News & Research

The rapid growth of robotics and embedded system technologies has increased the need for intelligent and userfriendly robotic systems. Conventional robot control methods such as remote controls, keyboards, and programmed instructions often make human-robot interaction difficult and less efficient. To overcome these limitations, this project proposes the design and development of a Voice Controlled Humanoid Robot that can understand human voice commands and perform corresponding actions.The proposed system uses speech recognition technology to convert voice commands into digital signals. These commands are transmitted through Bluetooth communication to a microcontroller such as Arduino or ESP32, which processes the commands and controls servo motors through a motor driver circuit. Based on the received instructions, the humanoid robot performs movements such as walking, turning, hand movements, and other predefined actions.The main objective of this project is to create a simple, low-cost, and efficient robotic system that improves natural communication between humans and robots. The system provides hands-free robot control, making it suitable for educational purposes, assistive technologies, automation systems, and future smart robotic applications. The project demonstrates the practical implementation of embedded systems, wireless communication, and voice recognition technologies in humanoid robotics.

Autonomous robot navigation requires reliable path planning under uncertainty. Classical algorithms such as $\mathrm{A}^{*}$ and Dijkstra's, and sampling methods like PRM/RRT, work well on static, discrete maps but degrade in dynamic, high-dimensional settings. We study reinforcement learning (RL) for this problem, contrasting value-based Q-learning/DQN (effective with discretised motion primitives) with policy-gradient, actor-critic methods that natively support continuous control. We present an actor-critic approach for continuous navigation that uses offpolicy training with experience replay and entropy regularisation (SAC-style) to stabilise learning while producing smooth, kinodynamically feasible commands (linear and angular velocities). Evaluations in a first-person navigation task and an unmanned-driving simulator use success rate, SPL/path-length ratio, collisions and learning curves. Compared with a DQN baseline and a vanilla actor-critic, our method converges faster and more stably, achieving rising episode returns (from −5 to +7 by 10 episodes) and the lowest average training time ($\sim 1300 \mathrm{s}$ versus $\sim 1300-1700 \mathrm{s}$ for DQN and $\sim 2300-2750 \mathrm{s}$ for standard actor-critic). Qualitative rollouts show fewer collisions and smoother trajectories. These results indicate that actor-critic RL is a strong choice for continuous-control navigation, outperforming discrete value-based methods in dynamic environments.

This paper compares the performance of a traditional approach for autonomous robot navigation and a new approach for the same problem, all within the framework of reinforcement learning. A new approach for the problem has been introduced and compared against the traditional approach, referred to as the value iteration approach for holonomic robots and the new approach for the same problem in relation to the traditional approach. These approaches include sampling-based policy estimation and interpolation and optimization-based filtering for obstacle avoidance. Actor critic methods for non-holonomic scenarios include Deep Deterministic Policy Gradient (DDPG) and Soft Actor-Critic (SAC) approaches. The simulation of various 2D and 3D scenarios, ranging from simple to complex, shows that value iteration method convergence occurs rapidly, while at the same time a success rate of over 95% can be attained within 31 minutes of virtual time. DRL techniques, however, succeed in attaining an average of 88.5% ± 4.2% in 300 scenarios, where in each case, 35% faster convergence of SAC compared to DDPG could be attained. The efficacy of reinforcement learning approaches to find practical solutions to robot navigation in various scenarios, while meeting constraints, has been proven.

This paper presents NAVBOT25, a labelled dataset aimed at strengthening the overall security of autonomous robots against network-based cyber threats within the Robot Operating System (ROS) platform. NAVBOT25 offers a comprehensive, labelled dataset that captures both normal operational behaviour and a variety of attack scenarios relevant to ROS-based systems. This dataset was generated by deploying a TurtleBot3 running ROS Noetic in controlled laboratory setting, where real-world attack vectors were executed —including SSH brute-force attempts, reverse shells, port scans, and ROS-specific attacks such as unauthorized publishing actions and topic flooding. Network traffic was captured using tcpdump, and 83 flow-level features were extracted using CICFlowMeter, resulting in a series of CSV files. Designed to support the development of AI-assisted intrusion detection systems, NAVBOT25 addresses existing gaps in robotic cybersecurity research by providing a richer and more diverse dataset for evaluating threat detection in networked robotic systems.

Autonomous navigation in cluttered, unknown environments requires agents to balance local obstacle avoidance with global path optimality. This paper presents a novel hybrid approach for path planning in such environments by integrating Spiking Neural Networks, Artificial Potential Fields, and RRT* for episodic path optimization based on spatial memory. The proposed approach can be viewed as a lifelong learning paradigm where the intelligent agent creates a cognitive map based on the Spiking Neural Networks and continuously updates its spatial memory during episodes of navigation based on the Artificial Potential Fields approach. The spatial memory obtained from the Artificial Potential Fields approach can then be integrated into the RRT* path planning approach for path optimization during subsequent episodes of navigation, avoiding certain areas where obstacles are more probable based on the spatial memory. The performance of the proposed approach was evaluated on a grid environment with various obstacles, and the results show rapid convergence within six episodes with a success rate of 100% and a reduction in path loss of 89.8% for the normalized path length. The performance of the proposed approach was compared with the Artificial Potential Fields and RRT* path planning approaches, and the results show the proposed approach can significantly reduce the planning time and node expansion for path planning. The proposed approach can therefore be viewed as a novel approach for path planning based on spatial memory, which can be used for efficient path planning in unknown and dynamic environments.

Efficient representation and querying of railway networks are crucial for autonomous railway systems and digital infrastructure management. This paper introduces VEctorial Railway NEtwork (VERNE), an interpretable data structure and algorithm that integrates vector-based spatial partitioning with a railway-specific topological framework to enhance network representation and navigation. VERNE is designed to optimize query efficiency, reduce memory footprint, and ensure scalability for real-time applications. Its internal mechanism results from a comparative performance analysis between a $k$-d tree, an STRtree and two custom algorithms, highlighting trade-offs in computational efficiency and memory overhead. The proposed approach is validated using datasets from both the French and Swedish railway networks, demonstrating its effectiveness in real-world scenarios. The results indicate that VERNE provides a robust and scalable solution for railway infrastructure modeling, offering improvements in localization speed and computational efficiency. Another advantage is that it inherently manipulates atomic elements which can contain any information relevant to directly perform navigation onboard an autonomous robot. This work contributes to the advancement of railway digitalization by providing a structured methodology for spatial data processing in autonomous railway systems.

Assistive robotics can be designed to support the physically disabled persons in numerous ways. They are trying to reinstate human capabilities which has been condensed or lost by accident, at old age or disease. But physically disabled persons facing some troubles in their moments with the existing assisted devices. To give the support for Old age and disabled persons by developing an intelligent Robotic wheel chair, to improve the complex navigation techniques in mobile robotics replacing the existing assisted devices like wheelchair with the automated one. A new algorithm is developed depend onbetter reality which replaces the existing system and improves effective localization with high accuracy.This technique is mainly developed by blob analysis, pattern and color matching. We designed the total prototype on national instruments Robotic starterkit2.0. It is important to design a robot in such a way which avoids obstacles automatically when collision takes place. These types of robotic wheel chairs are very efficient and enable the user to move around easily and also gives the independence to one who have motor disability can easily move without others help.

This paper deals with a problem of multitask agents' navigation in urban environment with obstacles using different algorithmic approaches: neural network models with a system of rewards and penalties, neural networks oriented on distance minimization, as well as models that use direct movement vectors and rectangular route structures. The novelty of the presented method is the creation of a hybrid algorithm that incorporates strict rules for movement in an initially unknown environment and, when obstacles appear, switches to a neural network for obstacle avoidance. This approach combines deterministic movement, which can be adapted to artificial intelligence for safe and reliable navigation in uncharted territory. Experiments showed that thirty neural argents trained purely using rewards and penalties in movement exhibits slow learning and cyclical movement as clusters, which is due to the fact that they optimize the current state without global planning. Models trained solely on distance optimization perform slightly better, but still create clusters of movement toward the goal. Meanwhile, the use of strict linearity rules and rectangular routes allows for effective obstacle avoidance and consistent target achievement with less time under conditions of limited graph information. The results show that rule-based learning yields better results in agent movement than fully autonomous agents. Consequently, the combined path generation method yields the best results in agent navigation along a known path.

Autonomous aerial navigation in absolute darkness is crucial for post-disaster search and rescue operations, which often occur from disaster-zone power outages. Yet, due to resource constraints, tiny aerial robots, perfectly suited for these operations, are unable to navigate in the darkness to find survivors safely. In this letter, we present an autonomous aerial robot for navigation in the dark by combining an Infra-Red (IR) monocular camera with a large-aperture coded lens and structured light without external infrastructure like GPS or motion-capture. Our approach obtains depth-dependent defocus cues (each structured light point appears as a pattern that is depth dependent), which acts as a strong prior for our <italic>AsterNet</italic> deep depth estimation model. The model is trained in simulation by generating data using a simple optical model and transfers directly to the real world without any fine-tuning or retraining. <italic>AsterNet</italic> runs onboard the robot at 20 Hz on an NVIDIA Jetson Orin<inline-formula><tex-math notation="LaTeX">$^{\text{TM}}$</tex-math></inline-formula> Nano. Furthermore, our network is robust to changes in the structured light pattern and relative placement of the pattern emitter and IR camera, leading to simplified and cost-effective construction. We successfully evaluate and demonstrate our proposed depth navigation approach <italic>AsterNav</italic> using depth from <italic>AsterNet</italic> in many real-world experiments using only onboard sensing and computation, including dark matte obstacles and thin ropes (<inline-formula><tex-math notation="LaTeX">$\varnothing$</tex-math></inline-formula> 6.25 mm), achieving an overall success rate of <italic>95.5%</italic> with unknown object shapes, locations and materials. To the best of our knowledge, this is the first work on monocular, structured-light-based quadrotor navigation in absolute darkness.

We showed recently that a novel prosthesis control, based on natural arm movement reconstructed from an Artificial Neural Network (ANN) that receives movement goal and stump motion as inputs, enables close-to-natural reaching control in Virtual Reality (VR). Here, we applied and tested this control in the physical world using first-person teleoperation of Reachy2, an open-source humanoid robot made by Pollen Robotics that ranked 2nd at ANA Avatar XPRIZE. Direct teleoperation reproducing all arm joints of non-disabled participants (n=14) elicited a 100% success rate for grasping objects at various locations, with best possible usability scores and small workload scores. High success rates (>92%) were also obtained when all distal joints from the elbow onward were operated with the novel prosthesis control, using a movement goal identified through gaze-guided computer vision. While usability and workload scores were slightly degraded when non-disabled participants used the prosthesis control as compared to direct teleoperation, both were scored similarly well by a sample from our target population (n=8 participants with transhumeral limb loss). This platform and control schemes offer broad perspectives for prosthesis control, but also for teleoperation robotics and human-robot interactions.

Labor shortages and aging populations are straining hospital systems globally, prompting interest in humanoid robots as a viable technology solution for healthcare support. This paper presents a proof-of-concept deployment of a Unitree G1 humanoid robot using advanced SLAM with multi-modal sensors (LiDAR, depth cameras) for reliable navigation in dynamic hospital-like environments. Unlike conventional approaches that model humans solely as obstacles to avoid, our system implements human-aware navigation. Respecting proxemics, social context, and malleable spatial boundaries to treat people as collaborative partners, enabling safe, legible co-navigation in crowded wards and corridors. By demonstrating autonomous, purposeful movement for logistics and patient-support tasks, this research illustrates a pathway to augment healthcare delivery, worker support, and patient care outcomes through adaptable, human-centered robotics.

Behavior Cloning (BC) has emerged as a highly effective paradigm for robot learning. However, BC lacks a self-guided mechanism for online improvement after demonstrations have been collected. Existing offline-to-online learning methods often cause policies to replace previously learned good actions due to a distribution mismatch between offline data and online learning. In this work, we propose Q2RL, Q-Estimation and Q-Gating from BC for Reinforcement Learning, an algorithm for efficient offline-to-online learning. Our method consists of two parts: (1) Q-Estimation extracts a Q-function from a BC policy using a few interaction steps with the environment, followed by online RL with (2) Q-Gating, which switches between BC and RL policy actions based on their respective Q-values to collect samples for RL policy training. Across manipulation tasks from D4RL and robomimic benchmarks, Q2RL outperforms SOTA offline-to-online learning baselines on success rate and time to convergence. Q2RL is efficient enough to be applied in an on-robot RL setting, learning robust policies for contact-rich and high precision manipulation tasks such as pipe assembly and kitting, in 1-2 hours of online interaction, achieving success rates of up to 100% and up to 3.75x improvement against the original BC policy. Code and video are available at https://pages.rai-inst.com/q2rl_website/

High levels of electric vehicle (EV) penetration and load uncertainty pose significant challenges to traditional voltage regulation in distribution systems (DS), particularly concerning voltage drops. This study investigates the potential of a dual-service mode (V2V/V2G) for mobile charging using multiple charging robots, cooperating with conventional DS voltage regulation methods to enhance performance. Specifically, we propose a multi-robot adaptive charging network (MRACN) embedded in a three-level voltage regulation framework to address voltage violations. At the low level, we introduce a voltage security rule-based dispatch strategy for MRACN to mitigate EV-induced voltage drops. At the mid-level, we optimize day-ahead scheduling of on-load tap changers and capacitor banks via optimal power flow for long-term voltage regulation. At the high level, we employ an unscented Kalman filter-based deep reinforcement learning (UKF-DRL) approach to integrate MRACN into DSs for real-time voltage control. Experimental results demonstrate that MRACN effectively reduces voltage violations and enhances the flexibility of conventional voltage control systems. Moreover, the UKF-DRL method accelerates DRL training by nearly an order of magnitude compared to full AC power-flow solutions, with the overwhelming majority of state estimates deviating by no more than 2%.