Projects

The increasing prevalence of drones has prompted a critical need for effective counter-drone systems. While ground-based methods have limitations, this research explores the potential of drone-based acoustic detection. By leveraging aerial platforms, we aim to overcome challenges associated with ground-based systems and develop a more robust and adaptable counter-drone solution. This paper presents a novel approach combining advanced signal processing, data augmentation, and deep learning to accurately detect drones through...

This project developed a navigation framework for a mobile robot operating in dynamic environments populated by moving agents such as pedestrians. The system combines a Probabilistic Roadmap (PRM) for global offline planning with a novel Model Predictive Asymptotically Optimal RRT (MP-AO-RRT) for online local planning, integrating kinodynamic feasibility, a tailored cost function, and Model Predictive Control principles to adapt in real time.

This project is a continuation of a previous project, using the solution to the problem we found earlier: Fixing the problem that arises when you want to communicate with a drone that is out of range, autonomously by sending more drones to increase the reception range. The goal is to use autonomous drones to receive some information from the environment to the computer, in this case the information we receive...

This project evaluates visual odometry accuracy by comparing it to OptiTrack ground truth data. We conducted multiple experiments in different environments to analyse how factors like objects, featureless areas, and Z-axis changes affect motion estimation. Euclidean distance was used to calculate the error between the estimated trajectory and OptiTrack data. To improve the F1TENTH car’s performance, we optimized its ERPM gain by running tests with different gain values, calculating the...

In this project, we developed a system that enables discreet, reliable, and precise control of a pre-built robotic hand. The system is based on EMG signals from the upper leg muscles and is designed for individuals with upper limb amputations. The robotic hand was developed by the Haifa 3D organization, and we focused on designing and implementing an interface that converts muscle signals into commands for the hand. The main...

In this project, we use a Tello DJI drone to track a vehicle. Every half second, the drone captures an image and sends it to a computer. The computer receives the image and, using the YOLO algorithm, identifies objects in the image – the vehicle, obstacles, and the target. The RRT algorithm is then used to compute the optimal path from the car­­­ to the target considering the obstacles, and...

In recent years, the autonomous vehicle industry has been growing rapidly, with companies such as Tesla, General Motors and Mobileye competing to develop optimal solutions. The field is accompanied by many challenges that highlight the complexity of real-world driving scenarios, such as: planning algorithms for traffic planning, taking into account the dimensions of the vehicle and its physical limitations, and understanding the environment and its obstacles . An optimal route...

In this work, we develop a comprehensive local planning strategy to implement during F1TENTH races consisting of a reactive planner using the ’disparity extender’ strategy as well as a planner based on B-splines to handle overtakes. F1Tenth is an international community of researchers, engineers, and autonomous systems enthusiasts founded at the University of Pennsylvania in 2016 [3]. F1Tenth’s mission is to provide an open-source platform for autonomous systems research and...

As the use of robots and machines for automation accelerates, the need for algorithms to generate paths for them has emerged. One of the challenges in creating such algorithms is to build paths efficiently while preventing collisions between robots in a shared workspace. In projects like automated warehouse management, the issue of collisions becomes even more significant. Beyond the need to protect cargo while its moving from point to point,...

This project focuses on showing how a robotic hand can grasp and classify objects using only finger positions, without relying on additional sensors. Using NVIDIA’s Isaac Sim simulator the project integrates LEAP HAND, a robotic hand, and tests its ability to identify object type, position, and orientation using a with a MACE-based algorithm. A set of kitchenware items was chosen to showcase this capability. The MACE algorithm is a key...

This project focuses on integrating tactile sensors into a prosthetic hand and providing feedback to the user, with an emphasis on a cost-effective solution to ensure accessibility for a broader population. As part of the project, a literature review was conducted to examine existing solutions, sensor types, and various feedback methods. The review identified key criteria for sensor selection and their optimal placement within the system. Temperature and force sensors...

The goal of this project was to evaluate the distance between Kornhauser’s algorithm for the Pebble Motion Problem on graphs and the optimal solution — specifically, by comparing the number of moves required by each method to transform an initial configuration into a target configuration. Kornhauser’s algorithm offers a general polynomial-time solution based on group theory, decomposing permutations into 3-cycles. In contrast, we implemented an optimal solution using Mixed-Integer Linear...

In our project, we built upon a previous study that aimed to train a quadruped robot to walk even in scenarios where motor malfunctions occurred. The disturbances addressed in the previous project included scenarios where a motor completely stopped working or one of the robot’s joints became stuck at a fixed angle. In our work, we expanded the scope of disturbances to make them more realistic. Specifically, we introduced motor...

The prospect of integrating the ability to utilize the power of AI and machine learning into robotics for understanding incoming data collected from the surrounding environment by providing them with various types of sensors and cameras, as is the case in image and object segmentation for example, means that we are heading towards a future of even greater dependency on intelligent connected devices in our daily lives. The aim of...

Hand amputation (and limb amputation in general) can be caused by accidents, injuries in battle and congenitally. A person whose hand is amputated may find it much more difficult to do everyday tasks and is limited in certain activities. There have been many and varied solutions to this problem for decades, some of them simpler (like the hook we know from the pirates in the movies), and some of them...

This project focuses on the development and implementation of a vision-based solution for detecting rival vehicles in the F1Tenth competition environment. The primary challenge was to accurately identify dynamic objects in real time while adhering to the computational and mechanical constraints of the vehicle. The proposed solution integrates advanced image processing techniques with existing resources such as cameras to generate both RGB and depth images. After evaluating several algorithms, including...

This project aimed to develop a functional physical system in which drones collaboratively transport a payload from a starting point to a final destination. The key focus was to document the thought process, experiments, and challenges encountered, providing insights into the limitations of the chosen methodology and working environment. A simulation was created using the Webots robotics platform to demonstrate the behavior of the drone system. The drones followed the...

This project developed an affordable virtual referee system for amateur tennis players to determine whether shots are in or out. Professional systems like Hawk-Eye are prohibitively expensive, leading the team to create a cost-effective alternative using computer vision techniques. Project Goals Accuracy: At least 80% accuracy in call decisions Affordability: Significantly less expensive than professional systems Ease of Setup: Simple installation process for casual players Non-intrusive: No interference with gameplay Educational Value: Apply academic knowledge...

One of the well-known challenges in robotics is achieving efficient and precise autonomous movement from one point to another using a small robotic platform. This challenge is reflected in several areas of our lives : in logistics, robots move goods in massive warehouses. In the Home consumer market, A wide range of autonomous vacuum cleaners is available in a wide price range. And in the defense industry There is a...

In recent years, autonomous navigation systems have become increasingly sophisticated, with applications ranging from self-driving cars to delivery robots. These systems face numerous challenges, particularly in dynamic environments where conditions change rapidly and unpredictably. While traditional pathfinding algorithms excel in static environments, they often struggle when confronted with moving obstacles, traffic signals, and the need for real-time path adjustments. Our project implements an intelligent pathfinding system inspired by modern navigation...

The problem of finding the optimal path is one the main problems each autonomous system must solve. Therefore, this is a highly researched problem in robotics. In the past last years there has been continuous interest and accomplishments developing faster and more accurate algorithms for this purpose. Each algorithm has its own advantages and disadvantages, the tradeoff in those algorithms is mostly between running time and performance. After conducting research...

Amputation of limbs, particularly arms, can result from work accidents, road accidents, combat injuries, or congenital conditions. Various solutions exist to help arm amputees function as normally as possible. The market offers different products, some of which are expensive, heavy, and cumbersome for daily use. Additionally, some solutions involve arm movement through different body parts, including the muscles of the amputated arm, which is not preferred for amputees suffering from...

The project goal was to develop a mobile robotic system capable of localizing and mapping the environment using SLAM algorithm. The robotic platform, iRobot Create3, and computing platform, Nvidia Jetson nano 4GB, were integrated into a single system orchestrated using ROS2 middleware. Establishing communication between the different components of the system was done using several guides provided by Nvidia and iRobot. Since those guides are constantly updated and some of...

  Overview: The Jetbot Mini project involved using a robot equipped with wheels, a camera, and a Jetson Nano card. The robot was programmed in Python using Jupyter Notebook to navigate a room by detecting and moving towards objects of predefined colors.   Objectives: – Develop a system for the Jetbot Mini to automatically navigate to objects of specific colors within a room. – Ensure the robot can sequentially identify...

Our project introduces an automated system designed to digitize books’ pages efficiently. At its core is a robotic hand equipped with precise motor control, enabling it to flip pages of a book, Integrated into this mechanism is a RealSense camera, which is tasked with capturing clear images of each flipped page in real-time Following the image capture phase, advanced algorithms are employed to ensure optimal clarity, correct distortions, and alignment...

As robots will start to handle more tasks in society, so does the chance for damage to them increases.  Such damages are usually not incorporated inside their training scenarios and therefore, their behavior will become unpredictable. While some tasks can sustain such risk, in others, such as rescue missions, or handling of dangerous substances, a mission cannot be aborted in the middle. For robots to be successfully integrated in such...

לכלבים רובוטיים פוטנציאל תעשייתי משמעותי. החל מביצוע משימות מסוכנות/ חזרתיות, ועד סיוע לעיוורים. במהלך הפרויקט השתמשנו בפלטפורמה unitree go1 וביצענו עליה משימות שונות ע״מ לאפשר המשך מחקר בתחומים שונים ע״ב הפלטפורמה. תוצרי הפרויקט שלנו הם מדריך שימוש בפונקציות משמעותיות של הרובוט,  מעטפת קוד המאפשרת לכתוב לרובוט פקודות בשפת פייתון וסביבה המאפשרת שליטה בפעולות הרובוט דרך מקלדת המחשב. מוטיבציה: יצאנו לדרך עם הפרויקט דרך המוטיבציה של קידום הרעיון של כלב רובוטי...

The goal of our project is to synchronize a given number of drones, which communicate through a UDP network, by using artificial intelligence that instructs them to move in a given closed path (e.g., a circle, triangle, etc.). This interface receives an image of a closed path as input and makes the drones move on it without collision. This can be used to scan an area or in rescue missions....

In the project we use the controller placed on top of the ankle in combination with a sensing system located on the bottom of the foot. The purpose of the project is to allow the amputee to move the robotic arm in a comfortable and easy-to-use manner. The product we developed communicates with the arm via wireless Bluetooth communication. Identification of a command sent to the arm is carried out...

Advances in robotics and artificial intelligence have the potential to revolutionize the way we live our daily lives. Rather than being a danger to humans, robotics and AI can be used to augment human capabilities, making our lives easier, safer, and more efficient. The prospect of integrating the ability to utilize the power of AI and machine learning into robotics for understanding incoming data collected from the surrounding environment by...

In this project, we have created a tennis ball-collecting robot. We based our project on our last year’s project where we created an auto-navigation robot with the ability to identify a tennis ball. We have started our project by trying and testing different mechanisms that will use us to catch and lift a tennis ball. We went from super simple and light construction made of thin wood and finished with...

Intel’s Openbot is a platform that allows users to create and control their own robots using a smartphone. iRobot Create is a programmable robot platform that is widely used for education and research purposes. This project integrates iRobot Create with Openbot, allowing users to control their iRobot Create robots using the Openbot app. The integration of iRobot Create with Openbot increases functionality, thanks to the smartphone’s processing unit, camera and...

The goal of the project was to create a robot that draws a sketch of a given image on a page. The robot should be compact and easy to use. The project was carried out as a continuation of the project carried out by two students in the previous semester – Tal Shafi and Nohar Marcus. They reached a good result but could be improved. During the project, all stages...

In this work, we launch a new competitive robotics team at the Technion, which will aim to construct a fleet of autonomous small-scale racecars using the F1Tenth framework to participate in international racing competitions as well as conduct advanced autonomous vehicle research F1Tenth is an international community of researchers and engineers, originally founded at the University of Pennsylvania (UPenn) in 2016 to foster research and collaboration in autonomous systems, composed of 4...

Our project represents a significant breakthrough in the fields of robotics and human-computer interaction, as we have designed a sensor-based glove that permits the remote control of a system for drawing on a whiteboard without any physical contact. Our system uses four stepper motors that enable precise pen movement in any direction on the whiteboard. To achieve this, we have incorporated a highly accurate real-time sensor called the vector-nav 100,...

We created a robotics lab for the faculty. The lab is a place where students can learn and discover the field of robotics. The laboratory includes written and recorded explanations, examples and tasks. Furthermore, we created a detailed, clear and project-oriented study tool. The tool enables learning ROS without previous knowledge and refers to the learning weaknesses of the software. The student can use the lab as a guide to...