Skip to content
View ArashdeepSinghMaan's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report ArashdeepSinghMaan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ArashdeepSinghMaan/README.md

Hi there 👋

  • 👯 I’m looking to collaborate on Robotics Projects
  • 🛠️ Resume

Background

Currently pursuing an M.Tech in Robotics and Mobility Systems at IIT Jodhpur, I am deeply committed to integrating advanced robotics with agricultural practices to drive innovation and sustainability. My journey from Agricultural Entrepreneur and Manager to robotics engineer reflects a focused dedication to leveraging technology for transformative impact in the world.

With a B.Tech in Mechanical Engineering, I bring a robust foundation in engineering principles that enhances my approach to developing efficient, eco-friendly solutions. My experience at Nestlé, where I optimized warehouse layouts to boost productivity, further honed my skills in industrial engineering. I am proficient in Mathematical Modeling and Simulation, ROS, Sensor Integration, Robot Programming, Path Planning, Computer Vision, Artificial Intelligence, experimental research, and data analysis. I hold certifications and have completed projects in MATLAB, Python, Machine Learning, and SOLIDWORKS, which equip me to tackle the complexities of robotics applications.

I am passionate about advancing working standards through cutting-edge robotics, striving to create sustainable solutions that address global challenges and have a lasting impact on the industry.

Projects

Date: April 2025

Objectives

  • Modeling of AUV, ASV:

    • Creating accurate models to represent both the autonomous underwater vehicle (AUV) and the autonomous surface vehicle (ASV) dynamics is crucial for simulating real-world behavior, enabling effective depth and orientation control.
  • Control with Obstacle Avoidance:

    • Developing control systems to maintain stability, avoid obstacles, and transition between modes ensures safe and efficient operation.
  • Multi-Agent Architecture for AUVs:

    • Task Switching and Priority-Based Allocation: Enable each AUV to take on roles based on its capabilities, allowing for dynamic task switching and reallocation based on mission priorities. This will maximize resource utilization and ensure that high-priority tasks receive attention from the most capable agents.
    • Leader-Follower Control Strategy: Implementing a leader-follower setup will create efficient coordination in complex environments, ensuring a lead AUV can guide the group while followers maintain formation. This approach enhances mission cohesion and simplifies multi-agent movement through challenging areas.
    • Inter-Agent Communication: A reliable communication system among AUVs is essential for sharing real-time data on position, task status, and environmental changes. This will support adaptive decision-making, allowing agents to respond collectively to evolving mission conditions.
    • Obstacle Avoidance and Navigation: Equipping AUVs with autonomous obstacle detection and avoidance ensures safe operation and efficient navigation. This capability will be critical for uninterrupted multi-agent operations in dynamic underwater environments.
  • Hardware Development and Deployment:

    • Building and integrating reliable hardware that can withstand dual-environment operations is essential, especially given the added challenge of balancing the combined vehicle-drone system for optimal aerial and aquatic performance.

Tools & Technologies Used: Matlab, SolidWorks, Robot Operating System, Arduino, Sensor Integration


This project presents an integrated robotic bin-picking system that uses advanced computer vision techniques and ROS2 for real-time object detection, pose estimation, and grasp planning. The system utilizes YOLO for detecting objects in RGB images, Point Cloud Library (PCL) for estimating the orientation and position from depth data, and Grasp Pose Detection (GPD) calculate grasp points. These components enable the robot to perform efficient and reliable pick-and-place tasks. The entire process is modularized within ROS2, ensuring smooth communication MoveIt! is used for motion planning and execution.


Our lightweight model is designed to offer on-field disease detection, improving both accessibility and efficiency for agricultural applications. This model is a neural network inspired by the MobileNetV3 architecture and is specifically tailored for resource-constrained environments such as mobile and edge devices.


This project aimed to create a simulated campus environment in Gazebo. A robot was employed to sense this environment and create a map, adapting to environmental changes. After perception, the robot performed path planning to guide others from one location to another. This is a simulation-based project for Autonomous Systems.


Key aspects of this project include:

  • Understanding the kinematics of differential drive wheeled mobile robots (WMRs)
  • Modeling the leader-follower formation using relative distance and angle between robots
  • Designing Lyapunov-based controllers for position, velocity, and orientation control
  • Simulating line and circular formations using the derived control laws

Skills: Robotic Kinematics, Formation Control, Lyapunov Stability Analysis, Simulation and Visualization using Matlab, Problem-Solving, and Mathematical Modeling


Developed a voice-controlled smart home system using an Arduino Nano 33 BLE Sense microcontroller. Key features included:

  • Implementing a word recognition system for appliance control
  • Integrating environmental sensors (temperature, humidity, light)
  • Utilizing relays to connect low-power signals to appliances
  • Deploying machine learning models with TensorFlow Lite for Microcontrollers

The result was an intelligent, sensor-driven home automation solution.
Skills: Hardware-Software Integration, Voice Recognition, Machine Learning Integration, Sensor Integration, Embedded System Design


Designed and implemented a novel pipeline detection system by integrating various computer vision algorithms and filters, including:

  • LAB color space conversion
  • Gaussian blurring
  • Adaptive histogram equalization
  • Canny edge detection
  • Morphological operations
  • Probabilistic Hough transform
  • Adaptive region of interest selection

This approach led to improved detection accuracy.


Feel free to reach out for collaboration or inquiries related to these projects!

Pinned Loading

  1. Robot-Operating-System Robot-Operating-System Public

    C++

  2. Leader-Follower-Formation-Control Leader-Follower-Formation-Control Public

    MATLAB 4

  3. Development-of-Multi-Agent-Coordination-and-Control-for-Surface-and-Underwater-Vehicles Development-of-Multi-Agent-Coordination-and-Control-for-Surface-and-Underwater-Vehicles Public

    C++ 1