Department Publications

Intelligent control of RF transceivers adapting to dynamic operational conditions is essential in the modern and future communication systems. We propose a multi-agent neurosymbolic AI system, where AI agents are assigned for circuit components. Agents have an internal model and a corresponding control algorithm as its constituents. Modeling of the IF amplifier shows promising results, where the same approach can be extended to all the components, thus creating a fully intelligent RF system.

Vision-Language Navigation (VLN) enables robots to navigate through environments using natural language instructions, making human-robot interaction intuitive. Traditional VLN models often rely on navigation graphs, 360-degree views, and perfect localization which pose significant challenges when adapting these models to real-world settings. This work addresses these limitations by performing a simulation-to-real domain shift of a VLN approach that operates in continuous environments without requiring navigation graphs or panoramic views. The proposed system integrates vision-language models that align visual inputs and linguistic instructions within a shared embedding space, facilitating natural language-driven navigation. We employ a Cross-Modal Attention (CMA) based architecture trained on an existing dataset in a simulated environment and fine-tune it using real-world data collected from a …

Humanoid robots have become increasingly popular in applications such as social interaction, education, and service roles, which drives the need for more natural and efficient human-robot interactions. However, currently available humanoid heads often face limitations, including high costs, mechanical complexity, and limited adaptability across diverse environments. To address these challenges, we present an articulated humanoid robot head designed for a receptionist role, integrating a mechanical structure with 21 degrees of freedom (DoF), including mechanisms for the mouth, eyes, eyebrows, and neck, and covered with realistic silicone skin to achieve a human-like appearance and expression. The system integrates a model-based architecture that combines SCRFD, ArcFace, and ByTetrack for face recognition and Llama and Whisper for natural language processing, with hardware support enabling real …

Trajectory planning strongly influences tracking accuracy, actuator demand, and overall execution behavior in robotic manipulators. Classical planners such as cubic, quintic, and trapezoidal profiles are widely used for their simplicity and smoothness, yet they remain purely kinematic and ignore system dynamics and control effort during trajectory generation. As a result, nominally smooth trajectories can lead to inefficient nonlinear execution and increased corrective control action. This paper presents a control-aware optimal trajectory planning framework that explicitly incorporates manipulator dynamics and actuator effort within a finite-horizon formulation. A midpoint linearization strategy is introduced to improve approximation accuracy for large point-to-point motions. In contrast to prior comparisons, the proposed approach enables fair, isolated evaluation of trajectory generation effects under identical closed-loop nonlinear execution conditions. To this end, a unified evaluation framework is developed in which all planners are executed under identical nonlinear dynamics, controller structure, and actuator constraints. Simulations on a nonlinear simplified UR5 manipulator show that the proposed approach consistently reduces tracking error, corrective torque, and closed-loop execution cost compared to classical methods, achieving substantial reductions in actuator effort and execution cost across all evaluated scenarios, demonstrating that kinematic smoothness alone does not ensure dynamically efficient execution.

Traffic signal design in developing countries frequently underperforms due to the direct application of classical models—Webster's delay formula, HCM, ARR123, and ORN13—developed for homogeneous, lane-disciplined traffic conditions. Sri Lankan intersections exhibit fundamentally different characteristics: heterogeneous vehicle streams comprising motorcycles, three-wheelers, non-motorized vehicles, and pedestrians operating without strict lane discipline under geometric constraints. This systematic review synthesizes empirical evidence explaining why conventional signal design methods fail in such contexts. Following PRISMA principles, 138 records were screened, yielding 41 high-quality references spanning foundational theory, classical assumptions, regional adaptations, and Sri Lankan empirical data. The review demonstrates that local intersections systematically violate foundational assumptions regarding lane usage, headway uniformity, start-up behavior, and pedestrian compliance. Observed saturation flows reach 2574 pcu/h/lane—substantially exceeding HCM benchmarks—while behaviors such as motorcycle seepage, lateral filtering, initial surge, and dynamic clustering create discharge patterns that static PCU values cannot capture. A mathematical framework is presented mapping these deviations to quantifiable variables: lateral efficiency, surge discharge dynamics, dynamic vehicle equivalence, headway expansion, and geometric constraints affecting intersection capacity. The paper concludes by proposing context-sensitive design pathways incorporating dynamic PCU factors, behavioral modeling, and simulation …

This paper presents a multi agent neurosymbolic artificial intelligence architecture to dynamically adapt operating parameters of radio frequency (RF) transceivers. The proposed dual branch architecture combines deep learning feature extraction with deterministic symbolic reasoning, leveraging sensed physical parameters such as signal power and spectrum occupancy, to ensure self-adapting and robust hardware safety. Component specific control agents are trained using digital twins and integrated with physical hardware via shared memory space and socket-based inter-process communication for low latency. Experimental results demonstrate accurate modeling and rapid parameter adaptation for error vector magnitude optimization, providing a scalable foundation for intelligent self-adapting RF transceivers.

Solar photovoltaic (PV) systems have become increasingly popular as a sustainable energy source due to the growing need for renewable energy on a global scale. However, the buildup of dust and dirt on solar panels frequently compromises the effectiveness of these systems. Existing cleaning methods often require manual labor, exhibit low efficiency, and are restricted to either a single cleaning method or operational mode. To address these issues, we designed and implemented a semi-autonomous solar panel cleaning robot capable of both dry and wet cleaning. The robot can autonomously navigate on solar panels with a tilt of up to 20 or be manually controlled using a mobile app, and it operates for approximately 75 minutes on a single charge. This study enhances key aspects of the robotic system, integrating advanced edge detection and transition mechanisms using both ultrasonic sensors and image processing techniques. We implemented a robust localization system based on bus-bar detection for precise navigation, upgraded the water supply mechanism and refined the orientation estimation algorithm.

This concept paper proposes an architecture that integrates agentic AI models with digital twin representations for each subsystem component in an RF transceiver. The digital twins, constructed using machine learning techniques such as deep learning and reinforcement learning, are paired with specialized, autonomous AI agent(s) capable of independent reasoning, planning, and adaptive action. Agentic AI models go beyond traditional rule-based/symbolic AI to autonomously select optimal strategies, synthesize data from diverse sources, and interact with both virtual and real-world environments. Ideas for simulations and experimental validations are proposed for future work.

The quadrotor is an underactuated, nonlinear system that presents significant challenges in both modeling and control design. This work develops a decoupled control framework based on the translational (Newtonian) and rotational (Eulerian) dynamics of the quadrotor. A Linear Quadratic Gaussian (LQG) regulator is implemented for control, with two extended Kalman filters employed for state estimation in the respective dynamic subsystems. The full design process, from dynamic modeling to flight simulation presented in detail. Key elements include nonlinear simulation, model linearization, state-space representation, feedforward compensation, Linear Quadratic Regulator (LQR) gain tuning, actuator dynamics, sensor noise, LQG design, and extended Kalman filter. The limitations of applying linear control to a nonlinear system are also presented.

Solar photovoltaic (PV) systems have become a trend as a sustainable energy source on a global scale. However, the dirt accumulated on solar panels often reduces their efficiency, considerably. Existing cleaning methods have limitations such as requiring manual labour, low efficiency, limited to single cleaning method or single operational mode. As a solution, this research study describes the design and implementation of a semi-autonomous solar panel cleaning robot for both dry and wet cleaning. The robot can autonomously navigate on solar panels safely, or user can manually control it using a mobile app. The robot is capable of functioning for around 75 minutes on a single charge on solar panels tilted up to 20°, facilitated by image processing algorithms achieving an accuracy surpassing 96%. The orientation estimation is accomplished through the implementation of three parallel Kalman filters running on …

Optimization carries great significance in both human affairs and the laws of nature. It refers to a positive and intrinsically human concept of minimization or maximization to achieve the best or most favorable outcome from a given situation. Besides, as the resources are becoming scarce there is a need to develop methods and techniques which will make the systems extract maximum from minimum use of these resources, ie maximum utilization of available resources with minimum investment or cost of any kind. The resources could be any, such as land, materials, machines, personnel, skills, time, etc. The disciplines such as mechanical, civil, electrical, chemical, computer engineering as well as the interdisciplinary streams such as automobile, structural, biomedical, industrial, environmental engineering, etc. involve in applying scientific approaches and techniques in designing and developing efficient systems to …

Frequency-modulated continuous-wave (FMCW) multiple-input multiple-output (MIMO) long-range radars currently employed for autonomous robotics have limited maximum range. By employing transmit beamforming and beam scanning, the range can be increased. However, the beam scanning time reduces the achievable velocity resolution. In this paper, we propose an FMCW MIMO radar, operating at 77 GHz, with transmit (TX) beamforming with subarrays to increase the range. We employ four TX subarrays, each having three antennas, with analog beamforming. Compared to TX beamforming as one TX array, our approach provides sufficiently wide beams alleviating beam scanning, further, without substantially reducing the virtual elements of the MIMO radar. We implement the radar signal processing pipeline on a ZYNQ Ultrascale+ ZCU106 FPGA to achieve real-time processing. Furthermore, we employ a …

This chapter presents how optimal control is used in the form of feedback so that optimal control can be implemented on real systems. We consider linear plants and quadratic cost functions and develop the optimal regulator, which is known as the linear quadratic regulator (LQR). The nature of the optimality under LQR is analyzed, and the finite-time and infinite-time regulation processes are presented. Finally, the performance of LQR and PID control systems is compared.

We present SimuSIL, a software-in-the-loop (SIL) simulation platform using open-source tools to capture the behavior of connected vehicles in intelligent transportation system (ITS) applications. Connected cooperative vehicles use vehicle-to-everything (V2X) communication to enable ITS. Real-world testing of ITS applications involves significant risks. Simulating true vehicle dynamics and real-time behavior is challenging in discrete time step environments. We extend the Veins platform, integrating SUMO and OMNet++, with Webots, a simulator for robots and vehicles. Webots implements engine control unit (ECU) models in software to mimic physical vehicle behavior. We validate SimuSIL with a car-following application using Webots and demonstrate its ability to capture communication anomalies like packet losses. Additionally, we demonstrate fuel consumption and CO 2 emissions in autonomous eco-driving …

This study aims to check the behaviour of various controllers that can successfully control a catamaran vessel on the ocean surface for trajectory tracking. Unlike on the ground, the ocean surface has disturbances from water currents, wind forces and ocean waves. Therefore, trajectory tracking is challenging work. A 3D model of a catamaran vessel was simulated to check the vessel’s behaviour with the controllers: Polynomial recurrent neural network-based adaptive PID controller, first and second-order sliding mode controllers, and first-order adaptive controller are among them. The control system is a combination of two controllers. The primary controller controls the vessel’s surge and yaw according to the velocity error. The secondary controller controls the velocity errors required by the primary controller, according to the displacement error of the catamaran vessel from the trajectory and the required forward …

Modern control systems are mostly implemented in discrete time. Hence, the optimal control process also needs discrete-time implementation. This chapter presents how discrete-time optimal control can be developed for discrete state-space systems with quadratic cost functions. Several worked exercises are presented to show how discrete-time optimal control is implemented.

This chapter presents the optimal control design for linear, continuous-time systems. The two main formulations of functional optimization—Lagrange–Euler and Pontryagin–Hamiltonian—are presented, and the conditions for optimality in each formulation are derived. The nature of optimality is also explored. The process of introducing end-point conditions of final time and final state is presented. Several exercises are provided to emphasize the application of the two formulations in optimal control system design.

This chapter presents how to use the calculus of variations to find the optimum function within a group of functions without considering the constraints. A few examples of functional optimization, including the shortest path and the minimum-time path, are presented. The Matlab implementation of functional optimization is also demonstrated. Figure  shows possible paths f ( x ) of a single variable functional between two fixed points and . It also shows the optimal function .

This chapter presents how to combine the equality constraints with the objective function in the optimization process. How to deal with inequality constraints using KKT conditions is presented next. Then, the implementation of quadratic optimization with equality constraints and boundary limits is demonstrated using the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathtt quadprog$$\end{document} command in Matlab. In the end, the optimization of an arbitrary function subject to nonlinear constraints, linear constraints, and boundary limits is demonstrated using the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage …

Some control systems need to maximize a certain outcome while minimizing the cost. For example, a rocket propulsion system intends to reach the maximum altitude with the least fuel. In such systems, the cost minimization concept in optimal control is changed to outcome maximization, and the particular optimal control design process can be implemented using Pontryagin’s maximum principle. This chapter presents the maximum principle based on the Hamiltonian and demonstrates its application through several exercises. The bang–bang control and control switching, which are outcomes of the maximum principle, are also presented.

Optimization aims at finding a unique point, a unique state, or a unique function (a sequence of points or states) that is associated with the minimum cost or maximum benefit with respect to a certain criterion, subject to constraints. Function optimization is largely based on calculus developed by Sir Isaac Newton and Gottfried Wilhelm Leibniz. The most comprehensible optimization process is finding the minima or maxima of a single variable function by setting the first derivative , which can be extended to multi-variable functions by setting all partial derivatives to zero . More often, the functions to be optimized are costs that can be modeled in the quadratic form , which allows wider applicability of mathematical tools in the optimization process, hence quadratic optimization.

The optimal control sequence generated offline does not help realize optimal control in actual systems due to state deviations that are not captured in the state-space model. Such deviations are caused by unmodeled dynamics and noise, leaving only the first few control signals in the optimal control sequence valid and practically useful. In this context, the model predictive control (MPC) is presented in which an optimal control sequence is generated for a finite time into the future (the prediction horizon), and only the first few control signals (the control horizon) are practically used. After each control horizon, the process recurs in its actual state at that time.

In disaster-stricken environments, it’s vital to assess the damage quickly, analyse the stability of the environment, and allocate resources to the most vulnerable areas where victims might be present. These missions are difficult and dangerous to be conducted directly by humans. Using the complementary capabilities of both the ground and aerial robots, we investigate a collaborative approach of aerial and ground robots to address this problem. With an increased field of view, faster speed, and compact size, the aerial robot explores the area and creates a 3D feature-based map graph of the environment while providing a live video stream to the ground control station. Once the aerial robot finishes the exploration run, the ground control station processes the map and sends it to the ground robot. The ground robot, with its higher operation time, static stability, payload delivery and tele-conference capabilities, can then …