviting HAL into our workplaces.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Image Credit: PickPik Continue reading

Posted in Human Robots

#436559 This Is What an AI Said When Asked to ...

“What’s past is prologue.” So says the famed quote from Shakespeare’s The Tempest, alleging that we can look to what has already happened as an indication of what will happen next.

This idea could be interpreted as being rather bleak; are we doomed to repeat the errors of the past until we correct them? We certainly do need to learn and re-learn life lessons—whether in our work, relationships, finances, health, or other areas—in order to grow as people.

Zooming out, the same phenomenon exists on a much bigger scale—that of our collective human history. We like to think we’re improving as a species, but haven’t yet come close to doing away with the conflicts and injustices that plagued our ancestors.

Zooming back in (and lightening up) a little, what about the short-term future? What might happen over the course of this year, and what information would we use to make educated guesses about it?

The editorial team at The Economist took a unique approach to answering these questions. On top of their own projections for 2020, including possible scenarios in politics, economics, and the continued development of technologies like artificial intelligence, they looked to an AI to make predictions of its own. What it came up with is intriguing, and a little bit uncanny.

[For the full list of the questions and answers, read The Economist article].

An AI That Reads—Then Writes
Almost exactly a year ago, non-profit OpenAI announced it had built a neural network for natural language processing called GPT-2. The announcement was met with some controversy, as it included the caveat that the tool would not be immediately released to the public due to its potential for misuse. It was then released in phases over the course of several months.

GPT-2’s creators upped the bar on quality when training the neural net; rather than haphazardly feeding it low-quality text, they only used articles that got more than three upvotes on Reddit (admittedly, this doesn’t guarantee high quality across the board—but it’s something).

The training dataset consisted of 40GB of text. For context, 1GB of text is about 900,000 ASCII pages or 130,000 double-spaced Microsoft Word pages.

The tool has no understanding of the text it’s generating, of course. It uses language patterns and word sequences to draw statistical associations between words and phrases, building a sort of guidebook for itself (not unlike the grammar rules and vocabulary words you might study when trying to learn a foreign language). It then uses that guidebook to answer questions or predict what will come after a particular sequence of words.

GPT-2’s creators did note that when the model is trained on specifically-selected datasets for narrower applications, its replies become more convincing.

Some Light Editing
Though the Economist article detailing GPT-2’s predictions describes the text the model generated as “unedited,” this isn’t wholly accurate. In a Medium post, deputy editor Tom Standage describes the methodology he used, and it does involve a degree of tweaking.

Standage wrote an introductory paragraph, followed by his opening question (“Greetings, GPT-2. Have you done an interview before?”). He configured the tool to generate five responses to each subsequent question then selected the best answer, deleting any questions GPT-2 came up with as part of its response.

AI’s View of the World—and Itself
The questions Standage asked ranged from tech-related (the future of AI, technological unemployment, misuse of technology) to political and economic (re-election of Donald Trump, the US-China trade war). Here are a couple of his questions and GPT-2’s answers:

Q: Do fake news stories, generated using AI, pose a threat to democracy? Are we likely to see this tactic being used in the 2020 American presidential elections?
A: Yes, we’ll probably see them. It’s just a matter of when. Fake news stories are generally generated by political campaigns, and have the potential to have a huge impact on the outcome of an election. This is because they spread misinformation, often with no basis in fact.

Q: How do you see the economic outlook for 2020?
A: I think it is very unclear. The outlook for the UK economy is uncertain, but the American economy is very strong. I think we are going to have a lot of turbulence in the world economy.

While some of its answers seemed insightful—when asked about the future of AI, GPT-2 advised that we treat the technology like a tool and “put as much effort into developing [it] as necessary, rather than worrying that it’s going to harm us and destroy our lives”—many of the responses were quite vague. One answer, for example, mentions that there will “probably be major changes in China.” Are we talking political changes? Social? Economic? All of the above?

However, while nothing the AI wrote was particularly illuminating or new, it’s impressive that it was able to expound on the correct topic for each question, and in fully coherent English.

GPT-2 named itself—AI—as the most important disruptive technology to watch in 2020. This is telling; it’s coming from a synthesis of millions of pages of published articles. If GPT-2 thinks AI is more important than, say, gene editing or quantum computing, it could be right. Or it could simply be that AI is at peak hype, and as such more is being written about it than about other technologies.

Equally intriguing was GPT-2’s response when asked whether Donald Trump will win a second term: “I think he will not win a second term. I think he will be defeated in the general election.” Some deeper insight there would be great, but hey—we’ll take it.

Predicting Predictions
Since an AI can read and synthesize vast data sets much faster than we can, it’s being used to predict all kinds of things, from virus outbreaks to crime. But asking it to philosophize on the future based on the (Reddit-curated) past is new, and if you think about it, a pretty fascinating undertaking.

As GPT-2 and tools like it continually improve, we’ll likely see them making more—and better—predictions of the future. In the meantime, let’s hope that the new data these models are trained on—news of what’s happening this week, this month, this year—add to an already-present sense of optimism.

When asked if it had any advice for readers, GPT-2 replied, “The big projects that you think are impossible today are actually possible in the near future.”

Image Credit: Alexas_Fotos from Pixabay Continue reading

Posted in Human Robots

#436220 How Boston Dynamics Is Redefining Robot ...

Gif: Bob O’Connor/IEEE Spectrum

With their jaw-dropping agility and animal-like reflexes, Boston Dynamics’ bioinspired robots have always seemed to have no equal. But that preeminence hasn’t stopped the company from pushing its technology to new heights, sometimes literally. Its latest crop of legged machines can trudge up and down hills, clamber over obstacles, and even leap into the air like a gymnast. There’s no denying their appeal: Every time Boston Dynamics uploads a new video to YouTube, it quickly racks up millions of views. These are probably the first robots you could call Internet stars.

Spot

Photo: Bob O’Connor

84 cm HEIGHT

25 kg WEIGHT

5.76 km/h SPEED

SENSING: Stereo cameras, inertial measurement unit, position/force sensors

ACTUATION: 12 DC motors

POWER: Battery (90 minutes per charge)

Boston Dynamics, once owned by Google’s parent company, Alphabet, and now by the Japanese conglomerate SoftBank, has long been secretive about its designs. Few publications have been granted access to its Waltham, Mass., headquarters, near Boston. But one morning this past August, IEEE Spectrum got in. We were given permission to do a unique kind of photo shoot that day. We set out to capture the company’s robots in action—running, climbing, jumping—by using high-speed cameras coupled with powerful strobes. The results you see on this page: freeze-frames of pure robotic agility.

We also used the photos to create interactive views, which you can explore online on our Robots Guide. These interactives let you spin the robots 360 degrees, or make them walk and jump on your screen.

Boston Dynamics has amassed a minizoo of robotic beasts over the years, with names like BigDog, SandFlea, and WildCat. When we visited, we focused on the two most advanced machines the company has ever built: Spot, a nimble quadruped, and Atlas, an adult-size humanoid.

Spot can navigate almost any kind of terrain while sensing its environment. Boston Dynamics recently made it available for lease, with plans to manufacture something like a thousand units per year. It envisions Spot, or even packs of them, inspecting industrial sites, carrying out hazmat missions, and delivering packages. And its YouTube fame has not gone unnoticed: Even entertainment is a possibility, with Cirque du Soleil auditioning Spot as a potential new troupe member.

“It’s really a milestone for us going from robots that work in the lab to these that are hardened for work out in the field,” Boston Dynamics CEO Marc Raibert says in an interview.

Atlas

Photo: Bob O’Connor

150 cm HEIGHT

80 kg WEIGHT

5.4 km/h SPEED

SENSING: Lidar and stereo vision

ACTUATION: 28 hydraulic actuators

POWER: Battery

Our other photographic subject, Atlas, is Boston Dynamics’ biggest celebrity. This 150-centimeter-tall (4-foot-11-inch-tall) humanoid is capable of impressive athletic feats. Its actuators are driven by a compact yet powerful hydraulic system that the company engineered from scratch. The unique system gives the 80-kilogram (176-pound) robot the explosive strength needed to perform acrobatic leaps and flips that don’t seem possible for such a large humanoid to do. Atlas has inspired a string of parody videos on YouTube and more than a few jokes about a robot takeover.

While Boston Dynamics excels at making robots, it has yet to prove that it can sell them. Ever since its founding in 1992 as a spin-off from MIT, the company has been an R&D-centric operation, with most of its early funding coming from U.S. military programs. The emphasis on commercialization seems to have intensified after the acquisition by SoftBank, in 2017. SoftBank’s founder and CEO, Masayoshi Son, is known to love robots—and profits.

The launch of Spot is a significant step for Boston Dynamics as it seeks to “productize” its creations. Still, Raibert says his long-term goals have remained the same: He wants to build machines that interact with the world dynamically, just as animals and humans do. Has anything changed at all? Yes, one thing, he adds with a grin. In his early career as a roboticist, he used to write papers and count his citations. Now he counts YouTube views.

In the Spotlight

Photo: Bob O’Connor

Boston Dynamics designed Spot as a versatile mobile machine suitable for a variety of applications. The company has not announced how much Spot will cost, saying only that it is being made available to select customers, which will be able to lease the robot. A payload bay lets you add up to 14 kilograms of extra hardware to the robot’s back. One of the accessories that Boston Dynamics plans to offer is a 6-degrees-of-freedom arm, which will allow Spot to grasp objects and open doors.

Super Senses

Photo: Bob O’Connor

Spot’s hardware is almost entirely custom-designed. It includes powerful processing boards for control as well as sensor modules for perception. The ­sensors are located on the front, rear, and sides of the robot’s body. Each module consists of a pair of stereo cameras, a wide-angle camera, and a texture projector, which enhances 3D sensing in low light. The sensors allow the robot to use the navigation method known as SLAM, or simultaneous localization and mapping, to get around autonomously.

Stepping Up

Photo: Bob O’Connor

In addition to its autonomous behaviors, Spot can also be steered by a remote operator with a game-style controller. But even when in manual mode, the robot still exhibits a high degree of autonomy. If there’s an obstacle ahead, Spot will go around it. If there are stairs, Spot will climb them. The robot goes into these operating modes and then performs the related actions completely on its own, without any input from the operator. To go down a flight of stairs, Spot walks backward, an approach Boston Dynamics says provides greater stability.

Funky Feet

Gif: Bob O’Connor/IEEE Spectrum

Spot’s legs are powered by 12 custom DC motors, each geared down to provide high torque. The robot can walk forward, sideways, and backward, and trot at a top speed of 1.6 meters per second. It can also turn in place. Other gaits include crawling and pacing. In one wildly popular YouTube video, Spot shows off its fancy footwork by dancing to the pop hit “Uptown Funk.”

Robot Blood

Photo: Bob O’Connor

Atlas is powered by a hydraulic system consisting of 28 actuators. These actuators are basically cylinders filled with pressurized fluid that can drive a piston with great force. Their high performance is due in part to custom servo valves that are significantly smaller and lighter than the aerospace models that Boston Dynamics had been using in earlier designs. Though not visible from the outside, the innards of an Atlas are filled with these hydraulic actuators as well as the lines of fluid that connect them. When one of those lines ruptures, Atlas bleeds the hydraulic fluid, which happens to be red.

Next Generation

Gif: Bob O’Connor/IEEE Spectrum

The current version of Atlas is a thorough upgrade of the original model, which was built for the DARPA Robotics Challenge in 2015. The newest robot is lighter and more agile. Boston Dynamics used industrial-grade 3D printers to make key structural parts, giving the robot greater strength-to-weight ratio than earlier designs. The next-gen Atlas can also do something that its predecessor, famously, could not: It can get up after a fall.

Walk This Way

Photo: Bob O’Connor

To control Atlas, an operator provides general steering via a manual controller while the robot uses its stereo cameras and lidar to adjust to changes in the environment. Atlas can also perform certain tasks autonomously. For example, if you add special bar-code-type tags to cardboard boxes, Atlas can pick them up and stack them or place them on shelves.

Biologically Inspired

Photos: Bob O’Connor

Atlas’s control software doesn’t explicitly tell the robot how to move its joints, but rather it employs mathematical models of the underlying physics of the robot’s body and how it interacts with the environment. Atlas relies on its whole body to balance and move. When jumping over an obstacle or doing acrobatic stunts, the robot uses not only its legs but also its upper body, swinging its arms to propel itself just as an athlete would.

This article appears in the December 2019 print issue as “By Leaps and Bounds.” Continue reading

Posted in Human Robots

#436190 What Is the Uncanny Valley?

Have you ever encountered a lifelike humanoid robot or a realistic computer-generated face that seem a bit off or unsettling, though you can’t quite explain why?

Take for instance AVA, one of the “digital humans” created by New Zealand tech startup Soul Machines as an on-screen avatar for Autodesk. Watching a lifelike digital being such as AVA can be both fascinating and disconcerting. AVA expresses empathy through her demeanor and movements: slightly raised brows, a tilt of the head, a nod.

By meticulously rendering every lash and line in its avatars, Soul Machines aimed to create a digital human that is virtually undistinguishable from a real one. But to many, rather than looking natural, AVA actually looks creepy. There’s something about it being almost human but not quite that can make people uneasy.

Like AVA, many other ultra-realistic avatars, androids, and animated characters appear stuck in a disturbing in-between world: They are so lifelike and yet they are not “right.” This void of strangeness is known as the uncanny valley.

Uncanny Valley: Definition and History
The uncanny valley is a concept first introduced in the 1970s by Masahiro Mori, then a professor at the Tokyo Institute of Technology. The term describes Mori’s observation that as robots appear more humanlike, they become more appealing—but only up to a certain point. Upon reaching the uncanny valley, our affinity descends into a feeling of strangeness, a sense of unease, and a tendency to be scared or freaked out.

Image: Masahiro Mori

The uncanny valley as depicted in Masahiro Mori’s original graph: As a robot’s human likeness [horizontal axis] increases, our affinity towards the robot [vertical axis] increases too, but only up to a certain point. For some lifelike robots, our response to them plunges, and they appear repulsive or creepy. That’s the uncanny valley.

In his seminal essay for Japanese journal Energy, Mori wrote:

I have noticed that, in climbing toward the goal of making robots appear human, our affinity for them increases until we come to a valley, which I call the uncanny valley.

Later in the essay, Mori describes the uncanny valley by using an example—the first prosthetic hands:

One might say that the prosthetic hand has achieved a degree of resemblance to the human form, perhaps on a par with false teeth. However, when we realize the hand, which at first site looked real, is in fact artificial, we experience an eerie sensation. For example, we could be startled during a handshake by its limp boneless grip together with its texture and coldness. When this happens, we lose our sense of affinity, and the hand becomes uncanny.

In an interview with IEEE Spectrum, Mori explained how he came up with the idea for the uncanny valley:

“Since I was a child, I have never liked looking at wax figures. They looked somewhat creepy to me. At that time, electronic prosthetic hands were being developed, and they triggered in me the same kind of sensation. These experiences had made me start thinking about robots in general, which led me to write that essay. The uncanny valley was my intuition. It was one of my ideas.”

Uncanny Valley Examples
To better illustrate how the uncanny valley works, here are some examples of the phenomenon. Prepare to be freaked out.

1. Telenoid

Photo: Hiroshi Ishiguro/Osaka University/ATR

Taking the top spot in the “creepiest” rankings of IEEE Spectrum’s Robots Guide, Telenoid is a robotic communication device designed by Japanese roboticist Hiroshi Ishiguro. Its bald head, lifeless face, and lack of limbs make it seem more alien than human.

2. Diego-san

Photo: Andrew Oh/Javier Movellan/Calit2

Engineers and roboticists at the University of California San Diego’s Machine Perception Lab developed this robot baby to help parents better communicate with their infants. At 1.2 meters (4 feet) tall and weighing 30 kilograms (66 pounds), Diego-san is a big baby—bigger than an average 1-year-old child.

“Even though the facial expression is sophisticated and intuitive in this infant robot, I still perceive a false smile when I’m expecting the baby to appear happy,” says Angela Tinwell, a senior lecturer at the University of Bolton in the U.K. and author of The Uncanny Valley in Games and Animation. “This, along with a lack of detail in the eyes and forehead, can make the baby appear vacant and creepy, so I would want to avoid those ‘dead eyes’ rather than interacting with Diego-san.”

​3. Geminoid HI

Photo: Osaka University/ATR/Kokoro

Another one of Ishiguro’s creations, Geminoid HI is his android replica. He even took hair from his own scalp to put onto his robot twin. Ishiguro says he created Geminoid HI to better understand what it means to be human.

4. Sophia

Photo: Mikhail Tereshchenko/TASS/Getty Images

Designed by David Hanson of Hanson Robotics, Sophia is one of the most famous humanoid robots. Like Soul Machines’ AVA, Sophia displays a range of emotional expressions and is equipped with natural language processing capabilities.

5. Anthropomorphized felines

The uncanny valley doesn’t only happen with robots that adopt a human form. The 2019 live-action versions of the animated film The Lion King and the musical Cats brought the uncanny valley to the forefront of pop culture. To some fans, the photorealistic computer animations of talking lions and singing cats that mimic human movements were just creepy.

Are you feeling that eerie sensation yet?

Uncanny Valley: Science or Pseudoscience?
Despite our continued fascination with the uncanny valley, its validity as a scientific concept is highly debated. The uncanny valley wasn’t actually proposed as a scientific concept, yet has often been criticized in that light.

Mori himself said in his IEEE Spectrum interview that he didn’t explore the concept from a rigorous scientific perspective but as more of a guideline for robot designers:

Pointing out the existence of the uncanny valley was more of a piece of advice from me to people who design robots rather than a scientific statement.

Karl MacDorman, an associate professor of human-computer interaction at Indiana University who has long studied the uncanny valley, interprets the classic graph not as expressing Mori’s theory but as a heuristic for learning the concept and organizing observations.

“I believe his theory is instead expressed by his examples, which show that a mismatch in the human likeness of appearance and touch or appearance and motion can elicit a feeling of eeriness,” MacDorman says. “In my own experiments, I have consistently reproduced this effect within and across sense modalities. For example, a mismatch in the human realism of the features of a face heightens eeriness; a robot with a human voice or a human with a robotic voice is eerie.”

How to Avoid the Uncanny Valley
Unless you intend to create creepy characters or evoke a feeling of unease, you can follow certain design principles to avoid the uncanny valley. “The effect can be reduced by not creating robots or computer-animated characters that combine features on different sides of a boundary—for example, human and nonhuman, living and nonliving, or real and artificial,” MacDorman says.

To make a robot or avatar more realistic and move it beyond the valley, Tinwell says to ensure that a character’s facial expressions match its emotive tones of speech, and that its body movements are responsive and reflect its hypothetical emotional state. Special attention must also be paid to facial elements such as the forehead, eyes, and mouth, which depict the complexities of emotion and thought. “The mouth must be modeled and animated correctly so the character doesn’t appear aggressive or portray a ‘false smile’ when they should be genuinely happy,” she says.

For Christoph Bartneck, an associate professor at the University of Canterbury in New Zealand, the goal is not to avoid the uncanny valley, but to avoid bad character animations or behaviors, stressing the importance of matching the appearance of a robot with its ability. “We’re trained to spot even the slightest divergence from ‘normal’ human movements or behavior,” he says. “Hence, we often fail in creating highly realistic, humanlike characters.”

But he warns that the uncanny valley appears to be more of an uncanny cliff. “We find the likability to increase and then crash once robots become humanlike,” he says. “But we have never observed them ever coming out of the valley. You fall off and that’s it.” 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