GAUTAM BUDDHA UNIVERSITY

SCHOOL OF ICT
Department of Information Technology

Session 2023 – 24 (Even Semester)

Program Name: Robotics
CODE: IT318
SEMESTER: VI

REPORT: Humanoid Robot

SUBMITTED TO: SUBMITTED BY:

Anand Sir NAME: Sukriti Nautiyal ROLL NO.: 225/LIT/001

NAME: Prachi Verma ROLL NO.: 215/UIT/065

NAME: Aradhya Gupta ROLL NO.: 215/UIT/073
 INDEX
S.No. Contents Page No.
1. Introduction 2-3
2. Humanoid Robot 4-21
2.a In 2018-2019 4-9
2.b In 2020-2021 10-15
2.c In 2022-2023 16-23
3. Comparison Table 24-25
4 Reference 26-28

1
 Introduction
A humanoid robot is a type of robot created to imitate and replicate the features
and abilities of the body. These robots usually consist of a head, torso two arms
and two legs enabling them to navigate and engage with their surroundings, like
humans do. The advancement of robots is motivated by the aspiration to
produce machines of carrying out tasks, in human settings and aiding humans in
diverse tasks. Humanoid robots are challenging mechatronics structures with
several interesting features.
In education various types of robots are currently employed for teaching
purposes ranging from robots, to humanoid robots. The selection of a robot
typically depends on the field of study and the age group of the students. Basic
robots are commonly utilized for instructing robotics, electronics or computer
science while humanoid robots offer experiences and are often used to teach a
diverse array of subjects such as mathematics, science and language.
Consequently, in times humanoid robots have begun serving as aids or even
instructors in classrooms, for multiple subjects including language, mathematics
and science.
Repetitive tasks, in industries can be managed smoothly by robots. There are
certain tasks that demand human cognitive abilities. Human Robot
Collaboration (HRC) is seen as an approach to combine the skills of an operator
with those of a robot marking a key area for enhancing human life. The main
aim is to establish interaction with transferring objects being vital, for task
completion. Considerable research work had been developed in this particular
field in recent years, where several solutions were already proposed.
Nonetheless, some particular issues regarding Human-Robot Collaboration still
hold an open path to truly important research improvements.
Robots have been part of automation systems for a very long time, and in public
perception, they are often synonymous with automation and industrial
revolution per se. Fuelled by Industry 4.0 and Internet of Things (IoT) concepts
as well as by new software technologies, the field of robotics in industry is
currently undergoing a revolution on its own.
Throughout history, humankind has been fascinated by machines and devices
able to imitate the functions and movements of living beings. The ancient Greek
civilization had the word autómatos to refer to such devices. The first
automaton was arguably built by Hero of Alexandria (85 AD), who made

2
animated mechanisms that moved with hydraulic devices, pulleys, and levers,
mostly for ludic purposes. For many centuries, various inventors created
automatons, from Leonardo da Vinci to the loom of Jacquard (in 1801), Albert
the Great (1204–1282), and Roger Bacon (1214–1294), to mention just a few.
The automaton can be considered the forerunner of modern industrial robots.
In numerous applications of robots within human lives are presented, involving
topics such as bio-feedback system, schools and learning, medicine,
entertainment, space exploration and military. Several studies and research
works were recently developed contributing to the progress of this research
field. Considering the ultimate goal of a fluent, human-like and flawless
collaboration, we realize the existence of a wide range of topics that need to be
completely covered up, such as safety, interaction, physicality, cognition,
adaptation, metrics, among many others.

3
 Humanoid Robot
In 2018-2019:
Building humanoid robots is very hard in terms of generating human-like
movements although the human-like movement is an essential component for
natural human–robot interaction, collaboration and expressions and in terms of
the challenges arising when a robot takes a human form (Gielniak, Liu & Thomaz,
2013). A key practice in research efforts in humanoid robotics is to include
experts from multiple disciplines including robotics, computer science, electrical
engineering, mechanical engineering, human factors engineering,
organisational behaviour and the social sciences. Humans have three main
senses that are essential for moving through the world around, namely, balance,
proprioception and kinaesthetic. Therefore, mastering the movement and
awareness of the human body is highly difficult for robots to achieve and not to
mention the other difficulties of mimicking humans (Kupferberg, Glasauer, S.,
Huber, M., Rickert, M., Knoll, A., & Brandt, 2011). Since most humanoid robot
applications include mixed-initiative interaction and rich information exchanges
in complex and dynamic environments, one of the key challenges is that human–
robot interactions and resulting behaviours must accommodate complexity.
Such a scenario is associated with a number of fundamental problems across
different application domains in terms of requirements on autonomy,
information sharing and evaluation. Although proof-of-concept humanoid robot
technologies are important, they should be fully supported by extensive and
careful experiments with human subjects (Beer, Prakash, Mitzner & Rogers,
2011). Such experiments determine key attributes of the principles and design.
Moreover, some humanoid robot applications may include multiple robots and
multiple humans to interact with each other. In addition to the proximity and
vulnerability of the humans in the interaction, social and emotional aspects of
the interaction are the key attributes of this problem (Goodrich & Schultz, 2008).
Hence, it is essential to shape multiple interactions and dynamics by establishing
organisational structures with different and dynamic roles, communications
protocols and support tools.
Humanoid robots are complex mechatronic systems. As such, it is necessary to
consider the mechanical structure, the computational system and the
algorithms as a whole and for a given application. The robot’s size, weight and
strength are important factors when designing its structure. Let us consider two
general classes of applications: physical performances while doing motion
4
generation and validation of biological and/or cognitive models. The ATLAS
robot from Boston Dynamics is an example of the first category, while the
Kenshiro robot from Tokyo University is an example of the second category.
Human robot interaction implies to control the robot forces for safety. This can
be done in an active manner (using a feedback loop) or passively (by mechanical
design). Robots with high gains-controlled actuators are not able to estimate
correctly the forces applied by a human. If performance is still the main
objective, it is better to integrate at an early-stage supplementary sensors (force
sensors or artificial skin cf) at high frequency (1 kHz) as it is done for the Kuka
LWR robot. Another approach consists in using servomotors with which it is
possible to lower the gains and hence to allow the actuator to be compliant. This
strategy is used for instance by the Poppy robot.
The kinematic structure of humanoid robots has long been inspired by the
human structure, and more precisely based on the study of Saunders. For this
reason, numerous humanoid robots have the structure depicted in Fig.1. The
legs are made of 3 rotation joints at the hip level (to simulate a spherical joint),
one joint for the knee flexion-extension and two joints for the ankle (flexion-
extension and pronosupination (combination of pronation and supination)). This
structure has one advantage: it has an analytical solution to the problem of
finding a configuration for the legs with respect to a given position of the waist
and the feet. For all these reasons, it is found in numerous robots such as the
HRPs series, HUBO, ASIMO and REEM-C. The counterparts of this structure are
the performance limits in the kinematic chains. Adding a passive toe joint allows
to increase the robot walking speed. To limit singularities and kinematic
constraints, recent humanoid robots such as S-One from Schaft or ATLAS have
more joints. For instance, Schaft as one more DoF on its legs on the sagittal
plane. More generally in the context of the DARPA Robotics Challenge (DRC),
ROBOSIMIAN from JPL and CHIMP from CMU are ape-like robots which allow to
perform more extended locomotion modes than bipedal ones. S-One has highly
redundant arms which permit to avoid singularities and kinematic limits. In a
general manner, if dexterity is a primary objective, it is strongly advised to use
an arm with 7 DoFs to avoid singularities. This has however a direct impact on
the number of motor and therefore on the arm mass, its electronic complexity
and the its weakness.

5
UBTECH Walker: Figure 2 consists of a humanoid robot studied and developed
in 2018-2019. UBTECH and Tsinghua University jointly developed WALKER-1, a
humanoid robot for home services, and its joint actuator selects a position
control scheme. Humanoid robots can be regarded as floating-based robotic
arms with a bipedal walking design, suitable for various human living
environments, thus making home services the highest-demand application
scenario. For the robot to be stable enough to serve in home scenarios, the gait
stability problem of walking on uneven terrain needs to be overcome. The
control strategies for robots walking on uneven terrain can be divided into
disturbance rejection-based balance control and terrain estimation-based
adaptive locomotion. In the first control strategy, the underfoot force
disturbance from the uneven terrain and the contact force disturbance from
other parts of the body are described as the same form of disturbance, then
designs the control system so that the disturbance can converge. Thus, the robot
can maintain its balance. In the second control strategy, a reactive sensor is used

6
to estimate the underfoot terrain model, or an anticipatory sensor is used to
estimate the upcoming terrain model. Then performs reflexive control or
modifies gait planning trajectory based on the estimated state.

Fig 2. UBTech Walker

Finally, the prototype experiments achieved full and partial contact tests
between in situ stepping and ground obstacles without other balance control.
The experimental results were consistent with the simulation of attaining
accurate terrain estimation based on the disturbance state observer.
In future work, this more accurate terrain estimation can be used to design
adaptive locomotion and balance control further to reduce the instability that
the original gait control system needs to withstand to improve the balance
performance of the robot during walking on uneven terrain.

7
Applications:
• Healthcare Humanoid Robot: Healthcare practitioner and benefactors
have appreciated the advantage of advanced surgical robots. However,
our study highlights the application of humanoid robots and their roles in
healthcare. In addition to surgical robots, healthcare humanoid robots
have been successfully helping people in disease management, pain relief,
paediatric healthcare assistant, and physical therapy. The role of
healthcare robots can be broadly classified into the clinical and non-
clinical application.
• Clinical application: In Clinical setting, humanoid robots have been used
to assist patients with cerebral palsy, and paediatric cancer. To study the
influence of human-robot interaction two children of age 9 and 13 with
cerebral palsy were exposed to NAO robot under four different interactive
situations. The experiment aimed at improving patient coordination,
truncal balance and motor function. The first interaction was a general
introduction round where children and robot verbally communicated with
each other. In this situation, the subject had a tough time understanding
the robot and required the help of a therapist; thus, it increased positive
interaction between the subjects, humanoid-robot, and the therapist.
This was aimed to enhance a child's social adaptability.
• Non-clinical application: Non-Clinical healthcare have significantly
contributed to autism management followed by diabetes management by
performing activities such as playing games, greeting, singing, dancing,
hand movement, blinking, interacting with the patients. Robots also
measured blood pressure and asked questions, played a quiz with the
patients, monitored and helped patients with medical assistance.
• Education Humanoid Robot: Use of computer and e-learning in the field
of education have been performing well and have successfully increased
the accessibility to education worldwide.

Conclusion: The users have appreciated the role of humanoid robots in the field
of healthcare and education. Contrastingly, people's attitude towards social or
assistive robots varies significantly. Children and elderly users prefer robots and
have less resistance towards the application of humanoid robots than that of
middle-aged users. Trust and acceptance of humanoid robots were affected by
its appearance, gaze, and functionality. According to a survey by Alaiad, people

8
felt that using humanoid might be a threat to their privacy. Humanoid robots
were preferred more than general assistive robots, even people gave more
attention to humanoid robots which are user-friendly.
Adult female users’ trust decreased when the robots constantly gazed at them;
however, users with lower confidence had more trust towards the robot.
Humanoid robots were trusted with their functional knowledge such as weight,
size, colour, and other quantitative measures, but users did not trust on social
and logical knowledge such good, bad, and other qualitative measures given by
the robot. People also believe that humanoid robots take undesirable actions
intentionally and are more prone to make an error. Unlike adult users, children
were not concerned about the robot’s utility. They enjoyed the company of
humanoid robot and treated them as a friend. Children were willing and able to
interact with the humanoid robot easily. Old males had high concern about a
robot's functionality more than adolescent or females. Users want the
humanoid robots to measure blood pressure, body temperature, connecting
with a doctor remotely, reminding tasks, entertain, helping in the baby care
management, lifting heavy, detect fall, control home appliance, housekeeping,
making a phone call and many other things.

9
In 2020-2021:
A fully autonomous robot is a machine that is able to carry out a task by sensing,
planning, and acting into an environment without any human intervention.
However, despite the great progress achieved by automation in the recent
years, we are still far from providing robots with full autonomy, that would allow
them to successfully deal with unpredictable events or unforeseen situations.
The utilization of robotic systems has been increasing in the last decade. This
increase has been derived by the evolvement in the computational capabilities,
communication systems, and the information systems of the manufacturing
systems which is reflected in the concept of Industry 4.0. Furthermore, the
robotics systems are continuously required to address new challenges in the
industrial and manufacturing domain, like keeping humans in the loop, among
other challenges.
Smart manufacturing and smart factories depend on automation and robotics,
whereas human–robot collaboration (HRC) contributes to increasing the
effectiveness and productivity of today’s and future factories. Industrial robots
especially in HRC settings can be hazardous if safety is not addressed properly.
The concept of human trust in autonomy is another essential aspect to be
considered when developing effective human-robot collaboration techniques.
Trust favors the adoption of semiautonomous systems such as robot assistants.
SA paradigms integrating the notion of trust require the definition of its
computational model, which is a research question per se. The trust towards a
robotic system depends on many factors such as the context, the application,
and several individual factors such as user’s attitude and experience.
The interaction between humans and machines/collaborative robots appears in
two manufacturing system types: dual resource constrained system (workers
use machines/robots) and human-robot collaboration system (workers and
robots collaborate). In the beginning, the main characteristics of human-
machine/robot (hybrid) manufacturing systems such as heterogeneity,
homogeneity, ergonomics and safety are given. Then, optimization models in
terms of design, scheduling, resource planning and assignment in DRC systems
are mentioned.
As robots become increasingly prevalent and capable, the complexity of roles
and responsibilities assigned to them as well as our expectations for them will
increase in kind. For these autonomous systems to operate safely and efficiently
10
in human-populated environments, they will need to cooperate and coordinate
with human teammates.
Mechanics of human robot: The effects of mechanical system dynamics are
often disregarded in the design process of humanoid robots. Sophisticated
control methods may compensate for some limitations of the mechanical
structure; however, principal limitations of the system performance can arise
from poor mechanical architecture. Therefore, it is important to develop robot
hardware that behaves close to an ideal model and that is easy to be modelled
from the viewpoint of mechanics.
The upper limb of a humanoid robot must be well designed when moving with
the robot’s hands on the wall or handrails. It is important to utilize passive
compliance in robotic systems, which has the potential to improve their
performance during locomotion and interactions. Finally, it should be noted that
humanoid robots with compliant joints have been widely studied. From the
viewpoint of mechanics, wiring must be considered when designing a humanoid
robot. A humanoid robot that reduces wiring by utilizing optical communication
technology also appears
Human-humanoid Interaction:
Endowing humanoids with cognitive skills are a pivotal step to safely blend them
in our society. Such skills go beyond the abilities of reasoning, exploration and
learning, and are rather oriented towards a mutual interplay between the
humanoid “brain”, its physical embodiment and its environment. In this sense,
cognitive skills emerge from a proper and coherent exploitation of stochastic
internal models of the knowledge the robot has of itself and of its surrounding.
These models mediate past knowledge with new perceptions and are
continuously and incrementally updated according to feedback from new
experiences. As inherently probabilistic, the models are not only able to
represent temporal information through short and long-term memories, but
also spatial deictics, surmounting the limits of the Cartesian definition of space,
embracing the more flexible concepts of “here” and “there” and of “this,
“these”, “that”, and “those”.
Once the cooperation strategy with the human has been defined, and the robot
has access to the human state estimation, it has to be controlled adequately to
enable the physical interactions. The previous section discussed how the robot
can plan for cooperative actions, at the high level, taking into account the

11
human’s goals and states. High-level decisions must be translated into low level
commands, typically by means of desired behaviours, implemented as desired
trajectories, which needs to be translated into motor commands, as represented
in Figure 3.

Fig 3. Schematic drawing of the components involved in Human-Humanoid Interaction and

cooperation.

Similarly to other cooperative robots, humanoid robots need to estimate the

human physical, physiological and cognitive state in order to collaborate with
their human partner effectively: as discussed in the previous sections and shown
in Figure 3, the human state is a critical input for the high-level decision planning
and lower-level motion planning and control.
Human intention recognition is a trending topic within the HRI research field,
especially for industrial environments. Human–robot perception and the
prediction of possible humans’ unsafe conditions will be a fundamental enabler
for anticipating human operators’ behaviour and needs, to implement proactive
collaboration among humans and robots. In advanced manufacturing plants,
many applications require HRC operations, where humans and robots perform
joint tasks or share the same environment.
Culture holds societies together through shared perceptions and practices. This
review examined how rapidly developing advances in social robotics can be
integrated into this narrative, by looking at our prior preconceptions and
responses to these agents during interactions. Further, we presented insights as

12
to whether such social robots should be designed for specific cultures in mind,
or if they should be adaptive to multiple cultures, in order to support successful
interactions with people.
There is a wide and varying field of questions about relation-based trust, but
there seems little interest in measuring relation-based trust questions
objectively. Relation-based trust is almost exclusively measured by (subjective)
questionnaires. If we want to understand how we trust social robots in social
contexts and interactions, we need to develop ways to measure relation-based
trust objectively. As the studies presented in this survey and others have
shown, varying levels of trust can affect the way people actually interact with a
robot. However, their objective task behaviour may not match their subjective
reactions about themselves when they answer a questionnaire.

It resolves aspects related to safety design, the available levels of automation

for the application and the essential human-robot relation that can be
established. The reliable installation of robots on industrial shopfloors is the best
statement to affirm that this level is already safe enough to be considered
achieved. Even though it has gathered relevant interest from the scientific
community, the complexity for guaranteeing human operator safety in every
situation is not achieved yet.

At present, two studies investigated the interplay between humans’ and robots’
personalities in H-HRI. This stream of research is particularly important for two
reasons. One, in reality both the human and the robot personalities have to be
taken into consideration. Therefore, understanding the interplay between them
is likely to provide important insights that can be generalized into valuable
design recommendations.

13
Applications:
• Humanoids as companions: coaches and education tools: Humanoids
endowed with social skills have the potential to assist humans in their
daily endeavours (i.e., at a supermarket, at school, at work or at home)
and as tools for education and rehabilitation. The anthropomorphic shape
coupled with advanced cognitive and social behaviours, gestures and
communication channels, can favor legibility, engagement, atonement
and trust.
• Humanoids as co-workers: optimizing the human ergonomics and
performance: Collaborative robots have received a lot of attention lately
due to their potential to act as co-workers that can possibly improve
working conditions. While initially focused on fixed-base robotic arms,
research in this domain is now moving towards robotic manipulators
mounted on wheeled mobile bases. Even if providing more mobility, these
robots remain largely limited to indoor settings with flat and uncluttered
ground. Humanoid robots instead, could adapt to different environments
and leverage their versatility. Even if their capabilities have been mostly
validated in laboratory setups, the ultimate goal is to make them
proactively work side by side humans without the need of protective
cages. To this end, they should also exhibit advanced interpersonal
communication skills, and be able to learn new operations and new tasks
through social interaction.
• Humanoids as avatars: enabling humans to act in remote environments:
There are many scenarios where the human presence at the site is
inherently dangerous (e.g. interventions in contaminated environments,
construction sites, space exploration). In such situations, robots could be
employed to replace humans at the site as physical avatars, protecting the
operators from any potential hazards. Robot avatars could also be helpful
in contexts not necessarily dangerous, for example to allow humans to
virtually exist in another location in view of a more ecological and time-
efficient society with an overall improved work-life balance.

14
Conclusion: To guarantee proficient and adequate cooperative
behaviours, humanoid robots need to advance their cognitive, social and
physical interaction skills. This article reported on the current work in
these areas of research, acknowledging the main limitations due to the
real-time nature of the interaction and the complexity of modelling and
identifying the human state. Human-aware humanoid collaborators
capable of long-term interactions in real situations are the next grand
challenge.
Innumerable tasks can only be performed by humans (instead of robots)
due to the high degree of complexity, dexterous coordination, perception,
interpretation and decision capabilities they require. Even in an industrial
environment, where the presence of automated robots is already a well-
established reality, several objectives can only be achieved through the
collaborative work of human teams. In the past two decades,
collaborative robots have been increasingly studied, developed and
integrated in various sectors of the industry. These collaborative robots
are not completely agnostic to the surroundings of their operational
space, being capable of adapting their movements to possible human
interventions during the task performance. This adaptation has several
advantages such as safety promotion and human guiding acceptance.

15
In 2022-2023:-
Actuators are the motors responsible for the movement of the robot.
Humanoid robots are designed to mimic the human body. Although with
different structures, they use accelerators that act like muscles and joints.
The actuators of humanoid robots can be electric, pneumatic or hydraulic.

The robot uses the human body and voice to interact gently and naturally
with humans, to behave like a human child, and to interact with humans
on a daily basis. Our strategy is to analyse human-robot interactions based
on body movements using motion-capture. We performed experiments
comparing body movements with subjective assessment based on the
psychological method. In addition to evaluation, we would like to know
about the metaphor that partner robots can use to motivate humans.

In the literature, the terms teleoperation and telexistence have been used
indistinctly in different contexts. Telexistence refers to the technology
that allows human to virtually exist in a remote location through an
avatar, experiencing real-time sensations from the remote site. Both the
remote environment and the avatar can be real or virtual, but in this
article, we only consider a real environment and a surrogate humanoid
robot as avatar. Telexistence has also been referred to as telepresence in
the literature. The concept of teleoperation, on the other hand, still refers
to a human operator remotely controlling a robot, but the focus is mainly
put on performing tasks that require high dexterity in the remote location.
We use these terms interchangeably throughout this survey. From
another perspective, the teleoperation setup represents an interactive
system where the robot imitates the human’s actions to reach a common
objective.

Imagine that you’re moving heavy furniture, performing surgery, or

cooking with the aid of a robot. You would want it to be alert, aware, and
good at coordinating actions, and this would require competent real-time
interaction. Borrowing the words of Ward and DeVault (2016), we think
that in broad strokes, these systems will be characterized by low latency
and natural timing, a deft sensitivity to the multi-functional nature of
communication, and flexibility about how any given interaction unfolds.
Their skill with interaction timing will be manifest in the way they are

16
attuned to and continuously respond to their users with an array of real-
time communicative signals.

The topic of HRC has been discussed before the first collaborative enabled
industrial manipulator was made available in 2008. However, there is an
ongoing debate about the definition and interpretation of the non-
normative terms HRC and human–robot interaction within academia and
industry.

Robots in manufacturing have been developed from nonprogrammable

to programmable. For the next generation of smart robotic
manufacturing, the adaptation of uncertainties has been pinpointed as an
urgent requirement, which can also be named program-free robots.

Even with high level of automation, there are many tasks that are still
being performed by human butchers. Nevertheless, there is upraising
interest for collaborative robotics in agriculture sector, that indirectly
indicated by increased number of products by key robotic manufacturers,
that offer HRC as more flexible and more human-oriented approach to
industrial automation.

In the age towards human-centric smart manufacturing, both industry

and academia are striving for an actual human–robot collaborative
production, where the foreseeable Proactive HRC paradigm plays a
vital role. This study elaborately extends our position paper that
HRC systems should and can embrace mutual-cognitive, predictable,
and self-organising intelligence for flexible, natural, and efficient
production.

Through the use of a scoping review, we sought to examine how HRs have
been used in the care of older persons and to identify the possible
benefits and challenges associated with such use from older persons’
points of view. The four main categories related to how humanoid robots
have been used in care of older persons could provide a starting point for
the development of further studies.

17
GUIs are used in the literature to provide both feedback to the user and
give commands to the robot. In the DRC, operators were able to supervise
the task execution through a task panel, using manual interfaces in case
they needed to make corrections. The main window consisted of a 2-D
and 3-D visualization environment, the robot’s current and goal states,
motion plans, together with other perception sensor data, such as
hardware driver status.

A discussion on the effectiveness and current state of classical UVGI

systems and UVGI robots was presented. As of now, the use of these
robots is limited to healthcare settings where they are used after standard
cleaning procedures. Due to the risks associated with UV light to humans,
these robots cannot currently be operated in human presence without
more examination and development; however, the implementation of
such devices is expected to increase in the post-pandemic world. The
future generation of UV disinfection robots needs to possess improved
designs that could enable their use in the presence of humans.

Innovative walking Robots:

Walking robots are the second most common type of robot that can move
around. Currently, many devices have been created – walking robots,
where authors describe designs, characteristics and advantageous areas
of application of walking robots. Perfect walking robots imitate
movements of insects, crustaceans, and sometimes humans, that is, their
distinctive feature is that biological approach is used in design of
structure. WRs are mainly used for: research, rescue operations,
entertainment, military and industrial purposes, healthcare, agriculture.
There are different types of walking robots’ structures, body shapes and
types of propulsion systems for WR depending on tasks to be solved
(Table 1).

18
Table 1. Types of walking robots structures, body shapes and types of propulsion units

Cognitive computing: This application aims to stimulate the thoughts of

the human in processes into a computerized model. Using the self-
learning algorithms uses data mining, recognition of patterns,
natural language, and others that the computer can read that the human
brain will work.

A classification of different collaborative tasks was proposed, mainly

composed by collaborative assembly, object handover, object handling
and collaborative manufacturing. Alongside with it, metrics of these tasks

19
were analysed. The cognitive variables modelled in the tasks were
assessed and discussed, at different levels of details. Machine learning
techniques were subdivided in supervised, unsupervised and
reinforcement learning, according to the learning algorithm used. The use
of composite machine learning systems is not predominant in literature
and it is encouraged, especially regarding deep reinforcement learning.

Personalization and localization in robotics is complicated, but needs to

move beyond catering to simple language preferences or accents.
Instead, this encompasses the intricate details of interface design, service
and behavior expectations, proxemics and overall individual and cultural
communication styles and cultural values users may possess.

AMECA: Bipedal Ameca robot from Engineered Arts, endowed with

artificial intelligence robot, is most realistic humanoid robot in world (fig.
4). Ameca is considered face of robotics of future. Robot has perfect
humanoid body. Which over time will have perfect humanoid artificial
intelligence. The body of robot is modular platform. Robot has universal
appearance without gender and age. Ameca – robot with live facial
expressions Ameca application: sort data from sensors and encoders,
motors, network traffic, video streams, physical conditions and respond
to them in time. At moment, Ameca is equipped only with head and arms.

20
 Fig 4. Ameca robot from Engineered Arts

Applications:
• Telexistence and Telepresence: The COVID-19 pandemic has either
cancelled many conferences and meetings around the world or led them
to be transformed into virtual events. Moreover, many people cannot see
their beloved ones frequently. The current substitution for such cases
currently is to use communication mediums, allowing the people to see
and hear each other. However using these means, many social cues-
equally important in social interaction-are not yet conveyed. Instead,
humanoid robot teleoperation with anthropomorphic shape and motion,
similar to a human, would allow for a better experience. Moreover, it
would allow people to interact physically with each other.
• Space Applications: Space robotics has many applications, including
satellite on orbit servicing, maintenance of the ISS, performing
experiments there, and interplanetary exploration and construction.
Some of these tasks cannot be performed by humans due to cost, safety,
and the increased complexity of the required system. On the other hand,
the reliability and robustness of autonomous robots are not yet sufficient
to perform such tasks autonomously. Therefore, teleoperation of space
robots with different degrees of autonomy is required. Space applications

21
 are more challenging due to communication latency and bandwidth,
possible unknown kinematics and dynamics properties of the target
objects of manipulation, and human factors. In the case of bilateral
teleoperation, the round-trip communication delay matters; however,
time-domain passivity control approaches can compensate to some
extent for earth-orbiting robots with the cost of degrading the efficiency.
• Service Robotics Application: Another area of use of humanoid robot
teleoperation is in domestic environments such as houses, supermarkets,
schools, and hotels with a diverse range of goals, such as giving care to
elderly people or housekeeping, restocking the market shelves,
teleducation, guiding visitors in hotels, or teletourism. These
environments are intrinsically unstructured and built for humans’ use;
therefore, a humanoid robot is likely to be deployed for such applications.
These applications will become more evident when the operator of the
humanoid robot cannot be present in the target environment. In other
words, workforces who teleoperate the humanoid robot can be at any
place. The main requirements for such applications to be acceptable are
the safety of humanoid robots with the people whom they are interacting
with, and the ability to manipulate and modify remote locations.

Conclusion: Humanoid robots are amazingly complex machines, capable of

traveling on the same terrible terrain that humans can cross, and capable of
performing the same tasks as humans, with the potential consequences of
Challenging control issues and computationally difficult planning issues. To
estimate a moment in body movements the score is called the entry score. Gives
computers the ability to reflect human emotions and identify emotions that are
physically expressed by others. Movement should be neurologically and
psychologically based. The ability to use given references Learning theory is
based on the structure of relationships in a social context and context. Location
is an important component of learning Vaikotsky's Proximal Development Zone.
If robots are able to achieve adequate communication functions, Various
applications of interactive human robots will emerge and they will participate in
our daily lives. Partner refers to the potential uses of robots. Of course, these
robots have direct psychological ability to perform enrichment tasks such as
psychology and entertainment. Animals are like pet robots. Kinetics is
summarized in some small representations of both robotics and
communication.
22
This provides an overview of main types of walking robots structures, body
shapes and types of movers, it is determined that body with joints is most often
an oblong shape, consisting of movably connected parts. Such circuit has
advantages of one-piece circuit and improved ability to overcome obstacles. At
same time, design becomes more complex, which requires additional
calculations, and additional articulation elements (mounts, hinges and drives)
increase mass and power consumption. Anthropomorphic bipedal robots are
considered most spectacular, but not most practical, sometimes robots are
more stable, for example, on 4 legs. There are many designs of WR, but today
they strive to ensure that robots have property of adapting to arbitrary topology
of surface on which they move. Thus, on basis of review, classification of main
types of walking robots’ structures, body shapes and types of propulsion units
of WR is given; main parameters and areas of walking robots application are
determined.

23
 Comparison Between all the years:
Features 2018-2019 2020-2021 2022-2023
Overall Incremental Continued Accelerated
Advancements improvements in progress with a advancements
design, AI, and focus on AI, with more
mobility. mobility, and sophisticated AI,
human enhanced
interaction. mobility, and
improved human-
like features.
AI Capabilities Basic AI Improved natural Advanced AI with
functionalities; language better
limited processing and understanding,
understanding of context contextual
context. awareness. awareness, and
improved
communication
skills.
Mobility Basic walking and Improved walking Enhanced mobility
limited dexterity. stability; some with more fluid
robots with basic and agile
grasping abilities. movements;
improved
dexterity for
complex tasks.
Human Interaction Basic gestures and Improved social More advanced
responses; limited interaction, human-like
social interaction. including interaction, with
recognition of improved emotion
emotions. recognition and
empathy.
Use Cases Mainly used in Expanded use in Diverse
research labs and customer service, applications in
educational healthcare, and healthcare,
settings. entertainment. education,
customer service,
and even as
companions.

24
Commercial Limited Increased Widely available
Availability commercial commercial for commercial
availability; availability with a use, with various
primarily few robots in models tailored
experimental. various industries. for specific
industries.
Cost High production Costs decreasing Costs continue to
costs limited as technology decrease, making
widespread advances, but still humanoid robots
adoption. relatively high. more accessible
for various
applications.

25
 References
1. Avishek Choudhury, Huiyang Li, Christopher M Greene, Sunanda Perumalla “Humanoid
Robot-Application and Influence” (2018)Ildar Farkhatdinov, Julia Ebert, Gijs van Oort, Mark
2. Vlutters, Edwin van Asseldonk and Etienne Burdet “Assisting Human Balance in Standing
with a Robotic Exoskeleton” ■ IEEE (2018)
3. Yi LONG, Zhi-jiang DU, Wei-dong WANG, Long HE, Xi-wang MAO, Wei DONG “Physical
human-robot interaction estimation based control scheme for a hydraulically actuated
exoskeleton designed for power amplification” ■ Frontiers (2018)
4. Oliver Karrenbauer, Samuel Rader, Tamim Asfour “An Ontology-Based Expert System to
Support the Design of Humanoid Robot Components” (2018)
5. Shintaro Noda, Yohei Kakiuchi, Hiroki Takeda, Kei Okada, Masayuki Inaba “Goal-Oriented
Simulation-Based Motion Interpolator for Complex Contact Transition: Experiments on Knee-
Contact Behavior” (2018)
6. Yan Zhou, Hongbo Li, and Hui Li “A Single-Phase PV Quasi-Z-Source Inverter With Reduced
Capacitance Using Modified Modulation and Double-Frequency Ripple Suppression Control”
■ IEEE (2018)
7. O. Stasse and T. Flayols “An overview of humanoid robots’ technologies” (2018)
8. J. Camilo Vasquez Tieck, Pascal Becker, Jacques Kaiser, Igor Peric, Mahmoud Akl, Daniel
Reichard, Arne Roennan, R¨udiger Dillman “Learning target reaching motions with a robotic
arm using brain-inspired dopamine modulated STDP” ■ IEEE (2019)
9. Alexandru Blidaru, Stephen L. Smith, Dana Kulic “Assessing User Specifications for Robot
Task Planning” (2019)
10. Ahmad Yaser Alhaddad, John Cabibihan, and Andrea Bonarini “Recognition of Aggressive
Interactions of Children Toward Robotic Toys” (2019)
11. Tuna, G., Tuna, A., Ahmetoglu, E. & Kuscu, H. “A survey on the use of humanoid robots in
primary education: Prospects, research challenges, and future research directions.” (2019)
12. Yukai Gong, Ross Hartley, Xingye Da, Ayonga Hereid, Omar Harib, Jiunn-Kai Huang, and Jessy
Grizzle “Feedback Control of a Cassie Bipedal Robot: Walking, Standing, and Riding a
Segway” ■ American Control Conference (2019)
13. Laura Leondina Campanozzi, Eugenio Guglielmelli,Eleonora Cella, Giampaolo Ghilardi, Mirta
Michelli, Massimo Ciccozzi, and Vittoradolfo Tambone “Building Trust in Social Robotics” ■
IEEE (2019)
14. Lillian Hung, Cindy Liu, Evan Woldum, Andy Au-Yeung, Annette Berndt, Christine Wallsworth,
Neil Horne, Mario Gregorio, Jim Mann and Habib Chaudhury “The benefits of and barriers to
using a social robot PARO in care settings: a scoping review” ■ BMC Geriatrics (2019)
15. Velvetina Lim, Maki Rooksby, Emily S. Cross, “Social Robots on a Global Stage: Establishing a
Role for Culture During Human–Robot Interaction” ■ Springer (2020)
16. Theresa Law and Matthias Scheutz, “Trust: Recent Concepts and Evaluations in Human-
Robot Interaction” ■ ResearchGate (2020)
17. Gabriel Skantze, “Turn-taking in Conversational Systems and Human-Robot Interaction: A
Review” ■ Elsevier (2020)
18. Connor Esterwood and Lionel P. Robert, “Personality in Healthcare Human Robot Interaction
(H-HRI): A Literature Review and Brief Critique” (2020)
19. S. Ehsan Hashemi-Petroodi, Sergey Kovalev, Simon Thevenin, Alexandre Dolgui, “Operations
management issues in design and control of hybrid human-robot collaborative
manufacturing systems: a survey” ■ Hal Open Science (2020)

26
20. Kenji Hashimoto, “Mechanics of humanoid robot” ■ Crossmark (2020)
21. Aaquib Tabrez, Matthew B. Luebbers, Bradley Hayes, “A Survey of Mental Modelling
Techniques in Human–Robot Teaming” ■ Springer (2020)
22. Tobias Kopp, Marco Baumgartner & Steffen Kinkel “Success factors for introducing industrial
human-robot interaction in practice: an empirically driven framework” ■ International
Journal of Advanced Manufacturing Technology (2020)
23. Maria Rodalyn V. Sanchez, Satoru Mishima, Masayuki Fujiwara, Guangyi Ai, Melanie Jouaiti,
Yuliia Kobryn, Sébastien Rimbert, Laurent Bougrain, Patrick Hénaff, Hiroaki Wagatsuma
“Methodological Design for Integration of Human EEG Data with Behavioral Analyses into
Human-Human/Robot Interactions in a Real-World Context” ■ Hal Open Science (2020)
24. Diego Rodríguez-Guerra, Gorka Sorrosal, Itziar cabanes, and Carlos Calleja, “Human-Robot
Interaction Review: Challenges and Solutions for Modern Industrial Environments” ■ IEEE
(2021)
25. Andrea Bonci, Pangcheng David Cen Cheng, Marina Indri and Giacomo Nabissi and Fiorella
Sibona, “Human-Robot Perception in Industrial Environments: A Survey” ■ Sensors (2021)
26. Janis Arents, Valters Abolins, Janis Judvaitis, Oskars Vismanis, Aly Oraby and Kaspars Ozols,
“Human–Robot Collaboration Trends and Safety Aspects:A Systematic Review” ■ Sensors
(2021)
27. ANTONI GRAU, MARINA INDRI, LUCIA LO BELLO, and THILO SAUTER “Robots in Industry the
Past, Present, and Future of a Growing Collaboration with Humans” (2021) ■ IEEE
INDUSTRIAL ELECTRONICS MAGAZINE
28. Aitor Toichoa Eyam, Wael M. Mohammed * and Jose L. Martinez Lastra, “Emotion-Driven
Analysis and Control of Human-Robot Interactions in Collaborative Applications” ■ Sensors
(2021)
29. Afonso Castro, Filipe Silva and Vitor Santos “Trends of Human-Robot Collaboration in
Industry Contexts: Handover, Learning, and Metrics” (2021)
30. Lorenzo Vianello, Luigi Penco, Waldez Gomes, Yang You, Salvatore Maria Anzalone, Pauline
Maurice, Vincent Thomas, Serena Ivaldi “Human-humanoid interaction and cooperation: a
review” (2021)
31. Mario Selvaggio, Marco Cognetti, Stefanos Nikolaidis, Serena Ivaldi and Bruno Siciliano
“Autonomy in Physical Human-Robot Interaction: A Brief Survey” (2021)
32. QILUN WANG, QING LI, AND MINGGUO ZHAO “Accurate Terrain Estimation for Humanoid
Robot Based on Disturbance State Observer” (2021)
33. Malin Andtfolk, Linda Nyholm, Hilde Eide & Lisbeth Fagerström “Humanoid robots in the
care of older persons: A scoping review”, ■ Crossmark (2021)
34. S. Sowmiya, M. Ramachandran, Sathiyaraj Chinnasamy, Vidhya Prasanth, Soniya Sriram “A
Study on Humanoid Robots and Its Psychological Evaluation” (2022)
35. Svitlana Sotnik, Vyacheslav Lyashenko “Overview of Innovative Walking Robots” (2022)
36. Matthew Marge, Carol Espy-Wilson, Nigel G. Ward, Abeer Alwan, Yoav Artzi, Mohit Bansal,
Gil Blankenship, Joyce Chai, Hal Daumé III, Debadeepta Dey, Mary Harper, Thomas Howard,
Casey Kennington, Ivana Kruijff-Korbayová, Dinesh Manocha, Cynthia Matuszek l, Ross
Mead, Raymond Mooney, Roger K. Moore, Mari Ostendorf, Heather Pon-Barry, Alexander I.
Rudnicky, Matthias Scheutz, “Spoken language interaction with robots: Recommendations
for future research” ■ Elsevier (2022)
37. Ishaan Mehta, Hao-Ya Hsueh, Sharareh Taghipour, Wenbin Li, Sajad Saeedi, “UV Disinfection
Robots: A Review” ■ Elsevier (2022)
38. Sebastian Hjorth, Dimitrios Chrysostomou “Human–robot collaboration in industrial
environments: A literature review on non-destructive disassembly” ■ Elsevier (2022)

27
39. Amr Adel “Future of industry 5.0 in society: human‑centric solutions, challenges and
prospective research areas” ■ Open Access (2022)
40. Zhihao Liu, Quan Liu, Wenjun Xu, Lihui Wang, Zude Zhou “Robot learning towards smart
robotic manufacturing: A review” ” ■ Elsevier (2022)
41. Sarah Hopko, Jingkun Wang and Ranjana Mehta“Human Factors Considerations and Metrics
in Shared Space Human-Robot Collaboration: A Systematic Review” ■ Frontiers (2022)
42. Ruth Stock-Homburg, Ruth Stock-Homburg “Survey of Emotions in Human–Robot
Interactions: Perspectives from Robotic Psychology on 20 Years of Research” ■ International
Journal of Social Robotics (2022)
43. Vignesh Prasad, Ruth Stock-Homburg, Jan Peters “Human-Robot Handshaking: A Review” ■
International Journal of Social Robotics (2022)
44. Hong QIAO, Shanlin ZHONG, Ziyu CHEN & Hongze WANG “Improving performance of robots
using human-inspired approaches: a survey” ■ Crossmark (2022)
45. Nicholas Rabb, Theresa Law, Meia Chita-Tegmark, Matthias Scheutz “An Attachment
Framework for Human-Robot Interaction” ■ International Journal of Social Robotics (2022)
46. Kourosh Darvish, Luigi Penco, Joao Ramos, Rafael Cisneros, Jerry Pratt, Member, Eiichi
Yoshida, Fellow, Serena Ivaldi, Member and Daniele Pucci, Associate Member,
“Teleoperation of Humanoid Robots: A Survey” ■ IEEE (2023)
47. Francesco Semeraro, Alexander Griffiths, Angelo Cangelosi “Human–robot collaboration and
machine learning: A systematic review of recent research” ■ Elsevier (2023)
48. Norina Gasteiger, Mehdi Hellou, Ho Seok Ahn “Factors for Personalization and Localization
to Optimize Human–Robot Interaction: A Literature Review” ■ Springer Nature (2023)
49. Shufei Li, Pai Zheng, Sichao Liu, Zuoxu Wang, Xi Vincent Wang, Lianyu Zheng, Lihui Wang
“Proactive human–robot collaboration: Mutual-cognitive, predictable, and self-organising
perspectives” ■ Elsevier (2023)
50. Dmytro Romanov, Olga Korostynska, Odd Ivar Lekang, Alex Mason “Towards human-robot
collaboration in meat processing: Challenges and possibilities” ■ Elsevier (2023)

28