2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
In this paper, we consider a problem of foothold selection for the quadrupedal robots equipped wi... more In this paper, we consider a problem of foothold selection for the quadrupedal robots equipped with compliant adaptive feet. Starting from a model of the foot we compute the quality of the potential footholds considering also kinematic constraints and collisions during evaluation. Since terrain assessment and constraints checking are computationally expensive we applied a Convolutional Neural Network (CNN) to evaluate the potential footholds on the elevation map. We propose an efficient strategy for data clustering and segmentation with CNN. The data for training the neural network is collected off-line but the inference works on-line when the robot walks on rough terrains and allows for efficient adaptation to the terrain and exploitation of the properties of the soft adaptive feet.
Background COVID-19 digital contact-tracing apps were created to assist public health authorities... more Background COVID-19 digital contact-tracing apps were created to assist public health authorities in curbing the pandemic. These apps require users’ permission to access specific functions on their mobile phones, such as geolocation, Bluetooth or Wi-Fi connections, or personal data, to work correctly. As these functions have privacy repercussions, it is essential to establish how contact-tracing apps respect users’ privacy. Objective This study aimed to systematically map existing contact-tracing apps and evaluate the permissions required and their privacy policies. Specifically, we evaluated the type of permissions, the privacy policies’ readability, and the information included in them. Methods We used custom Google searches and existing lists of contact-tracing apps to identify potentially eligible apps between May 2020 and November 2021. We included contact-tracing or exposure notification apps with a Google Play webpage from which we extracted app characteristics (eg, sponsor, ...
2016 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET), 2016
In this paper we present an automated sedation system for ICU setting. The system is based on obj... more In this paper we present an automated sedation system for ICU setting. The system is based on objective sedation assessment using the bispectral index and takes into account the patient's hemodynamics i.e. heart rate and blood pressure to ensure that the target sedation level is reached safely. Two different intravenous sedative agents are used (propofol and midazolam) in two separate algorithms for closed loop automated sedation. Different sedation scenarios are simulated in order to mimic this medical process and test for possible complications that the patient might face during the stay in the ICU. The proposed system is adaptable to patient hemodynamic variations and presents an automated process to achieve an optimal target sedation. This system could reduce the patient's ICU length of stay, facilitates the work of the ICU nurses.
This dataset has data collected from force, current, position, and inertial sensors of the NAO hu... more This dataset has data collected from force, current, position, and inertial sensors of the NAO humanoid robot while walking on Vinyl, Gravel, Wood, Concrete, Artificial grass, and Asphalt without a slope and while walking on Vinyl, Gravel, and Wood with a slope of 2 degrees. In total, counting all different axes and components of each sensor, we monitored 27 parameters on-board of the robot. The data was collected while the robot was moving 0.4 meters in the Forward, Backward, Left, and Right directions, and the data collection process was repeated five times for each terrain in each direction. Moreover, the forward and backward iterations had a maximum step size of 0.02 m, step height of 0.01 m and maximum step frequency of 0.005 while the left and right iterations had a maximum step size of 0.12 m, step height of 0.02 m and maximum step frequency of 0.005.
2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2017
This paper proposes a novel technique for designing humanoid gaits, inspired from human walking c... more This paper proposes a novel technique for designing humanoid gaits, inspired from human walking characteristics, in which roughly seventy percent of the required energy during walking is attributed to the exchange of kinetic and potential energies. We test our system by creating an energy-conscious gait for a Hoap2 simulated robot in Webots, and validate that with this gait energy exchange occurs as per our design. Finally, we analyze the energy expenditure for the Hoap2 during walking and compare it to that of human walking.
2020 10th Institute of Electrical and Electronics Engineers International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), 2020
This paper presents a comparison of machine learning classification techniques used to identify n... more This paper presents a comparison of machine learning classification techniques used to identify nine different terrains based on data acquired from force, current, position, and inertial sensors of the NAO humanoid robot. We will be comparing four different classification techniques based on Support Vector Machines, K Nearest Neighbor, Naive Bayes, and Random Forest. Additionally, we will be exploring Manual Feature Reduction, Principle Component Analysis, and Linear Discriminant Analysis to identify which feature reduction method performs better in this application. This paper aims to compare the performance of different classification techniques as well as their performance vis-a-vis different subsets of the available sensors. This will allow us to choose the most suitable technique for our case given the large number of sensors and type of data we collected. At the end, we present the machine learning technique with the best feature reduction method achieving the highest accuracy.
This dataset has data collected from force, current, position, and inertial sensors of the NAO hu... more This dataset has data collected from force, current, position, and inertial sensors of the NAO humanoid robot while walking on Vinyl, Gravel, Wood,Concrete, Artificial grass, and Asphalt without slope and while walking on Vinyl, Gravel and Wood with a slope of 2 degrees.
2021 IEEE 11th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), 2021
In this paper, we propose an algorithm that aims at unifying motion control and bandwidth managem... more In this paper, we propose an algorithm that aims at unifying motion control and bandwidth management schemes via a supervisory monitor that manages a swarm of robots. The main idea of the proposed algorithm is to distribute available bandwidth among the existing communication channels in the network based on various factors representing changes occurring in the swarm and its environment. These factors include Interesting Events (IEs), Quality of Collaboration (QoCollab) between agents, Quality of Control (QoControl), and the Quality of Trajectory Generation (QoTG) of each agent of the swarm. The proposed algorithm is simulated on a fleet of two quadrotors, where the obtained results demonstrate its effectiveness in reducing network bandwidth consumption by approximately 42% as compared to two static algorithms with equal rates and equal bandwidth, while maintaining similar swarm performance.
2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2017
In this paper, an energy-based controller is proposed in the context of humanoid gait design and ... more In this paper, an energy-based controller is proposed in the context of humanoid gait design and humanoid fall avoidance applications. The proposed energy-based controller aims at not only reaching the desired final state but also at tracking a desired reference trajectory with minimal energy expenditure. The controller is validated on two nonlinear systems, an inverted pendulum with a fixed pivot and an inverted pendulum with a moving pivot. The results are benchmarked against a tuned traditional PID controller as well as the controlled Lagrangian approach. The performance improvements in terms of energy efficiency and work expenditure are validated through both simulations and experiments on an actual system. Finally, the novel energy-based control strategy is applied to the fall avoidance problem on a NAO humanoid robot where it was simulated in Webots.
This paper presents a review of minimum energy based humanoid gait design. The use of energy in g... more This paper presents a review of minimum energy based humanoid gait design. The use of energy in gait design is inspired by the theory in human kinesiology stating that human behavior is guided by energy minimization. The different approaches in designing and controlling gait based on energy minimization are explained. The methods are also categorized based on the models used, types of energy monitored, and controller types. The paper presents the energy exchange theory, which to our knowledge has not been implemented in humanoid gait control previously. The importance of this theory is shown in designing a more human-like gait. Preliminary simulation results on the Nao H25 V3.3 in Webots show the limitations of the default gait and the need for implementing the energy exchange theory.
2015 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2015
In this paper we present a model-free system for humanoid push recovery. The concept is inspired ... more In this paper we present a model-free system for humanoid push recovery. The concept is inspired by human proprioceptory sensory input used for detecting balance disturbances. In our implementation, the foot pressure sensors found on a humanoid are used to detect the degree of sway in any direction. This difference is fed to a PID controller which sets the proper ankle torque to be applied in order to keep the humanoid standing in the upright position. This approach imitates the proprioceptive sensor information used by humans which dominates posture assessment. The system is implemented on the NAO H25 V3.3 humanoid in Webots against push disturbances in various directions. The system is also tested on the actual Nao humanoid.
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
In this paper, we consider a problem of foothold selection for the quadrupedal robots equipped wi... more In this paper, we consider a problem of foothold selection for the quadrupedal robots equipped with compliant adaptive feet. Starting from a model of the foot we compute the quality of the potential footholds considering also kinematic constraints and collisions during evaluation. Since terrain assessment and constraints checking are computationally expensive we applied a Convolutional Neural Network (CNN) to evaluate the potential footholds on the elevation map. We propose an efficient strategy for data clustering and segmentation with CNN. The data for training the neural network is collected off-line but the inference works on-line when the robot walks on rough terrains and allows for efficient adaptation to the terrain and exploitation of the properties of the soft adaptive feet.
Background COVID-19 digital contact-tracing apps were created to assist public health authorities... more Background COVID-19 digital contact-tracing apps were created to assist public health authorities in curbing the pandemic. These apps require users’ permission to access specific functions on their mobile phones, such as geolocation, Bluetooth or Wi-Fi connections, or personal data, to work correctly. As these functions have privacy repercussions, it is essential to establish how contact-tracing apps respect users’ privacy. Objective This study aimed to systematically map existing contact-tracing apps and evaluate the permissions required and their privacy policies. Specifically, we evaluated the type of permissions, the privacy policies’ readability, and the information included in them. Methods We used custom Google searches and existing lists of contact-tracing apps to identify potentially eligible apps between May 2020 and November 2021. We included contact-tracing or exposure notification apps with a Google Play webpage from which we extracted app characteristics (eg, sponsor, ...
2016 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET), 2016
In this paper we present an automated sedation system for ICU setting. The system is based on obj... more In this paper we present an automated sedation system for ICU setting. The system is based on objective sedation assessment using the bispectral index and takes into account the patient's hemodynamics i.e. heart rate and blood pressure to ensure that the target sedation level is reached safely. Two different intravenous sedative agents are used (propofol and midazolam) in two separate algorithms for closed loop automated sedation. Different sedation scenarios are simulated in order to mimic this medical process and test for possible complications that the patient might face during the stay in the ICU. The proposed system is adaptable to patient hemodynamic variations and presents an automated process to achieve an optimal target sedation. This system could reduce the patient's ICU length of stay, facilitates the work of the ICU nurses.
This dataset has data collected from force, current, position, and inertial sensors of the NAO hu... more This dataset has data collected from force, current, position, and inertial sensors of the NAO humanoid robot while walking on Vinyl, Gravel, Wood, Concrete, Artificial grass, and Asphalt without a slope and while walking on Vinyl, Gravel, and Wood with a slope of 2 degrees. In total, counting all different axes and components of each sensor, we monitored 27 parameters on-board of the robot. The data was collected while the robot was moving 0.4 meters in the Forward, Backward, Left, and Right directions, and the data collection process was repeated five times for each terrain in each direction. Moreover, the forward and backward iterations had a maximum step size of 0.02 m, step height of 0.01 m and maximum step frequency of 0.005 while the left and right iterations had a maximum step size of 0.12 m, step height of 0.02 m and maximum step frequency of 0.005.
2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2017
This paper proposes a novel technique for designing humanoid gaits, inspired from human walking c... more This paper proposes a novel technique for designing humanoid gaits, inspired from human walking characteristics, in which roughly seventy percent of the required energy during walking is attributed to the exchange of kinetic and potential energies. We test our system by creating an energy-conscious gait for a Hoap2 simulated robot in Webots, and validate that with this gait energy exchange occurs as per our design. Finally, we analyze the energy expenditure for the Hoap2 during walking and compare it to that of human walking.
2020 10th Institute of Electrical and Electronics Engineers International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), 2020
This paper presents a comparison of machine learning classification techniques used to identify n... more This paper presents a comparison of machine learning classification techniques used to identify nine different terrains based on data acquired from force, current, position, and inertial sensors of the NAO humanoid robot. We will be comparing four different classification techniques based on Support Vector Machines, K Nearest Neighbor, Naive Bayes, and Random Forest. Additionally, we will be exploring Manual Feature Reduction, Principle Component Analysis, and Linear Discriminant Analysis to identify which feature reduction method performs better in this application. This paper aims to compare the performance of different classification techniques as well as their performance vis-a-vis different subsets of the available sensors. This will allow us to choose the most suitable technique for our case given the large number of sensors and type of data we collected. At the end, we present the machine learning technique with the best feature reduction method achieving the highest accuracy.
This dataset has data collected from force, current, position, and inertial sensors of the NAO hu... more This dataset has data collected from force, current, position, and inertial sensors of the NAO humanoid robot while walking on Vinyl, Gravel, Wood,Concrete, Artificial grass, and Asphalt without slope and while walking on Vinyl, Gravel and Wood with a slope of 2 degrees.
2021 IEEE 11th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), 2021
In this paper, we propose an algorithm that aims at unifying motion control and bandwidth managem... more In this paper, we propose an algorithm that aims at unifying motion control and bandwidth management schemes via a supervisory monitor that manages a swarm of robots. The main idea of the proposed algorithm is to distribute available bandwidth among the existing communication channels in the network based on various factors representing changes occurring in the swarm and its environment. These factors include Interesting Events (IEs), Quality of Collaboration (QoCollab) between agents, Quality of Control (QoControl), and the Quality of Trajectory Generation (QoTG) of each agent of the swarm. The proposed algorithm is simulated on a fleet of two quadrotors, where the obtained results demonstrate its effectiveness in reducing network bandwidth consumption by approximately 42% as compared to two static algorithms with equal rates and equal bandwidth, while maintaining similar swarm performance.
2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2017
In this paper, an energy-based controller is proposed in the context of humanoid gait design and ... more In this paper, an energy-based controller is proposed in the context of humanoid gait design and humanoid fall avoidance applications. The proposed energy-based controller aims at not only reaching the desired final state but also at tracking a desired reference trajectory with minimal energy expenditure. The controller is validated on two nonlinear systems, an inverted pendulum with a fixed pivot and an inverted pendulum with a moving pivot. The results are benchmarked against a tuned traditional PID controller as well as the controlled Lagrangian approach. The performance improvements in terms of energy efficiency and work expenditure are validated through both simulations and experiments on an actual system. Finally, the novel energy-based control strategy is applied to the fall avoidance problem on a NAO humanoid robot where it was simulated in Webots.
This paper presents a review of minimum energy based humanoid gait design. The use of energy in g... more This paper presents a review of minimum energy based humanoid gait design. The use of energy in gait design is inspired by the theory in human kinesiology stating that human behavior is guided by energy minimization. The different approaches in designing and controlling gait based on energy minimization are explained. The methods are also categorized based on the models used, types of energy monitored, and controller types. The paper presents the energy exchange theory, which to our knowledge has not been implemented in humanoid gait control previously. The importance of this theory is shown in designing a more human-like gait. Preliminary simulation results on the Nao H25 V3.3 in Webots show the limitations of the default gait and the need for implementing the energy exchange theory.
2015 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2015
In this paper we present a model-free system for humanoid push recovery. The concept is inspired ... more In this paper we present a model-free system for humanoid push recovery. The concept is inspired by human proprioceptory sensory input used for detecting balance disturbances. In our implementation, the foot pressure sensors found on a humanoid are used to detect the degree of sway in any direction. This difference is fed to a PID controller which sets the proper ankle torque to be applied in order to keep the humanoid standing in the upright position. This approach imitates the proprioceptive sensor information used by humans which dominates posture assessment. The system is implemented on the NAO H25 V3.3 humanoid in Webots against push disturbances in various directions. The system is also tested on the actual Nao humanoid.
Uploads
Papers by Noel Maalouf