Synopsis of Minor Project - I (ETMN601)
Minor Project Title: - Design and Development of a Cloud-Connected AI-
Driven Multi-Mission Unmanned Ground Vehicle for Modern Defense
Applications
Name of Student: Shree Ranjan N
Enrolment No.: A177158825006
Program: MTech. (Defence Technology) Year/Semester: 1st/ 1st
Introduction
Unmanned Ground Vehicles (UGVs) have become increasingly vital in modern military operations, serving
as force multipliers that enhance operational efficiency, reduce soldier risk, and extend battlefield
capabilities. These robotic platforms are designed to perform a variety of tasks ranging from reconnaissance
and surveillance to logistics support, explosive ordnance disposal, and direct combat engagement. However,
despite their growing deployment, current UGV platforms face significant challenges that limit their
effectiveness. These challenges include limited autonomous decision-making capabilities, vulnerability to
electronic warfare and GPS denial, reduced operational reliability with frequent maintenance needs, and
restricted capability for multi-mission adaptability.
Furthermore, conventional UGV systems typically rely heavily on human operators for navigation and
tactical decisions, which increases manpower requirements and communication dependencies that are
susceptible to jamming or interception. Many existing platforms also suffer from limited situational
awareness due to incomplete sensor integration and inadequate coordination among multiple units, restricting
their ability to operate efficiently in complex or contested environments.
This project proposes the design and development of an Advanced Multi-Mission Unmanned Ground Vehicle
(AM-UGV) that overcomes these limitations by integrating cutting-edge artificial intelligence, hybrid GPS
and SLAM navigation, multi-sensor fusion, and adaptive robotic manipulators. Crucially, the AM-UGV will
utilize a secure, cloud-based command and control infrastructure enabling real-time, bidirectional data
exchange. This approach enhances autonomy, situational awareness, multi-vehicle coordination, and
battlefield support while dramatically reducing operator workload and increasing mission success rates.
By addressing the critical operational and technical gaps found in current UGVs, this research aims to deliver
a highly reliable, multi-functional defense platform capable of performing diverse missions autonomously
and cooperatively within a networked defense ecosystem. The development of such a system will
significantly advance military robotics and enhance national security posture in evolving modern warfare
scenarios.
Aim and objective of minor project
• To develop an autonomous navigation system combining GPS and SLAM for robust operation in
GPS-denied and contested environments.
• To implement AI-driven decision-making algorithms for real-time threat detection, target
identification, and autonomous mission planning.
• To enhance soldier support through automated ammunition delivery, medical assistance, and
casualty evacuation capabilities.
• To design adaptive robotic arms capable of handling weapons, neutralizing bombs, and providing
casualty assistance.
• To establish secure cloud-based command and control infrastructure for real-time bidirectional
communication and coordination among multiple UGVs and operators and to validate system
performance through simulation, prototyping, and testing for reliability, operational endurance, and
multi-mission adaptability exceeding existing UGV platforms.
Methodology to be adopted
• Literature Review: Conduct an extensive study of existing UGV platforms, autonomy algorithms,
sensor technologies, and cloud communication systems to identify current limitations and gaps.
• System Design: Develop detailed architectural designs for the UGV platform, including hybrid
GPS-SLAM navigation, AI-based decision engine, multi-sensor integration, robotic manipulators,
and secure cloud infrastructure.
• Hardware Selection and Prototyping: Select appropriate mechanical components, sensors,
computing units, and communication devices to build a prototype UGV system.
• Software Development: Implement AI and machine learning algorithms for autonomous navigation,
threat detection, and tactical decision-making; develop cloud-based command and control software
with real-time data exchange capabilities.
• Integration: Combine hardware and software components, ensuring seamless communication
between UGV subsystems and the cloud network.
• Simulation and Testing: Use simulation tools (e.g., ROS, Gazebo) to validate autonomous
navigation, sensor fusion, and multi-vehicle coordination; conduct field trials in controlled
environments for performance evaluation.
• Performance Evaluation: Assess key metrics such as reliability, operational endurance, threat
detection accuracy, latency, and operator workload reduction; compare with existing UGV
standards.
• Iteration and Optimization: Refine system design and algorithms based on testing feedback to
enhance capability, robustness, and security.
• Documentation and Reporting: Compile research findings, development processes, experimental
results, and conclusions for academic submission and defense collaborations.
Hardware and Software requirement
1. Hardware Requirements
• NVIDIA Jetson Orin Nano or NVIDIA Jetson Xavier NX development kit
• Raspberry Pi 4B (8 GB) for sensor interfacing and backup processing
• Custom small-scale tracked chassis (aluminum frame)
• 2× medium-torque DC motors with encoders
• 4× standard servo motors for camera pan/tilt and simple manipulator joints
• 24 V lithium-ion battery pack (10 Ah)
• 2× motor drivers/ESCs compatible with chosen motors
• 360° 2D LiDAR sensor (e.g. RPLIDAR A2)
• 2× RGB-D cameras (e.g. Intel RealSense D435)
• 1× mmWave short-range radar module
• 1× 9-axis IMU with basic GPS module
• 4× ultrasonic proximity sensors
• 1× simple 4-DOF robotic arm kit with gripper
• 2× force/torque sensor modules
• 1× Wi-Fi 5 (802.11ac) module with mesh-network support
• 1× high-gain Wi-Fi antenna
• 1× USB-LTE modem for cellular fallback communication
2. Software Requirements
• Ubuntu 20.04 LTS
• ROS Noetic
• Gazebo simulator
• OpenCV
• PCL (Point Cloud Library)
• TensorFlow Lite or PyTorch Mobile
• Docker
• Git/GitHub
• Python 3.8+ and necessary ML libraries
• MATLAB Student Edition (for control algorithm design)
• SolidWorks or Fusion 360 Student Edition (mechanical CAD)
Justification of the minor project
Modern military operations demand highly autonomous, resilient, and versatile platforms capable of
performing a wide range of mission’s reconnaissance, logistics, threat neutralization, and casualty
evacuation—without exposing personnel to undue risk. Existing UGVs suffer from limited autonomy,
frequent communication disruptions, and poor adaptability to contested or GPS-denied environments,
resulting in low reliability (6–24 hr MTBF), high operator workload, and significant mission failures.
Furthermore, the lack of integrated cloud-based command and control prevents real-time coordination among
multiple units, reducing operational effectiveness and situational awareness. By integrating advanced AI
decision engines, hybrid GPS–SLAM navigation, multi-sensor fusion, adaptive robotic manipulators, and
secure, low-latency cloud connectivity, this project directly addresses these critical gaps. The proposed AM-
UGV will autonomously navigate complex terrains, detect and neutralize threats, support soldiers with
automated supply and medical aid, and operate as a cohesive fleet under centralized oversight—ultimately
enhancing mission success rates by over 90%, reducing personnel exposure by 85%, and cutting lifecycle
costs by 60%. This innovation not only advances academic research in robotics and defense technologies but
also delivers a transformative capability that aligns with national security priorities and emerging battlefield
requirements.
Schedule of Activity
Week Activities
Literature review on UGV platforms, autonomy algorithms, sensor fusion, and cloud
1
connectivity
Finalize detailed system requirements and specifications; select hardware and software
2
components
3 Procure microcontrollers, sensors, actuators, and computing platforms
4 Design mechanical layout and CAD of chassis and robotic arm
5 Develop SLAM and GPS integration modules; begin ROS environment setup
6 Integrate primary sensors (LiDAR, depth camera, IMU) and validate data acquisition
7 Implement basic autonomous navigation algorithms; test obstacle avoidance in simulation
8 Build and test robotic arm manipulation routines in Gazebo/ROS
9 Develop AI-based threat detection (uniform recognition, object classification)
10 Establish secure cloud environment; implement data exchange protocols and encryption
11 Integrate UGV subsystems: navigation, perception, manipulation, and cloud communication
12 Conduct preliminary field tests: autonomous navigation and sensor performance
13 Evaluate multi-UGV coordination in mesh network; test real-time command and control
Week Activities
Perform comprehensive performance evaluation: reliability, latency, MTBF, mission success
14
metrics
15 Analyze results; prepare thesis chapters, project report, and presentation
Expected Outcomes & Impact
• 90% reduction in operator intervention
• 85% decrease in personnel exposure to high-risk tasks
• 90% mission success improvement
• 70% survivability enhancement through advanced detection
• $180 M+ annual savings; $2 B+ export potential
• Network-centric warfare capability; continuous upgrades via cloud
Conclusion
The proposed AM-UGV transforms individual vehicles into an integrated defence ecosystem with real-time
coordination, autonomous decision-making, and secure cloud connectivity.
Name of student with Enrolment No.
Shree Ranjan N, A177158825006
Name of Faculty Guide.
Dr. Arun Rajput
Amity Institute of Defence Technology
