Robot Appearance

Group Members

Name	Student ID
Bart Bronsgeest	1370871
Mihail Tifrea	1317415
Marco Pleket	1295713
Robert Scholman	1317989
Jeroen Sies	0947953

Relevance of robot appearance

In a social context, robots may be subject to judgement from humans based on their appearance Walters, M.L., Syrdal, D.S., Dautenhahn, K. et al. Avoiding the uncanny valley: robot appearance, personality and consistency of behavior in an attention-seeking home scenario for a robot companion. (2008). The perceived intelligence of the robot is correlated to the attractiveness of the robot since it is the case that humans make a ‘mental model’ of the robot during social interaction and adjust their expectations accordingly:

“If the appearance and the behavior of the robot are more advanced than the true state of the robot, hen people will tend to judge the robot as dishonest as the (social) signals being emitted by the robot, and unconsciously assessed by humans, will be misleading. On the other hand, if the appearance and behavior of the robot are unconsciously signaling that the robot is less attentive, socially or physically capable than it actually is, then humans may misunderstand or not take advantage of the robot to its full abilities.”

It is thus very important to predict and attribute the correct level of attractiveness depending on the intellectual capabilities of a robot. Not only that, but humans attribute different levels of trust and satisfaction when dealing with robots, depending on how much they like it Li, D., Rau, P.L.P. & Li, Y. A Cross-cultural Study: Effect of Robot Appearance and Task. (2010). Furthermore, an anthropomorphic robot is said to be better when high sociability tasks are required Lohse M et al (2007) What can I do for you? Appearance and application of robots. In: Artificial intelligence and simulation of behaviour, which is a statement that does not lack controversy as some research did not find any conclusive evidence of this aspect Li, D., Rau, P.L.P. & Li, Y. A Cross-cultural Study: Effect of Robot Appearance and Task. (2010).

Study objective

As many have regarded the uncanny valley the pitfall of humanoid robots, there is the necessity of figuring out how the appearance should change in order to climb this valley. The answer to this research question is rather simple, namely: to become indistinguishable from humans. But the problem of this simple answer is that there is no way to quantify the similarity in appearance to the one of humans other than measuring the uncanniness of the robot using humans and surveys. Better ways need to be researched in order to predict the similarity of a robot to the one of a human, based on robot features. For this, we intend to come up with a scoring system that can accurately predict where the robot sits on the uncanny valley. We are interested in computing this score using latent variables inferred from our research.

State of the Art

Hand-and-Finger Movement

In 2018 the non-profit research company OpenAI created a realistic human-hand-shaped robotic hand with a level of dexterity similar to that of a human [1]. The system that is responsible for the movement of the robotic hand uses a reinforcement model, where the AI is trained via trial and error. The hand itself is able to grasp and manipulate objects with state-of-the-art precision. Moreover, the hand exhibits unprecedented levels of dexterity as multiple grasp types that are found in humans can also be found in its hand movements.

Realistic facial expressions and head movement: Geminoid H1, H2, F and DK

The geminoid DK is a robot with a very anthropomorphic design, created to examine how the presence, the appearance, the behavior and the personality traits of an anthropomorphic robot affects the communication with human partners. The robot mimics the external appearance and the facial characteristics of the original, being its creator and a Danish professor Hendrik Scharfe. Apart from the movements in the robot’s facial expressions and head it is not able to move on it’s own (own = remotely by the operator). The Geminoid DK does not possess any intelligence of itself and has to be remotely controlled by an operator. Pre-programmed sequences of movements can be executed for subtle motions such as blinking and breathing. Moreover, speech of the operator can be transmitted through the computer network of the geminoid to a speaker located inside the robot.

Questionnaire

Method

All participants will be asked to fill out the questionnaire. In this questionnaire, subjects will see an image of a robot, and a video of the same robot moving, for three different robots. These robots fall into three different categories: slightly humanlike, humanlike and extremely humanlike. These three categories will be illustrated by the following robots: Atlas (Boston Dynamics), Honda ASIMO (Honda), and Geminoid DK (Aalborg University, Osaka University, Kokoro & ATR) // Sophia (Hanson robotics). To ensure that confounding variables like habituation to the robot have a minimal effect on participant judgement, the order of presentation is counterbalanced. This means that half of all participants will first see the image, then the video (normal order), and the other half will first see the video, then the image (reversed order). The order in which the different robots are presented is randomized. For a visual representation, please refer to table 1.

Subject responses will be measured using the Robotic Social Attributes Scale (RoSAS), developed by Carpinella, M. et al. (2017). Each robot will be rated on its warmth, competence and discomfort. Each of these three factors contains six items on which the robot will be evaluated. See table 1 for more details.

Enterprise

Introduction: Probleem schetsen, eventueel mogelijke oplossingen aanstippen? Waarom het relevant is, waarom we er uberhaupt een oplossing voor nodig hebben Marco

For the longest time in human history, humans have seized every opportunity they could find to automate and make their lives easier. This already started in the classical period with a very famous example, where the Romans would build large bridge-like waterways, aqueducts, to automatically transport water from outer areas to Rome, automated by the force of gravity and the general water cycle of nature. Today, computational sciences opening ways for AI and robotics have opened many new opportunities for this automation. Think about all the robots that are used in production to do the same programmed task over and over again, classification of images (often better than human results) with deep learning networks, and more recently, the combined robotics and AI task of self-driving cars!

Slowly but surely, robots can take over repetitive, task-specified jobs, and do them more efficiently than their human counterparts. Currently, however, such jobs are very concrete. For robots to have more versatility, they simply need to become more like us. Robots should be adaptive, be able to learn from their mistakes, and handle anomalies efficiently; essentially, a robot should have a level of decision-making and freedom equivalent to that of a human being. For example, when a robot is specifically tasked with picking up a football from the ground, it should find out a way to get the football back when it's accidentally thrown in a tree. Another issue arises in this social situation as well: the robot has to have a certain level of flexibility in its movement, since it should not just be able to move around and pick up a ball, but also to use tools that help it in fulfilling its "out of the ordinary" task. All in all, one thing becomes very clear: These tasks can not be hardcoded, they have to be learned.

It stands to reason that building a robot with all implementations specified above, a robot suitable in a social environment, requires a humanoid design. This causes many challenges, among which the most notable would be the challenges grouped into Electrical/Mechanical Engineering and Computer/Data Science. A human has many joints and muscles for various movements, expressions, and goals. The human face in particular is an incredibly complex design, consisting of 43 muscles, using about 10 of those muscles to smile and about 30 to simply laugh. All these joints and muscles have to work together perfectly since every joint's state influences the entire structure of joints and muscles. One huge aspect in the collaborative work of these joints and muscles is our sense of balance, meaning how the robot prevents itself from falling over. At every iteration, the robot has to check the state of its balance and decide which joints and muscles need to be given a task for the next iteration. Additionally, there is the Computer Science-related challenge of mapping such an unpredictable environment to binary code interpretable by the robot. Every signal from its surroundings has to be carefully processed and divided accordingly. The robot has to learn, diving into AI, and more specifically, Reinforcement Learning. Reinforcement Learning currently only exists as a solution to very basic learning problems, where the rules are very concretely specified, and suffers from the environment being too broad in terms of data. This is why it is still a very experimental field, and many robot studies include abstract definitions of states and policies for environment data that heavily imply the usage of Reinforcement Learning in theory, but lack a practical implementation.

As a consequence, social/humanoid robots are still a widely researched topic. The research has for example huge usage potential in care facilities and other forms of social care for the elderly, people with a disability, or even in the battle against loneliness and depression. Many papers cover how the robot could be taught certain skills with respect to the environment (Reinforcement Learning) and how it would communicate with humans. However, an oftentimes overlooked question is whether this robot would be accepted by humans at all. Many studies have found that a robot in the shape of a cute animal -a more easily modeled robot than a humanoid robot because humans expect less from the robot and the mimicked behavior is often very repetitive and standard- has a positive impact on its environment. People like engaging with the robot, as some see it as a kind of pet, and it successfully requests the attention of its audience. But, as we have established, such a robot would be very limited in the tasks it could fulfill, and modeling a humanoid robot is not as easy as modeling the behavior of an animal because we expect a lot more detail from the humanoid robot being humanoid beings ourselves. What would this robot look like to make it appealing instead of scary?

users, society and enterprise: Een algemene uitleg over de user geven en concrete users verzinnen en de problemen beschrijven enzo. En dan zonder je technologie te gebruiken laten zien hoe die personen zou kunnen benefitten van onze solution. Marco

Implementation details: Uitleggen hoe het bedrijf te werk zou kunnen gaan. Later komt hier ook het resultaat van de research bij Jeroen

We want to create an online platform on which users can receive feedback on the competence and likeability of a robot. There is much data on this topic available at the moment, for example how the appearance of a robot affects humans reactions towards it. Though the combination of the appearance with actual movement is much harder to determine. On our platform users can upload their robot and receive immediate feedback about their robot in the form of a prediction of how it would be received by people of a certain age group.

The most amount of work will be the setup of the whole platform and the gathering of the data. For the former we need an intuitive interface. Since there could be many variables that contribute to the result the way customers submit their robot should be made as easy as possible. We will support video content together with some easy to answer questions like the purpose of the robot and the target audience. For better assesment we would also increase our support to for example fbx files. There is also a possibility for users to request a human analysis, which one of our data analysts will then conduct. The result will then not be received instantaneously, but will be sent by email after the review is completed.

The data needed to be able to perform such an assessment will be gathered beforehand. A user research will be conducted among people of different age groups. In this research we aim to be able to map the likeability of robots of various levels of humanness compared to their way of moving. At first we focus on healthcare robots and thereby also on seniors. We will transform the data gathered into a usable model that we can implement on the platform.

After this initial setup there are a couple key factors to the whole process. First of all we need to maintain the platform, second of all we need publicity and at last we would like to improve the current model and expand it to other domains as well.

Funding for starting the enterprise: how should we get it and for what should it be used? Robert

To successfully start up the enterprise we would need to get some funding from other organizations. Organization that might want to fund the enterprise are stakeholders that would benefit from the service the enterprise offers, like a robotics manufacturer or a care home that uses robots. This funding would be mostly used to hire data analysts to develop the robot attractiveness scales and for the advertisement of the company. These are necessary for the enterprise until it is able to manage and survive on its own.

Enterprise structure: hierarchy, what kind of company do we need to have? Robert

The enterprise itself will consist of just a few people and will mostly be located online. Clients will be able to send in their robot designs and they would be rated and evaluated online. After the robot attractiveness scale has been created it will not quickly age and therefore we do a need for need full-time data analysts. We do need one or more employees to perform maintenance to the website/platform we will be using and one or more employees that are taking care of advertisements. Thus the body of employees will be relatively small.

Cost and profit: Evaluate the costs and profit and explain/discuss why it is a decent model for earning revenue. Robert

Since the enterprise will be mostly located online we can decide against hiring or buying an office. There are a benefits to having an office, for example you can have a central meeting point, and therefore we only decide against getting an office if the profits won’t allow for it. If we do so, we might need to hire computers, which can be located anywhere, for hosting the websites and running the evaluations. We should be able to hire only specific amounts of processing power of a computer, therefore we could reduce costs. The evaluation service we offer shall not be expensive, this is because we assume most anthropomorphic robot manufacturers already have a team designated to the design of the robot. Thus we cannot ask too much money, since then they will just solely rely on the designated team for design evaluation. However, making little profit is not necessarily bad, since the costs for maintaining the enterprise and performing the evaluation are also very low.

Aspect of the platform used by clients: waarom het platform goed werkt voor onze target users. Jeroen

Papers and summaries

The papers that were read and summarized fit into three categories, namely: remote physical therapy, robot appearance, and robot physics. Below are the three categories together with their respective papers for each team member: