ArticlePDF Available

Robot Based Logistics System for Hospitals - Survey


Abstract and Figures

This paper is a survey on autonomous hospital logistics sys- tems. We present commercial products that are successfully installed in the hospitals and research projects proposed by various researches from around the world. Such systems in- clude mobile robots that need to navigate and safely move in a human populated environment. These robots are spe- cial designed to carry various goods that need to be trans- ported. Autonomous hospital logistic systems can include also user interfaces, mission planners, delivery and pick-up stations, parking and charging stations or special designed carts. We describe and compare the various approaches and systems functionalities. We specify the main problems and challenges that need to be considered when designing such systems. The innovative approach that could be an e-cient solution for hospital transportation is also presented.
Content may be subject to copyright.
Robot Based Logistics System for Hospitals - Survey
Karol Niechwiadowicz
Örebro University
Zahoor Khan
Mälardalen University
This paper is a survey on autonomous hospital logistics sys-
tems. We present commercial products that are successfully
installed in the hospitals and research projects proposed by
various researches from around the world. Such systems in-
clude mobile rob ots that need to navigate and safely move
in a human populated environment. These robots are spe-
cial designed to carry various goods that need to be trans-
p orted. Autonomous hospital logistic systems can include
also user interfaces, mission planners, delivery and pick-up
stations, parking and charging stations or special designed
carts. We describe and compare the various approaches and
systems functionalities. We specify the main problems and
challenges that need to be considered when designing such
systems. The innovative approach that could be an efficient
solution for hospital transportation is also presented.
There exist several commercial products that are success-
fully installed in hospitals [1], [6] or [23] and there are many
projects that are currently progressed in research groups
around the world [2] or [4]. It is proved and tested that
autonomous delivering improves the efficiency of the hospi-
tal transportation [1], [6], [12] or [16]. Special analysis in [16]
showed that installation of 6 robot units reduces the annual
cost by approximately 56% and improves turn-around time
p erformance by 33%. Implementing such a system brings
several advantages:
1. It is cost efficient.
2. Robots never get sick, do not need holidays and work
also in weekends.
3. Robots are predictable and do not make human mis-
4. An autonomous system can work 24 hours 7 days per
5. Hospital personnel can focus on patients.
6. Transportation tasks could be scheduled and done in
the night shifts.
There are many items that could be transported on robot’s
b ody within hospitals: medicines, medical devices, speci-
mens, food, shoppings, documents, waste, etc.
Ozkil et al.
[15] made a deep study on things that are transported within
Contact author
the hospitals every day. Goods are divided into groups and
authors presented estimated amount that are transported
every day and with quantity of personnel that are needed
for this reason. Other aspect of hospital transportation is to
carry carts that could contained linens, laundry, meals, etc.
This is still a challenge to introduce mobile robots for ma-
neuvering safely and fast in human populated environments
such as factories, offices or hospitals. The problem of mobile
robot delivery in highly populated environment is widely
described in [10]. In [22] a list of the topics that need to
be considered when designing a robot-friendly hospital was
presented. Designing such a system involve the knowledge
from several areas, such as: project management, mechani-
cal technology, control systems, artificial intelligence or com-
munication networks.
This paper goes through existing systems and solutions and
it describes the state of the art in the hospital transporta-
tion. There is a list of challenges that need to be consid-
ered when designing such complicated system. We believe
that our survey will be helpful for all of the researchers that
would like to design a robot based logistic system for hos-
pitals. Hada and others [10] presented the state of the art
of different approaches in robot navigation in human popu-
lated environments. Several examples of systems that pro-
vide transport in hospitals can be found in [15]. However
there is no available work that goes through approaches of
serving the autonomous transportation within the hospitals.
The rest of this pap er is organized as follow: section 2
presents the main challenges that could be met, when de-
signing robot-based logistics systems for hospitals. The third
section describes the functionalities of existing commercial
products and research projects. In section 4 the innovative
approach to hospital logistic systems is presented.
Hospital environment brings many constraints that system
need to fulfill. In [5] problems and challenges for transport-
ing in such environment are pointed. Authors of [18] present
requirements that every autonomous system need to fulfill
to transport goods within the hospitals.
Nowadays not too many new hospitals are built. Therefore
it is more required to design a new autonomous system that
can be adopted to an existing hospital environment, than
to design autonomous system and then design a new hos-
pital that can fulfill such system requirements. The main
challenges, when designing robot-based logistics system for
hospital, are:
Safety - When robots are sharing space with p eople,
the safety is the first thing that need to be considered.
We have to be sure that robots would not collide with
p eople and would stop or safely pass the obstacles on
its way.
Obstacle detection - How to place sensors on a robot
platform and which sensors should be used to achieve
detailed area scan around the robot.
Map of the environment - How to build a map.
Path planning - How to plan the path to go from start
to destination point.
Follow the path - Keep the preplanned path and make
sure that robot will reach the final destination.
Navigation - During the motion it is needed to know
continuously the position and orientation of the robot.
The easiest way is to install artificial landmarks. How-
ever in some cases it is not allowed to place extra land-
marks. In environments like hospitals it’s preferable
to install as less extra points as possible. Navigation
using only natural landmarks (walls, lamps, corners,
etc.) brings new challenges.
Robots need to navigate in narrow environment.
Organize logistics - How to organize the cooperation
b etween robot units and supervisory system. How to
organize ordering the tasks.
Each mission should be monitored and system should
b e still working if one of the units fails.
Automatic use of doors and elevators - System should
b e able to control doors and elevators and use them
without human interfere.
Wireless communication - How to plan the network,
where place the access points, etc.
Installation of the robot charging and parking stations.
Installation of the pickup/delivery stations.
User interface - This is important that interface is easy
to use and that a proper request is send later to the
task-scheduling server.
Stable transportation - Goods like meals or specimen
demand very stable carrying. Random people should
not have access to the transported items.
Next section 3 goes through existing commercial products
and research projects. It is presented how various systems
deal with listed challenges.
3.1 Commercial systems
There exist several commercial systems that are known and
which are already successfully installed in the hospitals. Be-
low we present examples of such systems, their functionali-
ties and main features.
Figure 1: HelpMate robot
3.1.1 Helpmate
Evans in [6] presented the system technologies embodied in
HelpMate (see Figure 1). HelpMate works as follow:
1. Hospital personnel (operators) place the goods in a
sp ecial designed shelves installed on robot’s platform.
2. Operator selects a destination or destinations from the
map displayed on robot GUI (Graphical User Inter-
3. Robot is building a mission plan (a path to go).
4. Robot starts to go to destination on preplanned path.
If meets an obstacle, robot tries to go around and if
there is no path to go then robot is waiting till obsta-
cles will be removed.
5. When goods are delivered, a person that receives them,
needs to confirm that mission is finished.
Each robot has its own mission plan and path to go. There
is a simple supervisory system that helps when two or more
robots compete for critical resources such as elevators or
narrow corridors. In [5] more detailed information of Help-
Mate navigation can be found. This robot uses odometric
system [7] and natural landmarks (hallway walls) due to the
continuous p osition estimation. The robot can transport
unscheduled meal trays, lab, pharmacy supplies or patient
records. On doors and elevators are installed special con-
trol computers that robot can communicate with through
an infrared transceiver. The map is generated by the instal-
lation engineer via an off-line special designed application.
Robot has a flashing warning light and emergency STOP on
its body. At the beginning of the project ultrasonic sensors,
lights in front and bumpers were installed for obstacle de-
tection. HelpMate example shows that such system could
be continuously improved corresponding to the technology
novels. In [21] last updates about the product and short
commercial history are described. In the last system ver-
sion light sensors have been replaced with a laser scanner
for more detailed area scan and to achieve more efficient
obstacle avoidance function. HelpMate was one of the first
products that served the robot transportation within the hu-
man populated environments and it is treated as a pioneer
in autonomous systems for hospitals. Nowadays HelpMate
is a registered trademark of Cardinal Health, Inc. but there
is no information available about current product status.
Figure 2: Swisslog robot
3.1.2 Swisslog
Swisslog developed a TransCar AGV (Automated Guided
Vehicle) system for carts transportation [23]. It includes a
flat robots (see Figure 2) that are going under the carts, lift
them and deliver to desired position. The operator places
a cart in a pick-up station and enters a destination on a
wall-mounted terminal. Then all of the transport activities
are handled automatically. There is no information avail-
able if it is possible to schedule a task that will b e executed
To install this system in the hospital, the environment need
to fulfill many needs. List of the topics that should be con-
sidered when designing a hospital are presented in [23]. The
advantage of this system is that robot can carry on its body
most of the cart types. The only requirement is that the
trailers need to be wide and high enough that swisslog robot
could go under them. Therefore there is no need of buying
new carts and system could be adopted to the trailers that
already exist in the hospital. An disadvantage of this sys-
tem is that it can not carry simple items on its body such
as medicines, documents, fo od, etc.
3.1.3 Hospi
The Matsushita’s Robotic Blood Sample Courier System
[25] consists a group of autonomous mobile robots (see Fig-
ure 3).The System is designed to control blood samples de-
livery and other transportation tasks within the hospitals
and the laboratories. The main computer assigns various
tasks to individual robots who pick up blood samples, de-
liver them to automatic analyzers, and collect the samples
after testing. Robots detect obstacles through laser scanner
and can provide free of collisions path. Matsushita’s sys-
tem include also group control system that monitors robot
missions, solves failure situations, control robot’s batteries
level, etc. (full list [25]). Each vehicle unit is equipped with
p ositioning mechanism that provides high precision in spec-
imens pickup and delivery.
3.1.4 Aethon
Aethon designed an automated system for transporting and
tracking hospital goods [1]. There are two developed robot
systems: TUG (see Figure 4) and HOMER. TUG robot
transp orts a special designed carts within the hospitals. The
functionality of carts transportation is similar to Swisslog
system 3.1.2. Robot is a flat unit that goes under the carts,
Figure 3: Hospi robot
Figure 4: TUG robot
lifts them and safely delivers to selected place. There are
several types of designed carts and they are divided based
on the items that they are transporting. There are follow-
ing carts: central supply, nursing, pharmacy, lab, medical
records, dietary, linens. Each cart is designed to provide
most efficient and safety transport for its items type. Carts
are equipped with touch screens, basic control buttons and
electronic lo cks. TUG robot is equipped with light sensors
to detect obstacles on its way. HOMER is the RFID-based
(Radio frequency identification) asset management solution
that can locate hospital equipment. HOMER robot runs
around the hospital and checks (through reading RFID la-
bels) if equipment such as beds, wheelchairs, carts, etc. are
in the right place. HOMER cooperates with TUG system.
When one of the items is detected in wrong place and it is
possible to transport it by TUG robot, then the TUG robot
gets an order to move this item to the proper position.
The disadvantage of this system is that robot can transport
only specific carts. It increases the costs of the system in-
stallation and requires more changes in the hospital logistics
than for example in Swisslog system, see 3.1.2.
3.1.5 SpeciMinder
CCSRobotics provided an efficient specimen delivery sys-
tem [20]. The robot’s (see Figure 5) autonomous features
are based on MobileRobots [13] technology. This system al-
lows robot to navigate without artificial landmarks. Upon
Figure 5: SpeciMinder robot
installation, the robot builds a map of the environment and
later uses this map for planning the mission. In this system
the request of delivery is made on robot’s body interface.
User places the items on the robot and then select a desti-
nation. When the task is done robot goes back to its station.
An disadvantage of this system is that items and tasks can
not be scheduled. SpeciMinder is successfully installed in
Delaware Hospital in the United States.
3.1.6 Commercial products summary
The summary of the commercial products is presented in
Table 1 and in Table 2. The collected information is based
on the referred articles and commercial products descrip-
tions. In some cases it was not possible to find specific facts
or available information were not enough to specify the fea-
ture status. In such situations a ’not available - na.’ status
was declared. In tables we included also a RobCab system,
which is described more detailed in Section4.
Description of transportation functionalities:
Specific goods transportation - robot is designed to
transp ort only specific goods on its platform (meals,
blo od sample, etc.)
Varied goods transportation - robot is able to carry
any goods that are placed in a special box on/in its
Carry carts on its body - robot is designed to go under
the carts, lift them and next transport to the desired
Tow the trailers - robot can grab a trailer and tow it
to wanted position.
Description of logistic systems features:
Group of robot cooperation - robots are working as a
fleet of units, they can share an environment sources
in a scheduled order.
Supervisory system - Supervisory system plans, sched-
ules and sends the mission plan to the specific robot
that executes the mission. Each robot and mission can
b e monitored on-line.
Ordering on robot’s platform - robot is equipped with
GUI, which allows the personnel to define a task.
Ordering through logistic system - personnel define a
task through logistic system. GUI could be placed
at any place in a hospital that has connection to the
logistic system.
Task scheduling - tasks can be scheduled off-line and
set to specific time. Tasks could be repeated with de-
sired frequency.
Automatic elevator service - elevators can be controlled
by autonomous system.
Artificial landmarks - it is needed to install artificial
landmarks for navigation needs.
System installed in hospital - system is successfully
working at least in one of the hospitals.
3.2 Research systems
In this section we present several research projects that pro-
pose autonomous logistic systems for hospitals. Main as-
pects are described and characteristic features are pointed
and commented.
3.2.1 FIRST
FIRST (Friendly Interactive Robot for Service Tasks) [18]
is another mobile robot system to transport carts within
the hospitals. During 3 months installation in hospital at
Clamart near Paris system features were tested. However
there is no information if nowadays it is working at any
hospital. Development of this project is presented in [4].
The system could be divided into:
Ground Station - acquiring missions from the opera-
tors, scheduling missions, assigning missions to robots,
path planning, supervising missions, etc.
Robots - transporting goods along predefined paths
and safely maneuvering around people.
One of the advantages of this system is a function to simulate
mission plans for each robot. When mission is planned and
scheduled, first it is simulated in order to emulate the fleet
of robots in an automatic mode. Thanks to this a behavior
of robots can be predicted and it can be ensured that there
will be no conflicts in real world.
3.2.2 i-Merc
A group from Technical University of Lisbon, developed
a mobile robot system to deliver meals inside health ser-
vices [2]. To perform the service they designed the robot
called i-Merc. This robot is equipped with heating sys-
tem to keep temperature of meals and prevents bacterio-
logic proliferation. It provides more hygienic and efficient
meal transportation and is able to deliver personalized di-
ets. First stage of this project with a service concept and
virtual and physical prototype is described in [2]. Authors
focused on the transportation meals from the kitchen to the
patients’ rooms and returning the respective soiled dishes
safely. Chassis structure analysis which could be useful when
designing a new robot is also provided.
HelpMate Swisslog Hospi Aethon SpeciMinder RobCab
Sp ecific goods
transp ortation No No Yes No No No
Varied goods
transp ortation Yes No Yes No Yes Yes
Carry carts
on its body No Yes No Yes No No
Tow the
carts No No No No No Yes
Table 1: Transportation functionalities
HelpMate Swisslog Hospi Aethon SpeciMinder RobCab
Group of robots
co operation Yes Yes Yes Yes No Yes
Sup ervisory
system No Yes Yes na. No Yes
Ordering on
rob ot’s platform Yes No na. No Yes No
Ordering through
logistics system No Yes Yes na. No Yes
scheduling No na. na. na. No Yes
elevator service Yes Yes na. Yes Yes Yes
landmarks No No No na. No No
System installed
in hospital Yes Yes Yes Yes Yes No
Table 2: Functionalities of logistic systems
Carreira et al. presented in [3] fuzzy controller model [26]
and simulation results for i-Merc. Robot is able to deliver
meals and navigate between start and destination point.
Since authors in [2] were more focused on the developing
the structure of the system and in [3] on navigation, there
are many aspects in this system that were not considered or
just mentioned. Areas like map building, localization, power
management, sensors placement or safety motion would need
further developments.
3.2.3 Other projects
The authors of [8] presented a system that uses florescent
lamps on the ceiling of the corridors as natural landmarks
to localize a robot position and orientation. The robot uses
single camera to capture images of the lamps.This robot, in
opp osite to other robots described in our paper, has holo-
nomic ability to move in any direction without changing ori-
entation. Structure of ordering the task is similar as in 3.1.1
or 3.1.5. Touchscreen interface is installed on the robot’s
platform. User places the items to transport in the locker
and selects the destination from the map. Then robot plans
the map and starts to navigate in order to reach the destina-
tion point selected by operator. System has been tested in
the laboratory and in the Prince of Wales Hospital in Hong
Hada et al. [10] introduced an advanced AGV (Automat-
ically Guided Vehicle) that can work not only in hospitals
but in any populated environment, such as offices. They
also described the design policy, methodology, implementa-
tion and experimental results. Navigation is solved by using
iGPS (indoor Global Positioning System) server [9], which
tracks the robots within the area covered by cameras. This
mean that only for navigation needs there is a need to in-
stall many cameras in the environment where the robot is
going to maneuver. The authors of [10] presented also the
man-robot interface, which allows to request a delivery and
also monitor the progress of the requested task. Delivery
task-scheduling server is divided into three parts. It allo-
cates the request to specific robot, manages the execution
of primitive task sequences and controls the elevator oper-
ating devices. Such elevator’s manipulation device consists
radio control servos that operate the elevator by pushing
the buttons. However this solution is not so practical and
nowadays there exist much more common wireless solutions,
such as in described products [23], [1] or [20]. Mobile robot
in this system follows its path and stops when sensors detect
an object on the path. Robot waits 5 seconds and checks if
the object is still there, if yes then robot tries to avoid it if
there is enough place. The disadvantage of this solution is
that robot might be stuck in one place for longer time, when
still there is a place to go. It is necessary that people would
collaborate with robots, and would change their position if
they stay on robots path. Experiments show that there still
is a need to improve navigation system. Since when people
cover the iGPS cameras, robot has a problem to position
itself by using only odometric system[7].
Ozkil et al. proposed in [15] a system that consists group of
rob ot units, automatic stations and sp ecial designed con-
tainers for automation transportation of goods in hospi-
tals. The overall system structure is described and necessary
mo difications in hospital infrastructure are also presented.
Rob ot in this system is a part of a group of robots that
are controlled by remote server that control also elevator
service. There are three modes of transportation: shuttle -
transp orting goods from one station to another. Bus mode -
enabling to coverage of multiple stations in a defined route.
Taxi mode - transportation upon request. Robot similar to
system presented in 3.1.4 carries special designed containers
on its body. Each container has an embedded transponder.
Stations are equipped with a pneumatic lift to provide auto-
matic loading and unloading containers from the robots. Su-
p ervisory control system plans the route of the robot in or-
der to fulfill all scheduled deliveries and avoid conflicts that
result from different user requests. Beside main supervisor
on each robot is installed local interface, that in case of the
failure of the wireless communication can take responsibil-
ity of collecting the orders. For localization purposes several
reflectors are placed in the routes as landmarks, which help
rob ots to correct their positions. Several access points for
wireless communication are placed around hospital. Tests
in Bispebjerg hospital showed that some modifications need
to be done to improve system infrastructure.
Shieh and others [19] presented Intelligent Hospital Service
Rob ot (IHSR). Personnel of different departments of the
hospital order items through internet. These orders are col-
lected by staff of chart room and next the items are placed
into the rob ot. Next operator of the robot enter the de-
tailed tasks into robot system and robot starts to execute
its mission. System had been tested in a simulator.
In a system proposed by Takahashi and others [24] a patient
puts his or her personal belongings on trays. These trays
are stored in a special tray racks and robot goes back and
forward between patient and the tray rack. The idea of this
project is that patients would be able to store their private
b elongs in a special selected place and not only in a small
b ox close to the bed. Robot follows guide lines that are
placed on the floor or ceiling. In the paper authors present
also a guide how to place such lines, which robot treats as
The RobCab AB from aster˚as started the project to de-
velop a mobile robot system for transportation within the
hospitals. Robot will be able to carry goods on its body, tow
the trailer and move safe and fast in the human populated
environment with and without the trailer. Implemented al-
gorithm has been tested on testing platform (see Figure 6)
in a hospital like environment. An example scenario could
lo oks as follow:
1. Nurse at floor 5 orders several items from the hospi-
tal supermarket (floor 1) through friendly interface.
Nurse selects that items should be delivered to the
station number 13 (Station13).
2. Supermarket’s employee collects the order, places the
items in the station (Station7) and confirms that goods
Figure 6: RobCab testing platform
are collected.
3. Supervisory system receives an order, plans and sched-
ules a mission and sends a mission plan to the robot
that at current moment would execute such a mission
with a minimal cost. Lets called this robot Penguin2.
4. Penguin2 receives the mission and starts to execute it.
Firstly goes to the Station7, automatically collects the
go ods and places them in a locked box.
5. Penguin2 goes to the elevator and supervisory system
calls the elevator.
6. When elevator arrives Penguin2 checks if there is a free
area inside and enters.
7. Supervisory system sends the elevator to fifth floor and
when it arrives Penguin2 leaves the elevator and goes
to the Station13.
8. In a meanwhile Supervisory system receives an order
that a trailer with the dirty linens (TrailerA) needs to
b e transported from a parking place (PlaceP) at floor 5
to the laundry in a basement. Supervisory system col-
lects an order and plans and schedules a mission. Since
it is known that Penguin2 will soon finish his current
mission close to the PlaceP, Supervisory system sends
a mission plan to Pinguin2, who puts a mission in a
9. Penguin2 leaves the items at Station13, sends a con-
firmation to the Supervisory system and starts to ex-
ecutes next mission.
10. Penguin2 goes to the PlaceP, docks to the TrailerA
and grabs it.
11. Penguin2 pulls the TrailerA, enters the elevator and
exits it in a basement (elevator control is the same as
in the case when going without a trailer).
12. Penguin2 delivers the TrailerA to the laundry station,
sends a confirmation, goes to the one of the empty
charging stations and waits for the next mission from
the Supervisory system.
From above scenario it could be concluded that this same
rob ot unit is able to carry goods on its body and tow a
trailer. An extra capability that makes this system more
complicated than others described in this paper is a function
to drive with a trailer. Mobile robot when towing a trailer
is a highly nonlinear mo del and control such a model is not
a trivial thing [11], [14], [17]. This is one of the biggest chal-
lenges within this project. Robot needs to deliver a trailer
to the selected parking station and safely maneuvers around
p eople. Moreover there are also other technical aspects that
need to be challenged: detection a type of the trailers with-
out placing the landmarks, precise grabbing and releasing
the trailers, stable connection when moving or obstacles de-
tection around the trailer.
RobCab’s system includes also other main functionalities
that autonomous system should fulfill, which is pointed in
Table 1 and in Table 2. The system pilot installation in one
of the hospitals is planned at the end of the year 2009.
This paper describes the main challenges that could be met,
when designing a robot-based logistics system for hospitals.
The existing systems, solutions and state of the art in the
autonomous transportation within the hospitals has been
presented. The innovative approach has b een also described.
In the future work we want to develop a presented RobCab
system and finalize the pilot installation in one of the hos-
[1] Aethon. Tug - the automated system for transporting
and tracking hospital goods [online]. Available from: [accessed 6 October 2008],
[2] F. Carreira, T. Canas, A. Silva, and C. Cardeira.
i-merc: A mobile robot to deliver meals inside health
services. Proceedings of 2006 IEEE/RAM, 2006.
[3] F. Carreira, T. Canas, A. Silva, and C. Cardeira. A
fuzzy controller for a health services mobile robot.
IEEE, 2007.
[4] O. Causse and L.-H. Pampaganin. Management of a
multi-robot system in a public environment. IEEE,
[5] J. Evans, B. Krishnamurthy, B. Barrows, T. Skewis,
and V. Lumelsky. Handling real-world motion
planning: A hospital transport robot. IEEE, 1992.
[6] J. M. Evans. Helpmate: An autonomous mobile robot
courier for hospitals. Proceedings IROS, pages
1695–1700, 1994.
[7] L. Feng, J. Borenstein, and B. Everett. Where am i?
sensors and methods for autonomous mobile robot
lo calization. Technical Report, The University of
Michigan UM-MEAM-94-21, 1994.
[8] W. K. Fung, Y. Y. Leung, M. K. Chow, Y. H. Liu,
Y. Xu, W. Chan, T. W. Law, S. K. Tso, and C. Y.
Wang. Development of a hospital service robot for
transp orting task. Proceedings of the IEEE, 2003.
[9] Y. Hada and K. Takase. Multiple mobile robot
navigation using the indoor global positioning
system(igps). Proceedings IROS, pages 1005–1010,
[10] Y. Hada, K. Takase, H. Gakuhari, and E. I. Hemeldan.
Delivery service robot using distributed acquisition,
actuators and intelligence. Proceedings of 2004
IEEE/RSJ International Conference on Intelligent
Robots and Systems, pages 2997–3002, 2004.
[11] F. Lamiraux, S. Sekhavat, and J. P. Laumond. Motion
planning and control for hilare pulling a trailer. IEEE
Transactions on Robotics and Automation, vol. 15,
no. 4, 1999.
[12] W. F. Long. Nist special publication 950-1 [online].
Available from:
[accessed 28 August 2008], pages 41–44, 1999.
[13] MobileRobots. Intelligent robots for commercial and
research applications[online]. Available from: [accessed 28 August
[14] M. Nakamura and S. Yuta. Trajectory control of
trailer type mobile robots. In proceedings of the
IEEE/RSJ International Conference on Intelligent
Robots and Systems, 1993.
[15] A. G.
Ozkil, S. Dawids, Z. Fan, and T. Srensen. Design
of a robotic automation system for transportation of
go ods in hospitals. Proceedings of the 2007 IEEE
International Symposium on Computational
Intelligence in Robotics and Automation, 2007.
[16] M. D. Rossetti, A. Kumar, and R. A. Felder. Mobile
rob ot simulation of clinical laboratory deliveries.
Proceedings of the 1998 Winter Simulation
Conference, pages 1415–1422, 1998.
[17] J. Ryu, S. K. Agrawal, and J. Franch. Differential
flatness based controller designs for a mobile robot
with a trailer. In proc. of the IEEE International
Conference on Robotics and Automation, 2006.
[18] F. Sandt and L.-H. Pampaganin. Perception for a
transp ort robot in public environments. IEEE, 1997.
[19] M. Y. Shieh, J. C. Hsieh, and C. P. Cheng. Design of
an intelligent hospital service robot and its
applications. IEEE International Conference on
Systems, Man and Cybernetics, 2004.
[20] SpeciMinder. Ccs robotics - pioneers of autonomous
mobile robot solutions[online]. Available from: [accessed 28 August
[21] Spinoff. 100 years of powered flight [online]. Available
[accessed 28 August 2008], pages 16–17, 2003.
[22] Swisslog. 12 important considerations for planning
your agv robot-friendly hospital [online]. Available
[accessed 28 August 2008], 2006.
[23] Swisslog. Integrated logistics solutions for warehouses,
distribution centers and hospitals [online]. Available
from [accessed 5 October
2008], 2008.
[24] Y. Takahashi, M. Kohda, Y. Kanbayashi,
K. Yamahira, and T. Hoshi. Tray carrying robot for
hospital use. IEEE, 2005.
[25] M. E. Works. Automatic robotic blood sample courier
system[online]. Available from:
01.htm [accessed 28 August 2008],
[26] L. A. Zadeh. Fuzzy sets. Information and Control, vol.
8, pages 338–353, 1965.
... In the category Supportive (where robots assist in the performance of the task, providing tools or information), we find robots like TUG (Mutlu and Forlizzi, 2008;Niechwiadowicz and Khan, 2008;Zhang et al., 2008;AETHON, 2020), a robot to perform logistics activities in hospitals; BUDDY (Buddy Robotics, 2020), which has multiple functionalities at home (entertainment, monitoring old people, and reminding tasks and events); and AuRoRoll (German Federal Ministry of Education and Research, 2017; Wimmer et al., 2017) (when in automatic mode) a wheelchair capable of navigating autonomously. The parameters "Proximity" and "Autonomy" for these robots are identified as follows: ...
Full-text available
An increase of the aging population with a decrease in the available nursing staff has been seen in recent years. These two factors combined present a challenging problem for the future and has since become a political issue in many countries. Technological advances in robotics have made its use possible in new application fields like care and thus it appears to be a viable technological avenue to address the projected nursing labor shortage. The introduction of robots in nursing care creates an active triangular collaboration between the patient, nurse, and robot, which makes this area significantly different from traditional human–robot interaction (HRI) settings. In this review, we identify 133 robotic systems addressing nursing. We classify them according to two schemes: 1) a technical classification extended to include both patient and nurse and 2) a novel data-derived hierarchical classification based on use cases. We then analyze their intersection and build a multidimensional view of the state of technology. With this analytical tool, we describe an observed skew of the distribution of systems and identify gaps for future research. We also describe a link between the novel hierarchical use case classification and the typical phases of nursing care from admission to recovery.
... Robots have demonstrated tremendous utility as both independent and collaborative physical assistants in activities ranging from making deliveries in hospitals (Mutlu & Forlizzi, 2008;Niechwiadowicz & Khan, 2008) to working as assembly-line workers in factories (Akella et al., 1999;Jarrasse et al., 2014;Sauppé & Mutlu, 2015). Recent research into human-robot teaming, however, reveals a tremendously powerful yet unexplored potential for robots to not only serve as substitutes for people in repetitive, hazardous, or demanding tasks but to augment and complement human cognitive and physical capabilities, thereby enabling people to engage in work activities that were previously unsafe, unhealthy, mentally challenging, or unfeasible (Michalos et al., 2015;Pearce et al., 2018). ...
Objective Trade-offs between productivity, physical workload (PWL), and mental workload (MWL) were studied when integrating collaborative robots (cobots) into existing manual work by optimizing the allocation of tasks. Background As cobots become more widely introduced in the workplace and their capabilities greatly improved, there is a need to consider how they can best help their human partners. Methods A theoretical data-driven analysis was conducted using the O*NET Content Model to evaluate 16 selected jobs for associated work context, skills, and constraints. Associated work activities were ranked by potential for substitution by a cobot. PWL and MWL were estimated using variables from the O*Net database that represent variables for the Strain Index and NASA-TLX. An algorithm was developed to optimize work activity assignment to cobots and human workers according to their most suited abilities. Results Human workload for some jobs decreased while workload for some jobs increased after cobots were reassigned tasks, and residual human capacity was used to perform job activities designated the most important to increase productivity. The human workload for other jobs remained unchanged. Conclusions The changes in human workload from the introduction of cobots may not always be beneficial for the human worker unless trade-offs are considered. Application: The framework of this study may be applied to existing jobs to identify the relationship between productivity and worker tolerances that integrate cobots into specific tasks.
... Unquestionably, today, 60 years later, the boom in the robotics market is clear, behind which has been the active development of robotics technologies and artificial intelligence. So far, robots with skill learning have generally appeared in industrial manufacturing [1,2], logistics [3], field robotics [4], surgery [5] and other fields. In addition to these common areas, robots are also expanding into nursing [6], human-robot collaboration [7], autonomous vehicles [8] and transfer learning [9] (i.e. ...
Full-text available
Abstract A conventional robot programming method extensively limits the reusability of skills in the developmental aspect. Engineers programme a robot in a targeted manner for the realisation of predefined skills. The low reusability of general‐purpose robot skills is mainly reflected in inability in novel and complex scenarios. Skill transfer aims to transfer human skills to general‐purpose manipulators or mobile robots to replicate human‐like behaviours. Skill transfer methods that are commonly used at present, such as learning from demonstrated (LfD) or imitation learning, endow the robot with the expert's low‐level motor and high‐level decision‐making ability, so that skills can be reproduced and generalised according to perceived context. The improvement of robot cognition usually relates to an improvement in the autonomous high‐level decision‐making ability. Based on the idea of establishing a generic or specialised robot skill library, robots are expected to autonomously reason about the needs for using skills and plan compound movements according to sensory input. In recent years, in this area, many successful studies have demonstrated their effectiveness. Herein, a detailed review is provided on the transferring techniques of skills, applications, advancements, and limitations, especially in the LfD. Future research directions are also suggested.
... However, when the environment becomes more complex (a crowded environment, dynamic….), It appears essential for the robot to be endowed with decision-making capacities capable of making it react to the hazards that may interfere with its movements (partial failures, obstacles with complex shapes) [2]. This may be the case when the mobile robot operates in environments hostile to humans (radioactive environment) or too far away (space exploration). ...
... Logistic robots are widely used in industry, warehouse, and manufacturing to automate the storing or moving goods. In near future, smart logistic robots with an integrated infrastructure will roam around the Hospital to move food, lab samples, and other logistics [48]. ...
Advancement in robotic technology triggered its usability in the next generation healthcare system. Healthcare robots are expected to assist clinicians and healthcare professionals at all settings by monitoring patient’s physiological conditions in real time, facilitating advanced intervention such as robotic surgery, supporting patient care at the hospital and home, dispensing medication, assisting patients with cognition challenges and disabilities, keeping company to geriatric and physically/mentally challenged patients and hospital building management such as disinfecting places. Thus, the robotic agent can enhance healthcare experiences by reducing patient care work and strenuous/repetitive manual tasks. The robotic applications can also be elongated in supporting the healthcare system for the management of pandemics like novel coronavirus (COVID-19) infection and upcoming pandemics. Such applications include collecting the sample from a patient for screening, disinfecting the hospital, supply logistics, and food to the infected patient, collect physiological conditions. This chapter aims to provide an overview of various types of assistive robots employed for healthcare services especially in fighting pandemic and natural disasters.
Automated guided vehicles (AGV), which are frequently used to reduce the workload of employees in production systems, are now being used in service systems. AGV has been widely used in the field of healthcare and is well suited to transporting. This study aims to provide AGV is being used in different areas of healthcare today within the scope of Industry 4.0. In recent years, the use of AGV has started to increase to reduce the workload and contamination risk of healthcare workers. In this study, it was aimed that AGVs would distribute autonomous drugs by processing patient information such as age, drug type, frequency of use and so forth. The information obtained from the internal diseases department of a university hospital was transferred to a computer simulation environment and the current situation and the proposed situation were analyzed separately, and the results were compared. The statistically verified results show that an autonomous AGV that will process patient information and distribute drugs reduced the workload of nurses by 14% in approximately a month.
The ability to handle closed doors and elevators would extend the applicability of Socially Assistive Robots (SAR) enormously. In this paper, we present a new approach which integrates uninstructed persons as helpers to open doors and to call and operate elevators. The current implementation status of these two abilities into a robotic application developed for real-world scenarios together with first experimental results obtained are presented below.
Conference Paper
Full-text available
With the aim of increasing the quality of the meals transportation service inside hospitals and health care centers (HHCC), we are developing a dedicated mobile robot to perform this service, the i-Merc. This robot is equipped with a heating system in the meals compartment which guarantees the meals temperature and prevents bacteriologic proliferation. The i-Merc also integrates a personalized diets information system where information about patients' diets can be introduced and accessed by the service personnel. This project has been developed within the compass of the Master in Engineering Design, at the Technical University of Lisbon. The product development of the robot addressed many knowledge areas, some of which are presented in this paper. We finished the first stage of the project with a service concept, a virtual prototype which included some key specifications and a physical prototype. Presently, we are continuing the product development and searching some stakeholders that would be interested in the project
Conference Paper
The purpose of this paper is to present the devolvement of a fuzzy control applied for a hospitals and health care centres mobile concept robot, the i-MERC. The robot and fuzzy controller models are presented as well as simulation results. The simulation application that was developed included the possibility to change de bending radius of the curves. To analyze the performance of the robot in following curves posing different dynamic demands simulations were performed considering curves with an abrupt change of direction and with 10, 20, 30, 40 and 50 cm of radius. A virtual reality resource allows demonstrating the service concept with the purpose of searching stakeholders interested in the project.
A fuzzy set is a class of objects with a continuum of grades of membership. Such a set is characterized by a membership (characteristic) function which assigns to each object a grade of membership ranging between zero and one. The notions of inclusion, union, intersection, complement, relation, convexity, etc., are extended to such sets, and various properties of these notions in the context of fuzzy sets are established. In particular, a separation theorem for convex fuzzy sets is proved without requiring that the fuzzy sets be disjoint.
Conference Paper
Hospitals face with heavy traffic of goods everyday, where transportation tasks are mainly carried by human. Analysis of the current situation of transportation in a typical hospital showed several transportation tasks are suitable for automation. This paper presents a system, consisting of a fleet of robot vehicles, automatic stations and smart containers for automation of transportation of goods in hospitals. Design of semi-autonomous robot vehicles, containers and stations are presented and the overall system architecture is described. Implementing such a system in an existing hospital showed the need of necessary modifications to the hospital infrastructure.
Conference Paper
This paper presents a tray carrying robot for hospital use. A patient puts his or her personal belongings on trays, and the trays are stored in a separate tray rack located in a corner of a hospital ward. The tray carrying robot goes back and forth between a patient and the tray rack along single or multiple guide lines on the floor or ceiling. The guide line attached to the ceiling of a hospital ward is also proposed.
Conference Paper
The paper presents the design concepts of an intelligent hospital service robot (IHSR). The IHSR aims at saving human resources and also improving the hospital service. The navigation path planning can be concluded by an information decision making system. It is decided from the distribution of people in the hospital. For obstacle avoidance, the IHSR mounts a CCD camera and its attachments to determine the relative directions of obstacles. There are nine ultrasonic sensors installed on the IHSR to detect the distances between the IHSR and obstacles. An integrated fuzzy controller is proposed as the collision-free navigation control system. In which, there are two fuzzy subcontrollers designed for objective navigation and collision-free control respectively. Simulation results show that the IHSR is indeed able to accomplish navigation control in hospital environment.
Conference Paper
Delivery is an essential task for a mobile robot. Automatically guided vehicles play a crucial role in many factories by performing delivery tasks. The next step involves having mobile robots work in populated environments, such as offices, hospitals, and health care facilities. This paper proposes a service robot that can deliver parcels, letters or documents in such an environment. The design policy, architecture, methodology and implementation of this system are presented.
Conference Paper
This paper presents a mobile robot fro routine delivery tasks of medicine, specimen, and medical devices from one station to another in hospitals. This hospital transport robot uses the fluorescent lamps on the ceiling of the corridor as natural landmarks to localize its position and orientation. A simple and efficient algorithm has been developed based on motion continuity and features matching for on-line computation of the position and orientation. A robust method is also presented for the robot to avoid collisions with static obstacles and people moving in the hospital. We have implemented this transport robot in a hospital in Hong Kong. An experimental result was demonstrated to confirm the performance of the localization and navigation algorithms.