VISVESVARAYA TECHNOLOGICAL UNIVERSITY

“JNANA SANGAMA”, BELAGAVI – 590018, KARNATAKA

Technical Seminar REPORT

On
“NextGen WebEase – Powered Online Store with PWA”

Submitted in the fulfillment of the requirement of the award of

Bachelor of Engineering
In
Information Science and Engineering
Submitted By

ANJALI SINGH 1BO20IS004

KRISHNA PRAKASH 1BO20IS013
LALIMA KUMARI 1BO20IS015

Under The Guidance of

Prof. Divyashree H S
Head of Department
Dept. of ISE

DEPARTMENT OF INFORMATION SCIENCE AND ENGINEERING

DWARAKANAGAR, BAGALUR MAIN ROAD, YELAHANKA, BENGALURU-560063,

Affiliated to VTU Belagavi, Approved by AICTE, New Delhi, India
Accredited ‘B++’ level by NAAC
2024-25
 DWARAKANAGAR, BAGALUR MAIN ROAD, YELAHANKA, BENGALURU-63

Department of Information Science and Engineering

CERTIFICATE

This is to certify that the Technical Seminar report entitled “Three-Dimensional Robotic
Arm Control” is a bonafied work carried out by KOUSHIK M R 1BO20IS011, in the
fulfillment for the requirements of Eight Semester, Bachelor of Engineering in Information
Science and Engineering of Visvesvaraya Technological University, Belagavi during the year
2024-25. It is certified that all corrections and suggestions indicated for the internal
assessment have been incorporated in the report. This Technical Seminar report has been
approved as it satisfies the academic requirements in respect to the work prescribed for the
Bachelor of Engineering degree.

…………………………….. ………………………………

Name and Signature of the Guide Name and Signature of the HOD
Prof. Padmavathi R Prof. Divyashree H S
Department of ISE Department of ISE
BrCE, Bengaluru-63 BrCE, Bengaluru-63

Committee Members

Name Signature with Date

1………………………… …………………………..
2………………………… ...…………………………...
 ABSTRACT

Three-Dimensional Robotic Arm Control discusses the development of a brain-computer

interface (BCI) system that utilizes steady-state visual evoked potentials (SSVEPs) to control
a robotic platform. The study introduces a novel method for modulating the velocity of the
robotic arm based on the brightness of visual stimuli. By incorporating Gaussian mixture
model (GMM) and Bayesian inference techniques, the system calculates posterior
probabilities to distinguish between high and low brightness flickers, enabling precise control
of the robotic arm. Experimental results demonstrate the effectiveness of the proposed
method in reducing reaching time and improving target proximity in single- and multi-target
reaching tasks. The study showcases the potential of SSVEP-based BCIs in enhancing robotic
control through innovative velocity modulation strategies.
 ACKNOWLEDGEMENT

The satisfaction and euphoria that accompanies the successful completion of any task
would be incomplete without mentioning the people who made it possible. With deep
gratitude, we acknowledge all those guidance and encouragement, which served as bacon
of light and crowned our efforts with success. I thank each one of them for their valuable
support.

I express our sincere thanks to Dr. B.R. Shetty, Chairman, Brindavan Group of
Institutions, Bangalore, for providing necessary facilities and motivation to carry out
Technical Seminar work successfully.

I convey our sincere thanks to Dr. Shruti Sharma, CEO, Brindavan Group of Institutions
for her support and motivation.

I wish to express our sincere thanks to Dr. Venugopal A R, Director, Brindavan Group of
Institutions for his support and motivation.

I express our sincere thanks to Dr. Bhagappa, Principal, Brindavan College of

Engineering for providing necessary facilities and motivation to carry out Seminar work
successfully.

I would like to sincere thanks to Prof. Divyashree H S, Head of Department, Dept. of ISE,
Brindavan College of Engineering, for the constant encouragement and help to carry out
Seminar work successfully.

I express our heartfelt gratitude and humble thanks to our guide Prof. Padmavathi R,
Assistant Professor, Dept. of ISE, Brindavan College of Engineering, for the constant
encouragement and help to carry out Seminar work successfully.

I would like to mention our special thanks to all the faculty members of Information Science and
Engineering Department, Brindavan College of Engineering for their invaluable support and
guidance. We finally thank our family and friends who have been encouraging us constantly and
inspiring.

KOUSHIK M R 1BO20IS011
 TABLE OF CONTENTS

Sl. No TITLES Page. No

1 ABSTRACT i

2 ACKNOWLEDGEMENT ii

3 TABLE OF CONTENTS iii

4 LIST OF FIGURES iv

Chapter No. CHAPTER NAME Page. No

1 Introduction 1

2 Literature Survey 2
3 System Analysis 4
3.1 Existing System 4
3.2 Proposed System 4
4
System Architecture 5

4.1 Hardware 5
4.2 Software 6
4.3 Module Description 6
5 Applications 8
6 Advantages and Disadvantages 9
7 Conclusion 10
8 References 11
 LIST OF FIGURES

Fig. No FIGURE NAME Page No

2.1 Survey Paper 3

4.1 System Architecture 5
4.2 USB 3.0 5
4.3 D435 Camera 5
4.4 Robot Operating System 6
 CHAPTER 1

INTRODUCTION

Brain-Computer Interface Controlled Robotic Platform with Velocity Modulation highlights

the growing interest in utilizing steady-state visual evoked potentials (SSVEPs) for brain-
computer interface (BCI) applications. SSVEPs offer advantages such as non-invasiveness,
high information transfer rates, and user-friendliness, making them suitable for controlling
external devices like robotic platforms. However, existing SSVEP-based BCIs often lack the
ability to modulate movement velocity, limiting their practical utility in real-world scenarios
where users may require varying speeds.

To address this limitation, the study proposes a novel velocity modulation method based on
stimulus brightness for controlling a robotic arm within an SSVEP-based BCI system. By
manipulating the brightness of visual stimuli, the system can adjust the velocity of the robotic
arm, providing users with more flexibility and control during tasks. The synchronization of
the cursor and robotic arm is achieved without requiring users to switch their attention
between the stimuli and the robot, enhancing the overall user experience and task
performance.

The introduction sets the stage for the research by outlining the motivation behind developing
a velocity modulation strategy for SSVEP-based BCIs and introduces the key objectives and
contributions of the study in advancing the field of brain-computer interfaces for robotic
control. To overcome this limitation, the study introduces a novel approach that leverages
stimulus brightness as a means to modulate the velocity of a robotic arm controlled by an
SSVEP-based BCI system. By adjusting the brightness of visual stimuli, users can influence
the speed at which the robotic arm moves, allowing for more dynamic and adaptive control
during different tasks. This innovative velocity modulation method aims to enhance user
experience, improve task performance, and expand the potential applications of SSVEP-
based BCIs in fields such as rehabilitation, assistive technology, and human-machine
interaction.
CHAPTER 2

LITERATURE REVIEW

Brain-Computer Interface Controlled Robotic Platform with Velocity Modulation"

encompasses a comprehensive analysis of existing research in the field of steady-state visual
evoked potential (SSVEP)-based brain-computer interfaces (BCIs) and robotic control. Key
studies and contributions discussed in the literature review include:

1. Molina-Cantero et al. [T2] utilized SSVEP responses from a single-channel EEG headset
to modulate cursor speed based on attention levels, highlighting the potential for attention-
driven control in BCIs.
2. Studies investigating the influence of stimulus brightness on SSVEP signals [T2] revealed
that SSVEP amplitude increases with higher brightness levels, indicating the importance of
stimulus characteristics in BCI performance.
3. Previous research [T4] has explored velocity control in SSVEP-based BCIs, with
approaches ranging from discrete speed modes mapped to different frequencies to continuous
velocity mapping using correlation values and stimulus frequencies.
4. The literature review emphasizes the need for dynamic velocity modulation in BCI-
controlled robotic systems to enhance user experience, task performance, and applicability in
real-world scenarios.
5. By integrating insights from diverse studies, the literature review underscores the potential
of SSVEP-based BCIs for enabling precise and adaptive control of robotic platforms, with a
focus on innovative velocity modulation strategies based on stimulus brightness.

Overall, the literature review provides a comprehensive overview of the research landscape in
SSVEP-based BCIs and robotic control, highlighting the advancements, challenges, and
opportunities in the field. The synthesis of existing literature sets the stage for the current
study's novel approach to velocity modulation using stimulus brightness, contributing to the
advancement of BCI technology for enhanced robotic control applications.
CHAPTER 3
SYSTEM ANALYSIS

3.1 Existing System

 Experimental Setup: The system comprises a stimulation interface displayed on a

computer screen, featuring flickers, target markers, and a cursor workspace.
 Data Acquisition and Processing: The system incorporates data acquisition, feature
extraction, and a speed function trained offline to determine the velocity of the cursor
or robotic arm during online experiments.
 Experimental Validation: The system undergoes online experiments, including
single- and multi-target reaching tasks, to evaluate the performance of the proposed
velocity modulation method.
 User Participation: Ten healthy subjects participate in the experiments, providing
valuable insights into the usability and performance of the system.

3.2 Proposed System

The system introduces a velocity modulation method based on stimulus brightness, allowing
users to adjust the speed of the robotic arm by manipulating the brightness levels of visual
stimuli. This dynamic velocity control mechanism aims to enhance user experience and task
performance by providing real-time speed adjustments without the need for users to switch
their attention between stimuli and the robot. The proposed system incorporates feature
extraction techniques, including correlation coefficients and power spectral density analysis,
to construct feature vectors from SSVEP signals. These features are utilized in conjunction
with a Gaussian Mixture Model (GMM) and Bayesian inference to calculate posterior
probabilities for velocity determination and control. Future work on the proposed system may
involve integrating augmented reality (AR) glasses to enhance the user experience during
rehabilitation exercises. AR glasses could display visual stimulation, the cursor, and targets
directly in the user's field of view, reducing the need for users to focus on a separate
stimulation interface and potentially alleviating visual fatigue associated with SSVEP-based
BCIs
CHAPTER 4

SYSTEM ARCHITECTURE

Fig 4.1: System Architecture

The system incorporated a GMM model and Bayesian inference to calculate the posterior
probabilities of high- and low-brightness flickers, enabling the design of a speed function
based on the posterior probability difference. The final direction and speed were determined
by incorporating the velocity from the previous moment. To demonstrate the effectiveness
and feasibility of the proposed method, online experiments involving single- and multi-target
reaching tasks were conducted, showcasing the practical application of the system
architecture in real-time scenarios

4.1Hardware
• Intel RealSense D435 camera for capturing RGB-D images.
• Robotic arm with the capability to move into the capture region of the target under
BCI-guided control. Computer with USB 3.0 connectivity for streaming camera.

Figure 4.1: JSX

CHAPTER 5

APPLICATIONS

 The SSVEP-based Brain-Computer Interface (BCI) system in the study utilized a

stimulation interface designed with flickers, targets, and a cursor workspace,
allowing for brain-actuated control of the robotic arm without the need for the
subject's eye switch between stimuli and the robot.
 The proposed method incorporated a brain-actuated speed function based on
stimulus brightness to modulate the velocity of the robotic arm. This method
involved calculating posterior probabilities using Gaussian mixture model (GMM)
and Bayesian inference, with historical velocity considered to determine the final
velocity.
 Experimental results from online tasks, including single- and multi-target reaching
tasks, demonstrated the effectiveness of the proposed velocity modulation method
in reducing reaching time and improving proximity to the target.
 The study used a UR5 robotic arm with a maximum reaching radius of 850 mm for
the experimental tasks, with a designated horizontal workspace area of 803 mm ×
470 mm provided by a whiteboard positioned in front of the robot.
 CHAPTER 6

ADVANTAGES AND DISADVANTAGES

Advantages

1. The proposed stimulus brightness-based velocity modulation method in SSVEP-based

BCI systems offers advantages over traditional methods by reducing reaching time
and achieving proximity to the target.
2. The proposed method results in lower tracking errors compared to the DV control
method, with average values of 0.067 and 0.23 in reaching tasks.
3. Rapid, discrete direction changes in traditional methods can cause discomfort during
reaching tasks, especially for individuals with mobility limitations or during
rehabilitation exercises. The proposed method allows for smooth movements of the
robotic arm, enhancing user experience and participation.
4. By leveraging SSVEP signals and advanced signal processing techniques, the system
empowers users to control the robotic arm with precision and accuracy. The feature
extraction and velocity modulation model enable users to translate their intentions
into robotic arm movements effectively, enhancing user control and satisfaction.

Disadvantages

1. Tracking Errors: The DV control method produced larger tracking errors in reaching
tasks compared to the proposed method, affecting smooth movements and causing
discomfort, especially for individuals with mobility limitations or during
rehabilitation exercises
2. Time Inefficiency: The DV method may take longer to reach targets due to fixed
speeds and potential misclassifications, necessitating extra correction time and
potentially extending task durations
 CHAPTER 7

CONCLUSION

The system's advantages include dynamic velocity control, improved task performance, seamless
user experience, potential for augmented reality integration, and opportunities for hybrid BCI
approaches. These strengths highlight the system's potential to empower users with precise
and flexible control over robotic arm movements, offering benefits in assistive and
rehabilitative applications.

However, the system also exhibits limitations such as complexity in signal processing, user
training requirements, dependency on EEG equipment, potential for visual fatigue, hardware
compatibility constraints, and challenges related to generalizability. Addressing these
limitations through user training, optimization strategies, and usability testing could enhance
the system's usability, robustness, and acceptance in real-world scenarios.
CHAPTER 8

REFERENCES

[1] N. Cheng et al., “Brain–computer interface-based soft robotic glove rehabilitation for
stroke,” IEEE Trans. Biomed. Eng., vol. 67, no. 12, pp. 3339–3351, Dec. 2020.
[2] Kumar, L. Gao, E. Pirogova, and Q. Fang, “A review of error-related potential-based
brain–computer interfaces for motor impaired people,” IEEE Access, vol. 7, pp.
142451–142466, 2019
[3] Kapsalyamov, P. K. Jamwal, S. Hussain, and M. H. Ghayesh, “State of the art lower
limb robotic exoskeletons for elderly assistance,” IEEE Access, vol. 7, pp. 95075–
95086, 2019.
[4] Y. Zhang, S. Q. Xie, C. Shi, J. Li, and Z.-Q. Zhang, “Cross-subject transfer learning
for boosting recognition performance in SSVEP-based BCIs,” IEEE Trans. Neural
Syst. Rehabil. Eng., vol. 31, pp. 1574–1583, 2023.