Reading text 1.1: Meet Pepper – The Social Robot1

Vocabulary2 Pronunciation2

Commonplace

Done very often, or existing in many places, and therefore not unusual.

1) the act of accepting a gift, invitation, offer.

2) the act of agreeing with something and approving of it.

3) acceptance (into something): the process of allowing somebody to join something or be a member of a group.

4) the quality of being willing to accept an unpleasant or difficult situation.

There is no doubt that robots are becoming commonplace. Robotic machines of all shapes and sizes are entering our daily lives, and we witness them assisting, working, and serving at shopping malls, hospitals, museums, railway stations, elder-care facilities, schools, and homes.

With all these potential applications, mass production and deployment of these machines could eventually enrich our lives in manifold ways.

Robots capable of exhibiting sociability and achieving widespread societal acceptance are needed more than ever. Such sociable robots’ shape, size, look, behaviour, and intelligence must all be customized and specially designed. This was the idea behind the development of the Pepper robot by SoftBank Robotics.

Pepper was initially designed for a particular application of businessto-business (B2B) uses in SoftBank stores, but it became a platform of interest around the world for other applications. The Pepper robot is currently deployed in thousands of homes and schools; it is the chosen robotic platform for RoboCup@Home Social Standard Platform League (SSPL) competitions.

Manifold /ˈmænɪfəʊld/ Societal /səˈsaɪətl/

Adapt

1) to change your behaviour in order to deal more successfully with a new situation.

2) to change something in order to make it suitable for a new use or situation.

Capable

1) having the ability or qualities necessary for doing something.

2) having the ability to do things well.

A global overview of Pepper

Launched in June 2014, Pepper is an industrially produced humanoid robot first created for B2B, and later adapted for business-to-consumer, purposes. The machine is capable of exhibiting body language, perceiving and interacting with its surroundings, and moving around. It can also analyse people’s expressions and voice tones, using the latest advances and proprietary algorithms in voice and emotion recognition to spark interactions. The robot is equipped with features and high-level interfaces for multimodal communication with humans.

Launched /lɔːntʃ/ Humanoid /ˈhjuːmənɔɪd/ Exhibiting /ɪɡˈzɪbɪt/ Proprietary /prəˈpraɪətri/ Algorithm /ˈælɡərɪðəm/

Pepper is a 1.2-m-tall, wheeled humanoid robot, with 17 joints to aid body language, three omnidirectional wheels for smooth movement, approximately 12 h of battery life, and the ability to return to the recharging station. It has no sharp edges, and soft parts in some joints. The machine is designed for interacting with human beings and is equipped with a tablet (which also makes development and debugging convenient).

Omnidirectional /ˌɒmnɪdaɪˈrekʃənl/ Smooth /smuːð/

1 Redacted and extensively adapted from Amit Kumar Pandey and Rodolphe Gelin, “A Mass-Produced Sociable Humanoid Robot: Pepper: The First Machine of Its Kind,” IEEE Robotics & Automation Magazine, Volume 25, Issue 3, (2018): https://ieeexplore.ieee.org/document/8409927

2 From www.oxfordlearnersdictionaries.com/

Feature

1) something important, interesting or typical of a place or thing.

2) a part of somebody’s face.

3) (in the media) a special article or programme.

Animate

1) to make something more lively or full of energy.

2) to make models, toys, images, etc. seem to move in a film, etc.

Predilections to like something very much.

Natural, multimodal interaction with robots has long been seen as a necessity for robots’ successful deployment in human environments. In fact, the emergence of human–robot interaction (HRI) as a research domain was shaped around the need to “understand and shape the interactions between one or more humans and one or more robots” in anticipation of the situations and applications when robots would be all around us and collaborating with us.

Studies have shown that a robot’s physical embodiment and tactile communication can make it a more engaging and effective interaction partner than an animated character, and that a physical robot is a better support for human learning gains compared to voice or video.

Furthermore, researchers have found that human-like appearance and interaction modalities are some features that the majority of study participants imagine companion robots should have – although people’s predilections vary with their individual personality differences.

Collaborate

/kəˈlæbəreɪt/

Appearance

1) the way that somebody/something looks on the outside; what somebody/something seems to be.

2) the fact of somebody/something arriving, especially when it is not expected.

3) the moment at which something begins to exist or starts to be seen or used.

4) an act of appearing in public.

5) an act of being published or broadcast.

In addition, as humanoid robots come to display body language and other abilities that embody human-like social signals, they become capable of being highly engaging. It is no surprise, then, that SoftBank Robotics’ baby-sized humanoid robot NAO, with its multimodal interaction capabilities and easy-to-program interface, rapidly became a widely accepted robotic platform for HRI research. Such studies, along with use-case ideas (for B2B in SoftBank stores and later on for B2C, at least in Japan) and experience with the NAO robot, led to the design of the Pepper robot. Some of the principles behind its design are

• a pleasant appearance

• safety

• affordability

• interactivity

• good autonomy.

Previously at a time before the time that you are talking about.

Appearance characteristics include size, shape, look, and voice. For the shape and size aspects, user feedback on NAO, as suggested previously, and a family resemblance to NAO were incorporated into Pepper. For the look, too exact a human likeness was avoided, with the aim of not falling into the “uncanny valley”. The design also has a Japanese influence, e.g., the manga-like big eyes and the hip joint that allows Pepper to bow upon meeting someone.

Embodiment

/ɪmˈbɒdimənt/ Tactile

/ˈtæktaɪl/ Animated

Exhibit

1) to show something in a public place.

2) to show clearly that you have or feel a particular quality, ability, feeling, or symptom (to exhibit fear).

The shape aimed to be gender neutral (with no explicitly defined gender characteristics) to avoid any stereotyping effect. Some studies already show that a person tends to rate a robot that looks like the opposite sex as more credible, trustworthy, and engaging and that, if robots exhibit a gender, there is a stereotype-based bias in the expected services the robot should be providing.

In addition, to further avoid stereotypes and unrealistic expectations, the robot’s voice was crafted to be childlike and androgynous.

Safety is considered in various aspects of the Pepper body design. For example, the robot has no sharp edges, there are soft parts on the cover, and the centre of mass is at the base to keep the robot from falling over. The motors are powerful enough to move the joints but not strong enough to hurt someone accidentally. The robot is equipped with bumpers.

Stereotyping /ˈsteriətaɪpɪŋ/ Trustworthy /ˈtrʌstwɜːði/

Various /ˈveəriəs/ Mass /mæs/

Deliberate

1) done on purpose rather than by accident

2) an action done on purpose rather than by accident.

Components one of several parts of which something is made.

Facilitate to make an action or a process possible or easier.

Displacement

1) the act of forcing somebody/something away from their home or position.

2) the amount of a liquid moved out of place by something floating or put in it, especially a ship floating in water.

Only necessary components, sensors, and functionalities were added to fulfil specific use-case needs. For example, the hand was deliberately not designed for heavy manipulation but only to be good enough for expressive interaction.

Functionality /ˌfʌŋkʃəˈnæləti/ Deliberately /dɪˈlɪbərətli/ Interactivity

Interaction is one of the Pepper robot’s key features. The need for natural and intuitive interaction is at the heart of these, but the machine’s design also considers the real-life situations in which communication might not always be particularly reliable or useful. Pepper has a multimodality of interaction interfaces including a touch screen, speech, tactile head and hands, and light-emitting diodes (LEDs).

Several software components were developed to facilitate perception abilities and ensure a smooth HRI. This included the capacity to recognize and respond to human emotions, a library of expressive gestures, and microlevel behaviours for displaying liveliness.

Intuitive /ɪnˈtjuːɪtɪv/

Particularly /pəˈtɪkjələli/

Ability /əˈbɪləti/

To achieve human-like and graceful expressivity through body language, the kinetic structure of the robot was carefully designed with 17 joints. Three omnidirectional wheels help in achieving smooth movement and support the realization of local, small displacements more naturally.

Kinetic /kɪˈnetɪk/, / kaɪˈnetɪk/

Intervention

1) action taken to improve or help a situation.

2) action by a country to become involved in the affairs of another country when they have not been asked to do so.

3) action taken to improve a medical condition or illness.

4) the act of interrupting somebody when they are speaking in order to say something.

Random one chosen, etc., without somebody deciding in advance what is going to happen, or without any regular pattern

Embed

1) to fix something in a substance or solid object

2) to send a journalist, etc., to an area, so that they can travel with the military and report.

Autonomy

Long-term autonomy is also important, so the robot can last an entire workday in SoftBank stores without recharging or intervention. The whole system was designed to balance software and hardware loads and achieve a battery life of about 12 h. In addition, a specifically designed docking station for autonomous charging was developed. Furthermore, there are modules and apps for the robot to achieve behavioural autonomy in particular applications, reducing the need for human intervention.

The robot’s hull is smooth, high-quality plastic, with parts consisting of soft plastics to reduce the risk of pinching during physical interaction and minimize damage if the machine falls over. Tactile body parts with capacitive sensors indicate when the robot is touched.

Pepper is 1210 mm tall, 480 mm wide, and 425 mm deep. It weighs 28 kg. The robot is equipped with several LEDs for communicating. These are software controlled to change colours and intensity. The machine has an Atom E3845 processor with a quad-core central processing unit (CPU) and a clock speed of 1.91 GHz. It has a 4 GB double-data-rate, type-three random-access memory and a flash memory of 32 GB embedded multimedia card, of which 24 GB are available for users.

Pepper has 20 degrees of freedom (DoF) for motion (17 joints) and omnidirectional navigation (three wheels). The wheels allow the robot to climb a 1.5 cm step and a 5° slope.

Perceive

1) to understand or think of somebody/ something in a particular way.

2) to notice or become aware of something.

Presence

1) (of a person, thing, substance) the fact of being in a particular place

2) the quality of making a strong impression on other people by the way you talk or behave; a person who has this quality.

The core requirement of the initial B2B scenario was interaction with humans: the capacity to perceive people is needed to achieve this. The Pepper robot is equipped at both the hardware and software application programming interface (API) levels to provide good functionality for perceiving humans. The multimodal perception components are primarily intended to discern people’s presence and avoid collisions with the environment. The NAOqi People Perception module provides a list of inbuilt APIs to help in the development of high-level reasoning and behavioural capabilities.

Scenario /səˈnɑːriəʊ/ Discern /dɪˈsɜːn/ Behavioural /bɪˈheɪvjərəl/

Provide

1) to give something to somebody or make it available for them to use.

2) to state that something will or must happen.

Capability

1) the ability or qualities necessary to do something.

2) the power or weapons that a country has for war or for military action.

Devise

1) to invent something new or a new way of doing something.

Originate

1) to happen or appear for the first time in a particular place or situation.

2) to create something new.

3) to start in a particular place.

Manipulate

1) to control or influence somebody/something, often in a dishonest way so that they do not realize it.

2) to control, use, or change something with skill.

One of Pepper’s unique capabilities is dialogue-based interaction, crucial for delivering a natural, more gratifying HRI. A dialogue-based interaction system can be easily created using the NAOqi ALDialog and Qichat modules. These provide various functionalities to devise and shape natural interaction, such as originating concepts and topics and are the easiest means of providing input to and commanding the robot through natural language.

In addition, the robot is equipped with the Animated Speech and Expressive Listening modules to display human-like gestures while speaking or listening. These, combined with Pepper’s 17 articulations, allow the machine to move fluidly in ways that make it appear more naturally interactive, with the aim of achieving a high level of human–robot engagement.

Pepper is not designed to manipulate objects. However, it is equipped with two arms, each with a five-fingered hand, and thanks to its appropriate height, the robot can be used to achieve some basic object handover and tabletop manipulation tasks.

To ensure safety even during Pepper’s shutdown process, a two-step procedure has been adopted. First, the robot goes into a relaxed and safe position and turns its motors off. It also has a stop button at the back. In addition, it has no sharp edges. If someone bumps into the machine, it tries to maintain its balance. If the robot is pushed hard enough to fall over, it cuts off all of its motors as it falls. Most of the weight is in the base near the wheels, so the upper body is relatively light.

Pepper complies with some of the ISO norms on robot motion and corresponding safety requirements. It stops before colliding with any obstacles detected more than 1.5 cm away, and is equipped with touch reflex, reduced movement speed, blind zone analysis, and a module to create a local map for safe navigation. Furthermore, to avoid dangerous movements in blind zones, the arm speed is lessened when moving inside an unknown zone. The robot is designed to detect a human or obstacle using anticollision software. Also, the base is too low (2 cm) to roll over a human foot. Pepper’s travel speed limit is 2 km/h and its emergency speed limit (push recovery) is 3.6 km/h.

Unique /juˈniːk/

Gesture /ˈdʒestʃə(r)/ Articulation /ɑːˌtɪkjuˈleɪʃn/ Appropriate /əˈprəʊpriət/ Height /haɪt/

Procedure /prəˈsiːdʒə(r)/

Maintain /meɪnˈteɪn/

Obstacle /ˈɒbstəkl/

Analysis /əˈnæləsɪs

Work in pairs. Underline content words in a selection of paragraphs from the text above. Concentrate on pronouncing the content words: Pay attention to sentence stress and the correct intonation patterns, then read aloud in turn.

Intonation concerns how our voice goes up or down over several words within a statement. Intonation is essential to effective communication. It helps us understand feelings, attitudes, and meaning, and it helps to understand if the speaker has finished speaking and it is your turn, or if there is a question to be answered. Interestingly, the spoken word contains more information compared to the written word. Although punctuation marks, such as commas, can convey some of the intonational meaning, the majority of it cannot be expressed in writing. As a result, English spoken by native speakers is more informative than written English.

This is the most common pattern of speech, associated with statements and certainty. You are stating a fact or you believe you are right. It also communicates completion. You have finished speaking and the listener can now respond. (All sentences in this paragraph should be spoken using a general falling intonation at the end of the sentence).

• He’s going home.

• He’s going home to see his brother.

• He’s going home to see his brother before leaving for college.

Rising intonation is associated with uncertainty:

• What’s your favourite colour? Blue?

It invites the listener to answer yes or no:

• He’s great, isn’t he?

When you have not finished speaking, the rising intonation implies incompletion as indicated in writing by commas in the following examples:

• This is a pencil, and it’s made of wood.

• Eric plays the flute, clarinet, and saxophone.

• It was interesting, but tiresome.

Intonation may therefore change the meaning of a statement. Consider the following question:

• It’s raining, isn’t it?

If the phrase ‘isn’t it?’ is said with the pitch of the voice rising, it is likely to be heard as a question, while a falling pitch is likely to be heard as confirmation.

Intonation in some cases can convey significant different opinions or attitudes. Let’s take the following exchange between father and son, for example:

• Son: I’m dropping out of school.

• Father: Are you serious?

Are you serious? spoken with an upward pitch may convey an open attitude, interest, or concern for his son.

Are you serious? with a downward pitch is more what you would expect of a statement. It conveys a judgement, and a negative one: “I do not agree that you should be dropping out of school.” Same words, but very different meaning.

Work in pairs. Read the article on the social robot above.

Divide the four questions between yourselves. Try to prepare a longer explanation of several connected sentences, not just a single statement. Use vocabulary and phrases from the article. Pay attention to pronunciation, stress, and intonation. Look up pronunciation if in doubt. Spend 10 minutes to prepare, then try answering orally without reading from your notes.

1. What was done to ensure Pepper cannot harm anyone?

2. What influenced and informed the design of Pepper’s physical appearance?

3. What does the statement that a robot is “social” mean?

4. What does the statement that the robot has multimodal features mean?