International Journal of Reconfigurable and Embedded Systems (IJRES)

Vol. 14, No. 1, March 2025, pp. 100~108

ISSN: 2089-4864, DOI: 10.11591/ijres.v14.i1.pp100-108  100

Performance comparison of indoor navigation and obstacle

avoidance methods for low-cost implementation in wheelchairs

Satish Bhogannahalli Ashwathnarayan, Deekshitha Arsa, Sharath Kumar Yerriyuru Narasimhaiah,

Shreyas Anchan, Giri Prasath
Department of Electrical and Electronics Engineering, Dayananda Sagar College of Engineering, Bangalore, India

Article Info ABSTRACT

Article history: Wheelchairs are a huge support for the movement of people who have
disabilities. The wheelchairs that were traditionally moved using manual
Received Aug 20, 2024 effort have given way to powered and smart wheelchairs with various
Revised Oct 10, 2024 controlling methods. When powered wheelchairs are used indoors,
Accepted Oct 18, 2024 navigation and avoiding obstacles become challenging and tricky for a
disabled user. To address these challenges there have been implementations
of expensive and high-end systems to make the wheelchair move
Keywords: autonomously but as a result such a wheelchair is not economically viable
for many users. Thus, there is a need for an alternative low cost method for
Autonomous users to be able to navigate and move in an indoor environment. The paper
Economical reviews low-cost methods for implementing indoor navigation systems,
Embedded systems weighing their performances to validate if these methods can be used as a
Navigation viable alternative to the high-cost systems for autonomous navigation in an
Robotics indoor environment.
Wheelchair
This is an open access article under the CC BY-SA license.

Corresponding Author:
Satish Bhogannahalli Ashwathnarayan
Department of Electrical and Electronics Engineering, Dayananda Sagar College of Engineering
Bangalore, Karnataka, India
Email: [email protected]

1. INTRODUCTION
Wheelchairs have been used by the physically challenged for movement for many years. The simple
manually operated wheelchairs have in recent years given way to powered wheelchairs, with various modes
of control. These powered wheelchairs though make the movement simpler for the user, and also come with
the difficulty of navigating and avoiding obstacles, especially in crowded environments. Powered
wheelchairs have been under constant research and development with various methods being tested to
achieve better navigation, control, and ease of use. Research by Bastos-Filho et al. [1] discuss the automation
of wheelchair navigation using complete automation or supervised automation to allow users with different
levels of disabilities to use the wheelchair. Research by Arnay et al. [2] describe the use of laser combined
with video camera for detection of obstacles in front of wheelchairs in indoor as well as outdoor
environments to ensure easy movement of the wheelchair in different environments. Research by Sanders [3]
describes the control of a wheelchair using a joystick, by the user or using sensory inputs, allowing the user
to have complete control over the wheelchair based on the surrounding environment in which the wheelchair
is being driven. Research by Masud et al. [4] present a vision-based control of a wheelchair, allowing the
users to have complete control of the movement of the wheelchair using their eyes. This allows users even
with multiple disabilities to be able to control the wheelchair independently with no assistance from anyone.
Research by Carlson and Demiris [5] present a way to assist the users with the help of collaborative control
mechanisms. The system predicts the intentions of the user and adjusts the control signals based on the

Journal homepage: http://ijres.iaescore.com

Int J Reconfigurable & Embedded Syst ISSN: 2089-4864  101

requirements. Research by Lei et al. [6] present an intention prediction-based point-to-point navigation
system with control assistance to the users as needed. The system helps users navigate even in complex
environments and provides ease of navigation and obstacle avoidance. Research by Tawil and Hafez [7]
presents a deep learning based approach to avoid obstacles and help in the navigation of the wheelchair using
a single camera and imaging technique. The papers [8], [9] present a machine learning based technique using
computer vision to help wheelchair users navigate autonomously in various environments. Adámek et al. [10]
discuss e vector field histogram+(VFH+) and dynamic window approach (DWA) algorithms to enhance the
obstacle avoidance and navigation of a smart wheelchair. Research by Kawaguchi et al. [11] present a fuzzy-
based predictive model for controlling a wheelchair in crowded environments allowing obstacle avoidance
based on the prediction of behavior and other factors. In [12]-[20] authors describe various techniques, voice
control, IoT, hand movements, movement of the head, blink-of-an-eye use of artificial intelligence, and other
modes to control the movement of a wheelchair for easy navigation.
Candiotti et al. [21] discussed the advantages and challenges of a powered wheelchair for indoor
and outdoor navigation, concluding that a semi-autonomous system with a good user interface is more
beneficial for users. Research by Uganya et al. [22] implement a machine learning-based algorithm
optimized using a stochastic gradient descent algorithm to achieve better autonomous indoor navigation.
Research by Mascetti et al. [23] present the idea of smart wheels to identify the various features that
wheelchair users need to navigate through in an urban landscape. The smart wheels were proposed to make
the process easier for the users with automatic identification with no inputs required from the user. Research
by Sivakanthan et al. [24] have done a detailed review of how robotic wheelchairs have developed over the
years, and even though there have been many technological advances in the robotic wheelchairs, many of the
advances have not reached the market successfully yet.
Research by Bandara at al. [25] discuss the need for wheelchairs to employ a hybrid navigation
system where the user and the wheelchair both have control over the system and navigation is decided based
on the scenarios and the inputs received. Hisham at al. [26] discussed a customized indoor navigation system
for wheelchairs using 3D mapping of the location. Research by Lakmal et al. [27] discuss the implementation
of a Lidar and 2D mapping based implementation of indoor navigation for wheelchairs.
Afonso and Ferreira [28] discussed the implementation of autonomous navigation in wheelchairs
using deep learning and reinforcement along with the help of computer vision. Kobayashi et al. [29] discuss
the implementation of a navigation system based on various factors to identify the shortest path to a desired
destination using Dijkstra’s algorithm. The proposed method uses a digital twin to develop the path and
achieve the desired navigation. Mohamed et al. [30] developed an assistive navigation system for visually
impaired wheelchair users using deep learning algorithms providing users with information about their
environment and the path to be taken to reach the destination. The various implementations discussed fully
autonomous wheelchairs employ technologies which make them economically expensive for an average user
to buy and maintain. The paper attempts to compare two low cost options which can be employed to achieve
autonomous navigation with obstacle detection and avoidance in an indoor environment also bringing out the
advantages and challenges in the same.

2. PROPOSED SOLUTION
Wheelchairs, when used for indoor navigation, have to be very precise in identifying the objects
around it as an indoor setup might have multiple obstacles at closer distances. Two of the main functions that
the wheelchair used for indoor navigation should be able to perform are automatic detection of obstacles,
taking the necessary action as required and the second being able to reach a destination as requested by the
user. The obstacle avoidance and the navigation systems need to work in sync with each other to ensure
effective and proper movement of the wheelchair.

2.1. Obstacles detection

Using infra red (IR) and ultrasonic sensors: IR sensors have the ability to detect the presence of
objects in front of it using the reflection of the IR waves emitted by its transmitter. These sensors are low cost
and are effective in identifying the presence of objects in front of them at close distances. Four such sensors
were placed on the wheelchair, two on the handles and two near the wheels, to be able to detect the presence
of any obstacle in the path of the wheelchair. The signals from each of these sensors was monitored by the
controlling unit continuously to be able to detect the presence of any obstacle in the path on which the
wheelchair was moving. The drawback of using only IR sensors was that these sensors could not give the
distance at which the obstacle was present. Figure 1 shows the block diagram of integration of the IR sensor
with the wheelchair.

Performance Comparison of indoor navigation and obstacle … (Satish Bhogannahalli Ashwathnarayan)

102  ISSN: 2089-4864

Figure 1. IR sensor and wheelchair

To be able to identify the distance of the obstacle from the wheelchair ultrasonic sensors were also
added to the wheelchair. The ultrasonic sensors work by calculating the time taken for the ultrasonic waves to
travel from the wheelchair to the obstacle and bounce back. Calculating the distance of the obstacle from the
wheelchair allows the system to take appropriate action to ensure that the wheelchair does not collide with
the obstacle. Two ultrasonic sensors were installed on the wheelchair, one in the upper portion and one in the
lower portion of the wheelchair to be able to detect obstacles of all heights. Figure 2 gives a block diagram of
the interaction between the wheelchair and the ultrasonic sensor.

Figure 2. Ultrasound sensor and wheelchair

The combination of IR and ultrasonic sensors were capable of not only detecting the presence of
obstacles in time but also provide the distance of the obstacle so that the system can take the necessary action
in time to avoid the obstacle. Image-based method: the second method attempted was using a camera to take
photos of the objects in front of the wheelchair and use the image to calculate the distance. The image by
itself was capable of detecting the object’s presence and its distance of the object from the wheelchair. The
object detection and distance calculation were done using a YOLOv4 algorithm. The algorithm works by
using pre-trained images to identify the object. The dimension of the object also would be fed as part of the
training. The algorithm is capable of identifying the object and its distance from the camera from the pre
trained data. As the method is being proposed for indoor navigation the training of the objects and its
dimensions would be required only once and can be done during the first installation after which the
wheelchair can work autonomously using the camera to detect the images as well as calculate the distance of
the object. Figure 3 gives the block diagram of the interaction between camera and the wheelchair.

Figure 3. Camera based sensing

2.2. Navigation
Navigating to a desired location within the indoor space is also a major challenge for people using
wheelchairs. The paper compares navigation using two simple low cost methods, one using IR sensors and
second using images taken with a camera. Using IR sensors on wheels: to ensure the wheelchair can move
from one location to another autonomously a distance based algorithm was used. The distances between

Int J Reconfigurable & Embedded Syst, Vol. 14, No. 1, March 2025: 100-108
Int J Reconfigurable & Embedded Syst ISSN: 2089-4864  103

locations are fixed in an indoor environment, for example distance between rooms will always be the same.
Thus these fixed distances were fed as information into the system which would be used while navigating.
Calculation of distance traversed by the wheelchair was done using an IR sensor installed on the wheels
which would count the rotations of the wheel and in turn calculate the distance traveled. The starting point
would be fixed as the entrance of the room, which the user can move to, using simple commands to move
forward or backward. The fixed wheel diameter and fixed distances between locations in a home ensured that
the calculation of distance was easy to compute and compare.
Using camera: the cameras used for detection of obstacles were also used for the navigation of the
wheelchair. The path of the wheelchair from one location to another was mapped using known images or
markers placed at proper places for the camera to identify. The turns of the wheelchair were configured based
on the distance from these marked images. Once the path is identified and configured, the wheelchair would
be trained to follow the path by looking for the images. The turns would be configured based on the distance
from these set images. The camera would identify the image, and calculate the distance from the image using
the YOLOv4 algorithm. The wheelchair would be made to turn at the appropriate distance from the image as
trained, allowing the user to reach the desired location.

3. METHOD
Figure 4 gives a general flow of events adopted by the algorithm controlling the movement of the
wheelchair. The system waits for the user to enter a command which could be the name of a destination
location or a direction of movement. The command for movement can be issued using either voice, keypad or
gestures. Once the system identifies the command the movement of the wheelchair begins. If the command is
to move in a certain direction the wheelchair will continue to move till the user issues a stop command or an
obstacle is encountered. If the command is to a specific destination, which is mapped already in the system,
the wheelchair fetches the details of the movement required and will move in the corresponding directions
unless it encounters an obstacle causing it to stop or move to avoid the obstacle.

Figure 4. Movement of the wheelchair

Performance Comparison of indoor navigation and obstacle … (Satish Bhogannahalli Ashwathnarayan)

104  ISSN: 2089-4864

The main difference between the two proposed methods are the system comprising the way of
navigation to the destination and the obstacle detection systems. One system uses the IR and ultrasonic
sensors for obstacle detection and the distance calculation using IR sensor for navigation. The second system
uses a camera to achieve both obstacle detection and navigation.
In both the methods employed a predefined map of the indoor locations was fed using available
data. In the case of the IR based navigation the distance to be covered and the distance of each turn during the
navigation was stored in the system. Where as in the image based navigation the turns to be executed was
identified distance from fixed images or markers placed in the indoor environment.
Figure 5 details the steps followed in an IR sensor based distance calculation setup. The control unit
will receive the distance measured and then take the necessary action based on the command received from
the user. Figure 6 details the steps followed by the image based system while calculating the distance of the
object and updating the same to the control unit. Both the methods were implemented and tested on a wheel
chair to demonstrate the ease of use and effectiveness of the approaches. Figure 7 is the image of the
wheelchair on which the above mentioned algorithms were tested. Figure 8 shows a sample output of
detection of the distance of a person from the wheelchair.

Figure 5. IR sensor based navigation

Figure 6. Image based navigation

Int J Reconfigurable & Embedded Syst, Vol. 14, No. 1, March 2025: 100-108
Int J Reconfigurable & Embedded Syst ISSN: 2089-4864  105

Figure 7. Wheelchair model Figure 8. Distance and identification using camera

4. RESULTS AND DISCUSSION

The results below show the performance of the two algorithms on a real time wheelchair
considering various scenations. Table 1 provides the results of performance in detected obstacles at certain
distances. For distances greater than 0.5 m, both the methods proved not very effective but it would generally
be acceptable in the case of indoor navigation as in an indoor setup 0.5 m is a large distance. In the range 0.5
m to 0.4 m the ultrasonic was able to detect and provide the distance but the level of accuracy obtained for
this range was not very satisfactory, but the camera performed much better in this range compared to the
ultrasonic systems. In the range of 0.4 m to 0.2 m the ultrasonic based system was very effective and accurate
in providing the distance of the obstacle with an accuracy of 95%, the camera based system was also equally
effective with 93% efficiency. In the range of 0.2 m-0.1 m, which is the general range of interest in the case
of indoor navigation the accuracy of both the systems was very good and found to be above 95%. Thus, we
can see that the camera based as well as the ultrasonic based systems both are effective tools for indoor
obstacle detection, especially in close ranges.

Table 1. Distance based performance

Distance of obstacle (m) Ultrasonic sensor Camera
More than 0.5 Unable to detect Very low accuracy
0.5-0.4 Low accuracy Moderately accurate
0.4-0.2 95% accuracy 93% accuracy
0.2-0.1 98% accuracy 95% accuracy

During the movement of the wheelchair, it's not only detection of the obstacles, but avoiding them is
also very important. Table 2 provides the results obtained with respect to the obstacle avoidance in each of
the systems. As the number of obstacles reduced both the systems were effective in identifying and avoiding
obstacles. The camera based system was less accurate with a larger number of obstacles. One of the reasons
for the lower efficiency in a higher number of obstacles is that the processing time of the camera based
system is higher than the ultrasonic system. Thus, the obstacle was not avoided due to delayed response from
the detection system. Though this can be addressed with a faster processing power controller at the expense
of higher cost of the system. Navigation: the navigation to the desired destination as commanded by the user
is another factor that needs to be ensured for the wheelchair to be effective.

Table 2. Performance based on number of obstacles

Number of obstacles Obstacles avoided with ultrasonic Obstacles avoided with camera
10 9 8
6 5 5
4 4 4
2 2 2

Performance Comparison of indoor navigation and obstacle … (Satish Bhogannahalli Ashwathnarayan)

106  ISSN: 2089-4864

The Table 3 gives the comparison of how the two systems performed with respect to the navigation.
For longer distances, greater than 10 m the IR based system seemed to reach only about 8.5 m to 9 m the loss
in the distance was attributed to the lack of accuracy of the sensing as well as due to minor deviations due to
obstacles. The camera based system performed slightly better here reaching around 9 m while traveling to a
destination of 10 m. As the distances of the destination reduced the performances of both the systems
improved, with both of them achieving more than 95% accuracy for less than 2.5 m traversal. The navigation
of above 10 m in a domestic indoor setup may not be a very common occurrence and hence the errors can be
accommodated. The shorter distances are important for indoor navigation and that is being successfully
navigated by both the systems to a high degree of accuracy.

Table 3. Performance on distance of navigation

Distance to be navigated (m) Navigation accuracy with IR (%) Navigation accuracy with camera (%)
Greater than 10 85 90
5-10 92 94
2.5-5 95 95
2.5-1.5 98 97

Table 4 compares the two methods proposed under various parameters. The IR and ultrasonic based
system and the camera based system both are capable of identifying the obstacles as well as navigating based
on distances. The major advantage of the camera based system is the ability to identify the obstacle and
inform the user which the IR and ultrasonic based system is not capable of. But the camera based system has
the drawback of being slower and requires more processing power as compared to the IR and ultrasonic
based system.

Table 4. Comparison between the methods proposed

Description IR ultrasonic based Camera based
Obstacle detection Possible Possible
Identify object Not supported Supported
Speed of response Faster Slower
Processing required Lesser More

5. CONCLUSION
The results obtained indicate that wheelchair automation implemented using a combination of IR
and ultrasonic or camera based sensors are both effective in practical scenarios. These variations are a lot
more economical as compared to the more complex implementations based on technologies like lidar, radar,
and machine learning, which are effective but make the wheelchair not affordable to many users. The work in
the paper depicted that wheelchair automation for indoor navigation can be achieved using the low cost
alternatives and be effective too. The IR and ultrasonic based system is more suitable where the user is not
visually impaired making the requirement of obstacle identification unnecessary, but if the wheelchair is
being used by a visually impaired individual then the feature of identification of the obstacle becomes very
important, even at the the slight expense of slower movement.
These low cost alternatives might not be very effective in an outdoor environment as they rely on
predefined maps and images fed into the system and operate based on these maps. But the independence
offered to the user in the case of indoor navigation would be very helpful in ensuring that the disabled is able
to self navigate and move around without the need for assistance from any helpers. The implementation can
be further improved with the algorithms to be made dynamic in nature allowing them to adapt to a changing
environment even in the indoor environment. This will make the usage of the wheelchair for the user hassle
free and more efficient.

REFERENCES
[1] T. F. Bastos-Filho et al., "Towards a new modality-independent interface for a robotic wheelchair," IEEE Transactions on Neural
Systems and Rehabilitation Engineering, vol. 22, no. 3, pp. 567-584, 2013, doi: 10.1109/TNSRE.2013.2265237.
[2] R. Arnay, J. Hernández-Aceituno, J. Toledo, and L. Acosta, "Laser and optical flow fusion for a non-intrusive obstacle detection
system on an intelligent wheelchair," IEEE Sensors Journal, vol. 18, no. 9, pp. 3799-3805, 2018, doi:
10.1109/JSEN.2018.2815566.

Int J Reconfigurable & Embedded Syst, Vol. 14, No. 1, March 2025: 100-108
Int J Reconfigurable & Embedded Syst ISSN: 2089-4864  107

[3] D. A. Sanders, "Using self-reliance factors to decide how to share control between human powered wheelchair drivers and
ultrasonic sensors," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 25, no. 8, pp. 1221-1229, 2016,
doi: 10.1109/TNSRE.2016.2620988.
[4] U. Masud, N. Almolhis, A. Alhazmi, J. Ramakrishnan, F. U. Islam, and A. R. Farooqi, "Smart wheelchair controlled through a
vision-based autonomous system," IEEE Access, pp. 65099—65116, 2024, doi: 10.1109/ACCESS.2024.3395656.
[5] T. Carlson and Y. Demiris, "Collaborative control for a robotic wheelchair: evaluation of performance, attention, and workload,"
IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 42, no. 3, pp. 876-888, 2012, doi:
10.1109/TSMCB.2011.2181833.
[6] Z. Lei, B. Y. Tan, N. P. Garg, L. Li, A. Sidarta, and W. T. Ang, "An intention prediction based shared control system for point-to-
point navigation of a robotic wheelchair," IEEE Robotics and Automation Letters, vol. 7, no. 4, pp. 8893-8900, 2022, doi:
10.1109/LRA.2022.3189151.
[7] Y. Tawil and A. H. A. Hafez, "Deep learning obstacle detection and avoidance for powered wheelchair," in 2022 Innovations in
Intelligent Systems and Applications Conference (ASYU), 2022, pp. 1-6, doi: 10.1109/ASYU56188.2022.9925493.
[8] N. Farheen, G. G. Jaman, and M. P. Schoen, "Object detection and navigation strategy for obstacle avoidance applied to
autonomous wheelchair driving," in 2022 Intermountain Engineering, Technology and Computing (IETC), 2022, pp. 1-5, doi:
10.1109/IETC54973.2022.9796979.
[9] P. Patthanajitsilp and P. Chongstitvatana, "Obstacles detection for electric wheelchair with computer vision," in 2022 14th
International Conference on Knowledge and Smart Technology (KST), 2022, pp. 97-101, doi: 10.1109/KST53302.2022.9729083.
[10] R. Adámek, M. K. Bugeja, S. G. Fabri, and R. Grepl, "Enhancing the obstacle avoidance capabilities of a smart wheelchair," in
2022 20th International Conference on Mechatronics - Mechatronika (ME), 2022, pp. 1-7, doi: 10.1109/ME54704.2022.9983446.
[11] E. Kawaguchi, K. Sekiguchi, and K. Nonaka, "Self-driving electric wheelchair in crowded environments using a fuzzy potential
model predictive control," IFAC-PapersOnLine, vol. 56, no. 2, pp. 11827-11833, 2023, doi: 10.1016/j.ifacol.2023.10.582.
[12] I. Miftahussalam, E. S. Julian, K. Prawiroredjo, and E. Djuana, "Wheelchair control system with hand movement using
accelerometer sensor," Microelectronic Engineering, vol. 278, p. 112018, 2023, doi: 10.1016/j.mee.2023.112018.
[13] P. Mishra and S. Shrivastava, "IoT based automated wheelchair for physically challenged," Materials Today: Proceedings, vol.
56, part. 1, pp. 533-541, 2022, doi: 10.1016/j.matpr.2022.02.183.
[14] D. Kumar, R. Malhotra, and S. R. Sharma, "Design and construction of a smart wheelchair," Procedia Computer Science, vol.
172, pp. 302-307, 2020, doi: 10.1016/j.procs.2020.05.048.
[15] M. M. Abdulghani, W. L. Walters, and K. H. Abed, "Autonomous voice recognition wheelchair control system," in 2022
International Conference on Computational Science and Computational Intelligence (CSCI), 2022, pp. 226-230, doi:
10.1109/CSCI58124.2022.00043.
[16] Z. Wang, J. Xu, J. Zhang, R. Slavin, and D. Zhu, "An intelligent assistive driving solution based on smartphone for power
wheelchair mobility," Journal of Systems Architecture, vol. 149, p. 103105, 2024, doi: 10.1016/j.sysarc.2024.103105.
[17] A. Triwibowo, M. A. Riyadi, and I. Setiawan, "Wheelchair navigation based on head movements for quadriplegia patients," in
2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON),
2023, pp. 723-727.
[18] C. V. Chowdary, M. M. Rao, S. Radhika and V. Meenakshi, "Enhanced electrical wheel chair based on eye blinking control,"
2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI), Chennai, India,
2023, pp. 1-7, doi: 10.1109/ACCAI58221.2023.10200771.
[19] A. Kumar, M. Singh, M. Singh, J. Ramprabu, A. Dubey, and S. Mujoo, "A novel electronic wheelchair design using artificial
intelligence assisted smart sensors and controller," in 2024 5th International Conference on Intelligent Communication
Technologies and Virtual Mobile Networks (ICICV), 2024, pp. 274-281, doi: 10.1109/ICICV62344.2024.00048.
[20] Z. Alibhai, T. Burreson, M. Stiller, I. Ahmad, M. Huber, and A. Clark, "A human-computer interface for smart wheelchair control
using forearm EMG signals," 2020 3rd International Conference on Data Intelligence and Security (ICDIS), South Padre Island,
TX, USA, 2020, pp. 34-39, doi: 10.1109/ICDIS50059.2020.00011.
[21] J. L. Candiotti et al., "Usability evaluation of a novel robotic power wheelchair for indoor and outdoor navigation," Archives of
Physical Medicine and Rehabilitation, vol. 100, no. 4, pp. 627-637, 2019, doi: 10.1016/j.apmr.2018.07.432.
[22] G. Uganya, I. Bremnavas, K. V. Prashanth, M. Rajkumar, R. V. S. Lalitha, and C. Singh, "Empowering autonomous indoor
navigation with informed machine learning techniques," Computers and Electrical Engineering, vol. 111, p. 108918, 2023, doi:
10.1016/j.compeleceng.2023.108918.
[23] S. Mascetti, G. Civitarese, O. El Malak, and C. Bettini, "SmartWheels: detecting urban features for wheelchair users’ navigation,"
Pervasive and Mobile Computing, vol. 62, p. 101115, 2020, doi: 10.1016/j.pmcj.2020.101115.
[24] S. Sivakanthan et al., "Mini-review: robotic wheelchair taxonomy and readiness," Neuroscience Letters, vol. 772, p. 136482,
2022, doi: 10.1016/j.neulet.2022.136482.
[25] H. M. R. T. Bandara, K. S. Priyanayana, D. P. Chandima, and A. G. B. P. Jayasekara, "Hybrid navigation decision control
mechanism for intelligent wheelchair," IEEE Access, vol. 11, pp. 118558—118576, 2023, doi: 10.1109/ACCESS.2023.3318477.
[26] N. N. N. Hisham, N. A. C. Mustapha, and A. M. Ibrahim, "Indoor navigation and mapping for wheelchair people in KOE," in
2023 9th International Conference on Computer and Communication Engineering (ICCCE), 2023, pp. 150-154, doi:
10.1109/ICCCE58854.2023.10246083.
[27] I. T. Lakmal, K. L. A. N. Perera, H. A. H. Y. Sarathchandra, and C. Premachandra, "SLAM-based autonomous indoor navigation
system for electric wheelchairs," in 2020 International Conference on Image Processing and Robotics (ICIP), 2020, pp. 1-6, doi:
10.1109/ICIP48927.2020.9367336.
[28] P. D. Afonso and P. R. Ferreira, "Autonomous navigation of wheelchairs in indoor environments using deep reinforcement
learning and computer vision," in 2023 Latin American Robotics Symposium (LARS), 2023 Brazilian Symposium on Robotics
(SBR), and 2023 Workshop on Robotics in Education (WRE), 2023, pp. 260-265, doi:
10.1109/LARS/SBR/WRE59448.2023.10332918.
[29] T. Kobayashi, Y. Onimaru, K. Fukae, T. Imai, K. Arai, E. Nakazawa, and T. Suzuki, "Personal and intuitive indoor navigation
system based on digital twin," in 2021 IEEE 11th International Conference on Consumer Electronics (ICCE-Berlin), 2021, pp. 1-
6, doi: 10.1109/ICCE-Berlin53567.2021.9720024.
[30] E. Mohamed, K. Sirlantzis, and G. Howells, "Real-time powered wheelchair assistive navigation system based on intelligent
semantic segmentation for visually impaired users," in 2022 IEEE 5th International Conference on Image Processing
Applications and Systems (IPAS), 2022, pp. 1-6, doi: 10.1109/IPAS55744.2022.10053051.

Performance Comparison of indoor navigation and obstacle … (Satish Bhogannahalli Ashwathnarayan)

108  ISSN: 2089-4864

BIOGRAPHIES OF AUTHORS

Satish Bhogannahalli Ashwathnarayan received B.E. degree in electrical and

electronics engineering from the University Bangalore, India, the M.S. degree in embedded
systems computing from the Manipal University, India. He is currently Assistant Professor
with the Department of Electrical and Electronics Engineering, Dayananda Sagar College of
Engineering, VTU. His research interests include smart grids, embedded systems, and
renewable energy. He can be contacted at email: [email protected].

Deekshitha Arsa completed my B.E. in electrical and electronics engineering, St

Josephs Engineering College, Mangalore in 2007. Completed my M.Tech. in microelectronics
and control systems in Dayananda Sagar College of Engineering, in 2019. Currently pursuing
Ph.D. in DSU in deep learning and video processing. Presently working as an Assistant
Professor in the Department of Electrical and Electronics Engineering, Dayananda Sagar
College of Engineering from October 2019. Area of interest are image processing, machine
learning, signal processing, and programming. She can be contacted at email: deekshitha-
[email protected].

Dr. Sharath Kumar Yerriyuru Narasimhaiah works as an Assistant Professor

in the Department of Electrical and Electronics Engineering at Dayananda Sagar College of
Engineering. He has 16 years of teaching experience. His earned B.E. degree in electronics and
instrumentation technology and his M.Tech. in industrial electronics from Sri
Jayachamarajendra College of Engineering, Mysuru. He holds a Ph.D. degree from
Visvesvaraya Technological University, Belagavi, Karnataka. He has published 11 research
papers in refereed international journals and conferences. His areas of research include
embedded systems and VLSI digital circuit testing. He is an active member of ISTE. He can be
contacted at email: [email protected].

Mr. Shreyas Anchan is currently a final year student in Dayananda Sagar College
of Engineering, pursuing his engineering in electrical and electronics. He is passionate about
robotics and has executed several projects under the domain. He is the IEEE PES student vice
chair for the DSCE SBC in the year 2024. He can be contacted at email:
[email protected].

Mr. Giri Prasath is currently a final year student in Dayananda Sagar College of
Engineering, pursuing his engineering in electrical and electronics. He is an electronics
enthusiast with a wide variety of projects in the field. He is the IEEE PES student secretary for
the DSCE SBC in the year 2024. He can be contacted at email: [email protected].

Int J Reconfigurable & Embedded Syst, Vol. 14, No. 1, March 2025: 100-108