View My Projects
Research Publications
1. Unified Safety-Critical Motion Planning for Connected Non-Holonomic Agents Using an Adaptive A* and Hybrid A* Integration. - Ubiquitous Robots 2024 - Read More
Find the link here
Abstract : This paper presents a unified approach to safety-critical, multi-agent motion planning for connected autonomous robotic systems, seamlessly integrating the kinematic, dynamic, and safety constraints of individual agents, while reducing computational expense to ensure real-time applicability. By integrating Voronoi Cells with an adaptive blend of A* and Hybrid A* algorithms, the proposed combinational planner ensures the generation of feasible and executable trajectories, guaranteeing efficient and collision-free navigation of multiple agents in dynamically complex environments. An additional deadlock avoidance strategy is proposed to further enhance the safety layer. We demonstrate the effectiveness and robustness of our approach in terms of efficiency, collision avoidance, and deadlock resolution through simulations in diverse, randomly generated environments. The results show that the proposed method outperforms existing methods in terms of dynamic considerations and obstacle avoidance, making it a practical real-time motion planning approach for connected non-holonomic agents in complex environments.
2. Parametric review on Fuel Cells and their Applications
Find the link to paper here
Abstract : This study aims to review the issues affecting the long term performance and the life span of the fuel cell in accordance with the various surveys of the currently available. According to current research, parameters such as temperature, pressure along with other issues such as fuel and oxidant starvation (stoichiometric effect), corrosion, poor water management, humidity, and uncontrolled chemical reactions are some of the reasons leading to poor performance in the fuel cell. Poor water management can either lead to flooding or dehydration, both of which are extremely detrimental for the longevity of the fuel cell since the former facilitates corrosion of electrodes, membrane and catalyst layers whereas the latter leads to shrinkage of the membrane. Also, contamination of fuel cell membranes due to corrosion products or any impurities from outside leads to the poisoning of the cell. The construction of fuel cells in the future taking into consideration all these issues and mechanisms can lead to a performance-enhanced and long-lasting fuel cell.​
Skills
Programming:
PYTHON
C++
MATLAB &
SIMULINK
UNIX SHELL SCRIPTING
Libraries and Frameworks:
KERAS
Robotics Engineering Skills:
ROS NAV2
ROS1/ROS2
GAZEBO
Other Skills:
GitHub Actions
for CI/CD
Coursework
RBE 500 - Foundations of Robotics
Some topics covered : ROS, Intro to Forward, Inverse & Velocity Kinematics, Intro to Control Theory & Systems, Actuators, Sensors, Kalman & Bayesian Filters
RBE 501 - Robot Dynamics
Some topics covered : Forward, Inverse & Velocity Kinematics, Rodrigues Formula, Manipulability, Jacobian, Lagrangian & Newton-Euler Formulation
RBE 502 - Robot Control
Some topics covered : Linear and Nonlinear Control, Lyapunov Stability, State and Output Feedback Control, Linear-Quadratic Regulators, Trajectory Generation and Planning, Feedback Linearization Control, Robust and Adaptive Control, Force and Impedance Control, Control Lyapunov Functions, Model Predictive Control, Control of Robotic Manipulators through MATLAB and ROS
RBE 550 - Motion/Path Planning
Some topics covered : Search algorithms, Discrete and sampled-based planning algorithms(PRM, RRT*, A*, Dijkstra, etc) Collision Detection and Avoidance and planning with non-holonomic constraints, manipulation and mobile manipulation, grasping and human-aware motion planning.
RBE 595 - Reinforcement Learning
Some topics covered : Intro to RL, Bandit Problems, Markov Decision Processes and Bellman equations, Dynamic programming- value/policy iteration, Monte Carlo Methods, Temporal Difference (TD) Learning, n-step Temporal Difference Learning, Intro to Deep RL: Poly Gradient & Actor-Critic methods
CS 541 - Deep Learning
Some topics covered : Convolutional and Recurrent Neural Networks, General Adversarial Network, Optimization and Regularization techniques, Transformers, Activation functions, Loss functions, Auto-Encoders
CS 539 - Machine Learning
Some topics covered : Intro to ML, Pandas & Datasets, Probability & Exploratory Data Analysis, Classification, Hypothesis Testing, K Nearest Neighbors, k-means clustering, metrics, like accuracy, precision, recall, ROC curves, confusion tables, etc.