You are on page 1of 21

NEUROTIC ROBOTS

CHAPTER 1.

INTRODUCTION[1]

Currently, various types of robots are there, such as intelligent service robots,
entertainment robots, etc. are in various stages of development. One of the key issues for

these robots is human‐robot interaction (HRI). For successful HRI, it is desirable for a

robot to recognize and interact with the user’s facial expressions and pose, as well as their
gestures and voice.

“Neurotic Robot” the newest in the series, coming with an intelligence as powerful as
human brain. Scientists are programming robots to be more 'neurotic' in order to help
them make smarter, human-like decisions. Jeff Krichmar, professor of cognitive science
at the University of California, Irvine is experimenting with building neurotic robots that
exhibit signs of obsessive-compulsive disorder, just like humans, or are afraid of open
spaces. He is doing this by making a robot act like a mouse in a cage

Aim is to make the robot brain more like human brain. The brain has incredibly
flexibility and adaptability. If you look at any artificial system, it's far more brittle than
biology, if you put a rodent in a room that is open and unfamiliar, it will hug the walls. It
will hide until it becomes comfortable, then it will move across the room. It will wait until
it feels comfortable. It was so anxious it would never cross the room. Preparing
mathematical models of brain or cognitive system, then putting that in software and it
becomes the controller for the robot.

Modern robots can solve math problems, play chess and even read and respond to
some human emotions. However, when they try to perform other basic human tasks like
walking, running, carrying on a conversation or recognizing basic objects in their
environment, their abilities fall short.

Fig. 1.1 Neurotic Human Robot


DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 1
NEUROTIC ROBOTS

CHAPTER 2.

TYPES OF ROBOTS[7]

2.1 Mobile Robots


Mobile robots have the capability to move around in their environment and are not
fixed to one physical location. An example of a mobile robot that is in common use today
is the automated guided vehicle or automatic guided vehicle (AGV). An AGV is a mobile
robot that follows markers or wires in the floor, or uses vision or lasers. AGVs are
discussed later in this article. Mobile robots are also found in industry, military and
security environments. They also appear as consumer products, for entertainment or to
perform certain tasks like vacuum cleaning. Mobile robots are the focus of a great deal of
current research and almost every major university has one or more labs that focus on
mobile robot research.

2.2 Industrial Robots


Industrial robots usually consist of a jointed arm (multilinked manipulator) and
end effectors that are attached to a fixed surface. One of the most common types of end
effectors is a gripper assembly.

Fig. 2.1 Industrial Robot

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 2


NEUROTIC ROBOTS

2.3 Service Robots


Most commonly industrial robots are fixed robotic arms and manipulators used
primarily for production and distribution of goods. The term “service robot” is less well-
defined. The International Federation of Robotics has proposed a tentative definition, “A
service robot is a robot which operates semi- or fully autonomously to perform services
useful to the well-being of humans and equipment, excluding manufacturing operations.

2.4 Modular Robots


Modular robots are a new breed of robots that are designed to increase the
utilization of robots by modularizing their architecture. The functionality and
effectiveness of a modular robot is easier to increase compared to conventional robots.
These robots are composed of a single type of identical, several different identical module
types, or similarly shaped modules, which vary in size. Their architectural structure
allows hyper redundancy for modular robots, as they can be designed with more than 8
degrees of freedom (DOF). Creating the programming, inverse kinematics and dynamics
for modular robots is more complex than with traditional robots. Modular robots may be
composed of L-shaped modules, cubic modules, and U and H-shaped modules. ANAT
technology, an early modular robotic technology patented by Robotics Design Inc.,
allows the creation of modular robots from U and H shaped modules that connect in a
chain, and are used to form heterogeneous and homogenous modular robot systems.
These “ANAT robots” can be designed with “n” DOF as each module is a complete
motorized robotic system that folds relatively to the modules connected before and after it
in its chain, and therefore a single module allows one degree of freedom.

2.5 Nano Robots


Nan robotics is the emerging technology field of creating machines or robots
whose components are at or close to the microscopic scale of a nanometre (10−9 meters).
Also known as “nanobots” or “nanites”, they would be constructed from molecular
machines. So far, researchers have mostly produced only parts of these complex systems,
such as bearings, sensors, and synthetic molecular motors, but functioning robots have
also been made such as the entrants to the Nanobot Robocup contest. Researchers also
hope to be able to create entire robots as small as viruses or bacteria, which could perform
tasks on a tiny scale. Possible applications include micro surgery (on the level of
individual cells), utility fog, manufacturing, weaponry and cleaning. Some people have
DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 3
NEUROTIC ROBOTS

suggested that if there were nanobots which could reproduce, the earth would turn into
"grey goo", while others argue that this hypothetical outcome is nonsense.

Fig. 2.2 Nano Robot

2.6 Reconfigurable Robots


A few researchers have investigated the possibility of creating robots which can
alter their physical form to suit a particular task, like the fictional T-1000. Real robots are
nowhere near that sophisticated however, and mostly consist of a small number of cube
shaped units, which can move relative to their neighbours. Algorithms have been
designed in case any such robots become a reality.

2.7 Soft-Bodied Robots


Robots with silicone bodies and flexible actuators (air muscles, electro active
polymers, and Ferro fluids) look and feel different from robots with rigid skeletons, and
can have different behaviours.

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 4


NEUROTIC ROBOTS

CHAPTER 3.

NEUROTIC ROBOTS[2]

Fig. 3.1 Neurotic Ant Robot

Currently, various types of robots such as intelligent service robots, entertainment


robots, etc. are in various stages of development. One of the key issues for these robots is
human robot interaction i.e., neurotic robots. For successful HRI, it is desirable for a
robot to recognize and interact with the user’s facial expressions and pose, as well as their
gestures and voice. For instance, this applies to entertainment robots: a new type of media
machine with the ability to transfer various contents to audiences. Children can read and
hear fairy tales, comics and sing songs through a robot. However, almost all methods for
Neurotic robots are developed for controlling robots, not for interacting with them. For
natural communications between robots and humans, it is necessary for the robot to be
able to respond according to the user’s emotional state. In general, the user may feel more
satisfied with and friendly towards the robot when it responds in parallel with the user’s
emotion.

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 5


NEUROTIC ROBOTS

CHAPTER 4.

EMOTIONS : FROM BRAIN TO ROBOT[3]

Some robots have been given emotional expressions in an attempt to improve


human–computer interaction. Analyse what it would mean for a robot to have emotion,
distinguishing emotional expression for communication from emotion as a mechanism for
the organization of behaviour. Research on the neurobiology of emotion yields a
deepening understanding of interacting brain structures and neural mechanisms rooted in
neuromodulation that underlie emotions in humans and other animals. However, the
chemical basis of animal function differs greatly from the mechanics and computations of
current machines. We therefore abstract from biology a functional characterization of
emotion that does not depend on physical substrate or evolutionary history, and is broad
enough to encompass the possible emotions of robots.

4.1 Different Kinds Of Emotions


There is a wide spectrum of feelings, from the ‘motivation’ afforded by drives
such as the search for food afforded by hunger to ‘emotions’ in which, at least in humans,
cognitive awareness might be linked to feeling the ‘heat’ of love, sorrow or anger, and so
on. But as we have no criterion for saying that a robot has ‘feelings’, we will seek here to
understand emotions in their functional context, noting that not all emotions need be like
human emotions.

We analyse emotion in two main senses:

(1) Emotional expression for communication and social coordination.


(2) Emotion for organization of behaviour (action selection, attention and learning).

The first concerns ‘external’ aspect of emotions; the second ‘internal’ aspects. In
animals, these aspects have co-evolved. How might they enter robot design? Both robots
and animals need to survive and perform efficiently within their ‘ecological niche’ and, in
each case, patterns of coordination will greatly influence the suite of relevant emotions (if
such are indeed needed) and the means whereby they are communicated.

A key function of emotion is to communicate simplified but high impact


information. A scream is extremely poor in information (it says nothing about the cause

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 6


NEUROTIC ROBOTS

for alarm), but its impact on others is high. Moreover, neurobiology shows that simplified
but high impact information is communicated between brain areas, through the very
different ‘vocabulary’ of neuromodulation.

The similarity in facial expressions between certain animals and humans prompted
classic evolutionary analyses, which support the view that mammals (at least) have
emotions (although not necessarily the same as human emotions), and work reviewed
below explores their (neuro) biological underpinnings. What of robots? Robots are
mechanical devices with silicon ‘brains’, not products of biological evolution. But as we
better understand biological systems we will extract ‘brain operating principles’ that do
not depend on the physical medium in which they are implemented. These principles
might then be instantiated for particular robotics architectures to the point where we
might choose to speak of robot-emotions.

4.2 Neuromodulation
Neuromodulation refers to the action on nerve cells of endogenous substances
called neuromodulators. These are released by a few specialized brain nuclei that have
somewhat diffuse projections throughout the brain and receive inputs from brain areas
that are involved at all levels of behaviour from reflexes to cognition. Each
neuromodulator typically activates specific families of receptors in neuronal membranes.
The receipt of its own neuromodulator by a receptor has very specific effects on the
neuron at various time scales, from a few milliseconds to minutes and hours. Each neuron
has its own mixture of receptors, depending on where it is located in the brain.

Three main neuromodulation systems involved in emotion

4.2.1 Dopamine
In the mammalian brain, dopamine appears to play a major role in motor
activation, appetitive motivation, reward processing and cellular plasticity, and might be
important in emotion. Dopamine is contained in two main pathways that ascend from the
midbrain to innervate many cortical regions. Dopamine neurons in the monkey have been
observed to fire to predicted rewards Moreover, dopamine receptors are essential for the
ability of prefrontal networks to hold neural representations in memory and use them to
guide adaptive behaviour. Therefore, dopamine plays essential roles all the way from

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 7


NEUROTIC ROBOTS

‘basic’ motivational systems to working memory systems essential for linking emotion,
cognition and consciousness.

4.2.2 Serotonin
Serotonin has been implicated in behavioural state regulation and arousal, motor
pattern generation, sleep, learning and plasticity, food intake, mood and social behaviour.
The cell bodies of serotonergic systems are found in midbrain and pontine regions in the
mammalian brain and have extensive descending and ascending projections. Serotonin
plays a crucial role in the modulation of aggression and in agonistic social interactions in
many animals. In crustaceans, serotonin plays a specific role in social status and
aggression; in primates, with the system’s expansive development and innervations of the
cerebral cortex, serotonin has come to play a much broader role in cognitive and
emotional regulation, particularly control of negative mood or affect. The serotonin
system is the target of many widely used anti-depressant drugs.

4.2.3 Opioids
The opioids, which include endorphins, enkephalins and dynorphins, are found
particularly within regions involved in emotional regulation, responses to pain and stress,
endocrine regulation and food intake. Increased opioid function is associated with
positive affective states such as relief of pain, and feelings of euphoria, wellbeing or
relaxation. Activation of opioid receptors promotes maternal behaviour in mothers and
attachment behaviour and social play in juveniles. Separation distress, exhibited by
archetypal behaviours and calls in most mammals and birds, is reduced by opiate agonists
and increased by opiate antagonists in many species. Opiates can also reduce or eliminate
the physical sensation induced by a painful stimulus, as well as the negative emotional
state it induces. Opioids and dopamine receptors are two major systems affected by
common drugs of abuse.

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 8


NEUROTIC ROBOTS

CHAPTER 5.

MOTION PLANNING[5]

Progress in motion planning algorithms has enabled general and flexible solutions
for slowly moving robots, but we believe that in order to quickly and efficiently traverse
very difficult terrain, extending these algorithms to dynamic gaits is essential. In this
work we present progress towards achieving agile locomotion over rough terrain using
the LittleDog robot.

Fig. 5.1(a) Little Dog Robot and a corresponding five-link planar model

Fig. 5.1(b) Little Dog Robot and illustrated the geometric shape of the limbs and
body
A modified form of the Rapidly Exploring Random Tree (RRT) planning
framework to quickly find feasible motion plans for bounding over rough terrain. The
principal advantage of the RRT is that it respects the kinematic and dynamic constraints
which exist in the system; however for high-dimensional robots the planning can be

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 9


NEUROTIC ROBOTS

prohibitively slow. We highlight new sampling approaches that improve the RRT
efficiency. The dimensionality of the system is addressed by biasing the search in a low-
dimensional task space. A second strategy uses reach ability guidance as a heuristic to
encourage the RRT to explore in directions that are most likely to successfully expand the
tree into previously unexplored regions of state space. This allows the RRT to incorporate
smooth motion primitives, and quickly find plans despite challenging differential
constraints introduced by the robot’s under actuated dynamics. This planner operates on a
carefully designed model of the robot dynamics which includes the subtleties of motor
saturations and ground interactions.

5.1 Planning Approaches

Fig. 5.2 Planning Approaches

Planning algorithms have made significant headway in recent years. These


methods are particularly well developed for kinematic path planning in configuration
space, focusing on maneuvers requiring dexterity, obstacle avoidance, and static stability.
Sampling-based methods such as the RRT are very effective in planning in high-
dimensional humanoid configuration spaces. The RRT has been used to plan walking and
grasping trajectories amidst obstacles by searching for a collision-free path in
configuration space, while constraining configurations to those that are statically stable
(Kuffner et al. 2002, 2003). The robot is statically stable when the centre of mass (COM)
is directly above the support polygon, therefore guaranteeing that the robot will not roll
over as long as the motion is executed slowly enough. After finding a statically feasible
DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 10
NEUROTIC ROBOTS

trajectory of configurations (initially ignoring velocity), the trajectory is locally optimized


for speed and smoothness, while maintaining the constraint that at least one foot remains
flat on the ground at all times. This approach has been extended to account for moving
obstacles and demonstrated on the Honda Asimo (Chestnutt et al. 2005). An alternative
approach is to first generate a walking pattern while ignoring obstacles and collisions, and
then use random sampling to modify the gait to avoid obstacles while verifying
constraints to ensure the robot does not fall (Harada et al. 2007). Current methods are
adept at planning in high-dimensional configuration spaces, but typically only for limited
dynamic motions. Sampling-based planning algorithms are in general not well suited for
planning fast dynamic motions, which is governed largely by under actuated dynamics.

The use of static stability for planning allows one to ignore velocities, which
halves the size of the state space, and constrains the system to be fully actuated, which
greatly simplifies the planning problem. Statically stable motions are, however, inherently
conservative (technically a robot is truly statically stable only when it is not moving).
This constraint can be relaxed by using dynamic stability criteria (see Pratt and Tedrake
(2005) for review of various metrics). These metrics can be used either for gait generation
by the motion planner, or as part of a feedback control strategy. One popular stability
metric requires the centre of pressure, or the Zero Moment Point (ZMP), to be within the
support polygon defined by the convex hull of the feet contacts on the ground. While the
ZMP is regulated to remain within the support polygon, the robot is guaranteed not to roll
over any edge of the support polygon. In this case, the remaining degrees of freedom can
be controlled as if the system is fully actuated using standard feedback control techniques
applied to fully actuated systems. Such approaches have been successfully demonstrated
for gait generation and execution on humanoid platforms such as the Honda Asimo
(Sakagami et al. 2002; Hirose and Ogawa 2007), and the HRP series of walking robots
(Kaneko et al. 2004). Lower dimensional “lumped” models of the robot can be used to
simplify the differential equations that define ZMP.

5.2 Limit-Cycle Approach


Somewhat orthogonal to the planning approaches, a significant body of research
focuses on limit-cycle analysis for walking. Tools developed for limit-cycle analysis
allow one to characterize the behaviour of a particular gait, typically on flat terrain. Stable
limit-cycle locomotion can be achieved by using compliant or mechanically clever
designs that enable passive stability using open-loop gaits (e.g. Collins et al. 2005), or
DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 11
NEUROTIC ROBOTS

otherwise through the use of reflexive control algorithms that tend to react to terrain.
Recent applications of these strategies, for example on the Rhex robot (Altendorfer et al.
2001) and Big Dog (Raibert et al. 2008), have produced impressive results, but these
systems do not take into account knowledge about upcoming terrain.

Feedback control of under actuated “dynamic walking” bipeds has recently been
approached using a variety of control methods, including virtual holonomic constraints
(Chevallereau et al. 2003;Westervelt et al. 2003, 2007) with which impressive results
have been demonstrated for a single limit-cycle gait over flat terrain. In this paper, we use
an alternative method based on the combination of transverse linearization and time-
varying linear control techniques (Shiriaev et al. 2008; Manchester et al. 2009;
Manchester 2010). This allows one to stabilize more general motions, however a nominal
trajectory is required in advance, so this feedback controller must be paired with a motion
planning algorithm which takes into account information about the environment.

5.3 Dynamic Maneuvers


In order to use sample-based planning for a highly dynamic, under actuated robot,
the search must take place in the complete state space, as velocities play an important role
in the dynamics. This effectively doubles the dimension of the search. Furthermore, when
there are under actuated dynamics, the robot cannot accelerate in arbitrary directions, and
therefore can only move in state space in very limited directions. This makes
straightforward application of sample based planning extremely challenging for these
types of systems. In the second phase of the LittleDog program, our team began to
integrate dynamic lunging, to move two feet at a time (Byl et al. 2008; Byl and Tedrake
2009), into the otherwise quasi-static motion plans to achieve fast locomotion over rough
terrain. This paper describes the MIT team approach in the third (final) phase of the
project. We show that careful foot placement can be combined with highly dynamic
model-based motion planning and feedback control to achieve continuous bounding over
very rough terrain.

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 12


NEUROTIC ROBOTS

Fig. 5.3 Example of a hip trajectory, demonstrating position command (thin dashed
red), motor model prediction (solid magenta), and actual encoder reading (thick
dashed blue).

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 13


NEUROTIC ROBOTS

Fig. 5.4 Illustration of bounding up step with centre of mass trajectories indicated
nominal, open loop with perturbations, and stabilized with perturbation

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 14


NEUROTIC ROBOTS

CHAPTER 6.

LOCALIZATION SYSTEM[6]

localization system based on the fusion of visual information and sound source
localization, implemented on a social robot One of the main requisites to obtain a natural
interaction between human-human and human-robot is an adequate spatial situation
between the interlocutors, that is, to be orientated and situated at the right distance during
the conversation in order to have a satisfactory communicative process. Our social robot
uses a complete multimodal dialog system which manages the user-robot interaction
during the communicative process. One of its main components is the presented user
localization system. To determine the most suitable allocation of the robot in relation to
the user, a proxemics study of the human-robot interaction is required. The study has been
made with two groups of users: children, aged between 8 and 17, and adults. Finally, at
the end, experimental results with the proposed multimodal dialog system are presented.

6.1 Sound Source Localization Problem


An artificial auditory system may be used for three purposes:

(1) Sound source localization;


(2) To separate the sound sources into different channels;
(3) To extract sound features to perform different tasks such speech recognition, emotion
detection, or user identification.

In order to localize sound sources, according to the works presented in, there are
two main approaches to this problem. One of them is to study the amplitude differences
generated by a sound source among the microphones (or ears) used to perceive the signal.
This method is the one used in this work, and it is based on the comparison of the volume
differences between the microphones in order to determine the angular difference in
relation to the sound source. The microphone closest to the sound source should receive
the signal with the biggest amplitude in comparison to those received by the rest of
microphones. It must be said that the accuracy of this method is greatly influenced by the
reflection of the sound signal due to the objects present in the environment, such as walls
and furniture. The second method consists of the analysis of the phase differences
produced between the different signals received by each of the microphones related to the

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 15


NEUROTIC ROBOTS

same sound source. This method is based on the idea that the same signal generated by
the sound source will be perceived by the closest microphone before by the rest of them.
The accuracy of this second method depends on the size and the relative position of the
microphones: if the microphones are very close to each other, all of them will receive
almost the same signal.

There is a third method, not so extended due to its complexity that only needs one
microphone to localize the sound source. This method analyses the differences in the
spectrum produced by the same sound source from different positions in relation to the
microphone.

6.2 Interaction With Or Without Profiles


Consider that there are two types of interactions with a social robot: without and
with user profile. In the first one, the user interacts with the robot without having a
profile, typically because that is the user’s first interaction (maybe during a show or a
demo). Therefore, the robot behaviour focuses on catching the user’s attention. If the user
wants to interact with Maggie several times, it is convenient that they enrol in the system,
so that the robot can adapt its behaviour to the user profile. In the profile several features
are stored: age, name, gender, experience, and language. As mentioned, during an
interaction with a user profile, the dialog can be adapted to the user, and one feature that
needs adaptation is the interaction distance. Before loading the user profile it is necessary
to identify the user. In dialog system, the user is identified by his voice. In order to do
that, during the enrol dialog the system learns the specific features of the user’s voice
(voiceprints) and saves them in a file that will be used for user identification.

Fig. 6.1 Proxemics rules

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 16


NEUROTIC ROBOTS

6.3 Age
Analysing the collected data, age also influences the interaction distance. In
average, in the interaction with children from 8 to 10 years old, the normal distance to the
robot is bigger than 2 m, however, children over 10, and adults, decrease the interaction
distance to about 1 m, children under 10 years old feel more intimidated by the robot than
older children. Children over 10 years old feel more curious and try to interact more
closely with the robot. In the case of the adults, since they have already interacted with
robot in other occasions, they feel more comfortable.

6.4 Personality
Personality is a factor that influences proxemics as shown in. In experiments,
observed that, when the group of children is interacting with robot, those situated closer
to the robot are the most extrovert ones. On the contrary, the shy ones tend to keep a
certain distance to the robot, always looking at their teacher.

The most extrovert children interact with robot more enthusiastically, trying to
catch its attention over the rest of children. It is obvious that it is difficult to measure the
personality of the children, but in relation to HRI, it seems that the shyness degree is
related to the interaction distance and its duration.

6.5 Gender
Another factor that could influence proxemics is the gender of the user. It seems
that women prefer to be in front of the robot and men at the side. However, in studies, it
could not corroborate this statement, since no significant differences between the boys’
and girls’ behaviours were obtained.

6.6 Number Of Users


Although the dialog system is designed to interact with one user, that is, it is not
possible to load more than one profile at the same time; any user can actually talk to the
robot and perform some interactions in a cooperative mode. For this reason it is
interesting to study the interactions in groups. We have observed that, during interactions
with more than one child, the children tend to be very close to Maggie trying to catch the
robot’s attention separately. In fact, it has been observed that the same child who started

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 17


NEUROTIC ROBOTS

to interact alone with the robot (situated far from it) approaches Maggie when more
classmates are included in the interaction.

Fig. 6.2 Multimodal dialog system

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 18


NEUROTIC ROBOTS

CHAPTER 7.

ADVANTAGES , LIMITATIONS & APPLICATIONS[7]

7.1 Advantages
1. Work’s under extreme conditions
2. Good ability of problem solving
3. Constant and continuous work can be done
4. Perform tasks faster than humans and much more effectively and accurately
5. They can capture moments just too fast for the human eye to get, for example the
Atlas detector in the LHC project can capture ~ 600000 frames per second while
we can see at about 60
6. Most of robots are automatic so they can work by themselves without any human
interference

7.2 Disadvantages
1. Unemployment cause
2. Consumes more power
3. Need good maintenance
4. Costly
5. Complexity

7.3 Applications
Humanoid robots may used in
1. Space research centres
2. Medical field
3. Industries
4. Military
5. Education field
6. Chemical research centres
7. Programming & Logic solving
8. Mining industry
9. Entertainment field
10.Service provider field
DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 19
NEUROTIC ROBOTS

CHAPTER 8.

CONCLUSION AND FUTURE SCOPE[3]


The user localization system in addition with the proxemics research carried out
with users interacting, have studied proxemics ability to the multimodal dialog system.
This ability is the one responsible for positioning robot at the right place during the HRI
phase, making this process much more natural. In this sense, the dialog system is able to
adapt and to position the robot at the most appropriate distance for each communicative
situation. Both tasks outlined are required to achieve this task: the user localization
module, and the proxemics study.

In order to localize, the robot first computes the position of the user using the
sound source localization system, which makes use of eight microphones.

The goal interaction distance is determined according to the extracted rules


obtained from the proxemics study, depending on the type of user, that is, their age,
experience, etc. Once the robot has turned itself to face the user, it positions itself at the
goal distance from the user. The laser is used to determine the approximate distance of the
user and to maintain it close to the goal one.

In the near future, expect to try a similar planning algorithm on a dynamic biped
to achieve walking over rough terrain, and on a forklift operating in a highly constrained
environment.

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 20


NEUROTIC ROBOTS

CHAPTER 9.

REFERENCES

1. www.wikipedia.com
2. Emotional Interaction with a Robot Using Facial Expressions, Face Pose and
Hand Gestures Regular Paper Myung-Ho Ju and Hang-Bong Kang Received 31
May 2012; Accepted 16 Jul 2012
3. Emotions: from brain to robot by Michael A. Arbib1 and Jean-Marc Fellous,
Computer Science, Neuroscience and USC Brain Project, University of Southern
California, Los Angeles, CA 90089-2520, USA
4. Influences on Proxemic Behaviors in Human-Robot Interaction by Leila
Takayama and Caroline Pantofaru
5. Bounding on Rough Terrain with the LittleDog Robot
The International Journal of Robotics Research The International Journal of
Robotics Research published online 7 December 2010 byAlexander Shkolnik,
Michael Levashov, Ian R. Manchester and Russ Tedrake
6. User Localization During Human-Robot Interaction by F. Alonso-Mart´ın *, Javi
F. Gorostiza, Mar´ıa Malfaz and Miguel A. Salichs, Robotics Lab, Universidad
Carlos III de Madrid, Av. de la Universidad 30, 28911 Legan´es, Madrid, Spain;
E-Mails: jgorosti@ing.uc3m.es (J.F.G.); mmalfaz@ing.uc3m.es (M.M.);
salichs@ing.uc3m.es (M.A.S.)
7. www.google.co.in

DEPARTMENT OF MECHANICAL ENGINEERING, JCE BELAGAVI. Page 21

You might also like