Angela Faragasso
King's College London, Informatics, Department Member
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Deep learning object detectors achieve state-of-the-art accuracy at the expense of high computational overheads, impeding their utilization on embedded systems such as drones. A primary source of these overheads is the exhaustive... more
Deep learning object detectors achieve state-of-the-art accuracy at the expense of high computational overheads, impeding their utilization on embedded systems such as drones. A primary source of these overheads is the exhaustive classification of typically 10^4-10^5 regions per image. Given that most of these regions contain uninformative background, the detector designs seem extremely superfluous and inefficient. In contrast, biological vision systems leverage selective attention for fast and efficient object detection. Recent neuroscientific findings shedding new light on the mechanism behind selective attention allowed us to formulate a new hypothesis of object detection efficiency and subsequently introduce a new object detection paradigm. To that end, we leverage this knowledge to design a novel region proposal network and empirically show that it achieves high object detection performance on the COCO dataset. Moreover, the model uses two to three orders of magnitude fewer com...
Research Interests:
This paper presents the developments achieved via the Social Cooperation Program “Intelligent Construction System,” from three primary perspectives: environmental measurements, improvements in remote operability, and improvements in... more
This paper presents the developments achieved via the Social Cooperation Program “Intelligent Construction System,” from three primary perspectives: environmental measurements, improvements in remote operability, and improvements in efficiency and automation of remote operation. For improvements in remote operation, environmental measurements of the disaster sites are critical. Therefore, a method to integrate the data from drones and ground-based vehicles in order to generate 3D maps was proposed. Another method for estimating the changes in soil volumes through a 3D map based on drone data was also proposed. Finally, to estimate the trafficability in disaster sites, a cone index-based method employing spectral images was proposed. Improving remote operability is essential to facilitate improved working conditions for operators. Considering this, a method providing human operators with a bird’s-eye view of remotely operated machinery from any perspective was proposed. Additionally,...
Research Interests:
This chapter proposes an alternative actuation principle that investigates the capability of variable stiffness of a continuum silicon-based manipulator which was primarily developed for Minimally Invasive Surgery (MIS). Inspired by... more
This chapter proposes an alternative actuation principle that investigates the capability of variable stiffness of a continuum silicon-based manipulator which was primarily developed for Minimally Invasive Surgery (MIS). Inspired by biological muscular composition, we have designed a hybrid actuation mechanism that can be alternatively used for STIFF-FLOP manipulator. The current soft robot is actuated by pneumatic pressure, in addition to incorporating tendons’ tension, which are placed within the soft robot’s body. Experiments are conducted by exerting an externally applied force in different poses, and simultaneously varying the stiffness via the tendons. Test results are demonstrated, and it is observed that dual antagonistic actuation, with the benefit of higher force capacities, could indeed promise enhancing soft robotics morphological features.
This paper deals with the problem of controlling a ball–dribbling robotic system. In particular, a novel hybrid controller which combines elements of passivity and iterative learning control theories has been developed. Numerical... more
This paper deals with the problem of controlling a ball–dribbling robotic system. In particular, a novel hybrid controller which combines elements of passivity and iterative learning control theories has been developed. Numerical simulations have been performed to prove the validity of the proposed solution. Results confirmed the effectiveness of the developed methodology.
Search robotics involves the use of autonomous systems which have to operate in unknown environments and interact with external objects or humans. Typically, these robots are equipped with sensors which are used to perceive the... more
Search robotics involves the use of autonomous systems which have to operate in unknown environments and interact with external objects or humans. Typically, these robots are equipped with sensors which are used to perceive the surrounding scenario and feed it back to the human operator. Besides the extensive research effort, a sensory system able to reproduce the human “sense of touch” is still missing and highly desirable. In this paper we propose a vision-based touch sensor mechanism for autonomous robots with the aim of improving robot's navigation in unsettled environments. Furthermore, we explore a new application area and describe how the sensory system can be embedded to a surveillance robot and used to perform human pat-down search.
Research Interests:
This paper deals with the problem of controlling a ball–dribbling robotic system. In particular, a novel hybrid controller which combines elements of passivity and iterative learning control theories has been developed. Numerical... more
This paper deals with the problem of controlling a ball–dribbling robotic system. In particular, a novel hybrid controller which combines elements of passivity and iterative learning control theories has been developed. Numerical simulations have been performed to prove the validity of the proposed solution. Results confirmed the effectiveness of the developed methodology.
This paper proposes an innovative identification scheme to estimate parameters constituting linear relations in time–invariant systems: the bounding box recursive Frisch scheme. A novel recursive version of the Frisch scheme, a linear... more
This paper proposes an innovative identification scheme to estimate parameters constituting linear relations in time–invariant systems: the bounding box recursive Frisch scheme. A novel recursive version of the Frisch scheme, a linear estimator characterised by mild prior assumptions in the error-in-variables (EIV) framework, has been derived. The fast computational time and convergence in the identification of linear systems are the most relevant feature of this recursive version of the scheme. The performance of the developed algorithm has been evaluated trough numerical simulations. Results proved the effectiveness and accuracy of the proposed solution.
In this paper, we propose a novel camera orientation estimation method based on the computation of the vanishing point of water drops in leaking indoor environment. Camera orientation estimation is an important component of robots as it... more
In this paper, we propose a novel camera orientation estimation method based on the computation of the vanishing point of water drops in leaking indoor environment. Camera orientation estimation is an important component of robots as it allows them to perform complex tasks such as three-dimensional (3D) reconstruction of different environments. Camera estimation usually involves sensors, such as cameras or encoders and sophisticated processing algorithms. In recent years, computer vision techniques have been widely used to estimate the camera orientation in robotics-related research as visual sensing can improve the autonomy of the systems. Although most of these methods perform well in outdoor environments, they are problematic in the environments of indoor disasters, where common visual features may be missing due to collapse and erosion. To solve these problems, we developed a novel technique that employs particular characteristics of leaking indoor environment. Our method uses t...
Research Interests:
Using pliable materials for the construction of robot bodies presents new and interesting challenges for the robotics community. Within the EU project entitled STIFFness controllable Flexible & Learnable manipulator for surgical... more
Using pliable materials for the construction of robot bodies presents new and interesting challenges for the robotics community. Within the EU project entitled STIFFness controllable Flexible & Learnable manipulator for surgical Operations (STIFF-FLOP), a bendable, segmented robot arm has been developed. The exterior of the arm is composed of a soft material (silicone), encasing an internal structure that contains air-chamber actuators and a variety of sensors for monitoring applied force, position and shape of the arm as it bends. Due to the physical characteristics of the arm, a proper model of robot kinematics and dynamics is difficult to infer from the sensor data. Here we propose a non-linear approach to predicting the robot arm posture, by training a feed-forward neural network with a structured series of pressures values applied to the arm's actuators. The model is developed across a set of seven different experiments. Because the STIFF-FLOP arm is intended for use in sur...
Research Interests:
Using pliable materials for the construction of robot bodies presents new and interesting challenges for the robotics community. Within the EU project entitled STIFFness controllable Flexible & Learnable manipulator for surgical... more
Using pliable materials for the construction of robot bodies presents new and interesting challenges for the robotics community. Within the EU project entitled STIFFness controllable Flexible & Learnable manipulator for surgical Operations (STIFF-FLOP), a bendable, segmented robot arm has been developed. The exterior of the arm is composed of a soft material (silicone), encasing an internal structure that contains air-chamber actuators and a variety of sensors for monitoring applied force, position and shape of the arm as it bends. Due to the physical characteristics of the arm, a proper model of robot kinematics and dynamics is difficult to infer from the sensor data. Here we propose a non-linear approach to predicting the robot arm posture, by training a feed-forward neural network with a structured series of pressures values applied to the arm's actuators. The model is developed across a set of seven different experiments. Because the STIFF-FLOP arm is intended for use in sur...
Research Interests:
Autonomous mobile robots have been widely employed for many applications in indoor and outdoor environments. Most of these robots have to operate in environments where human intervention is expensive, slow, unreliable or even impossible.... more
Autonomous mobile robots have been widely employed for many applications in indoor and outdoor environments. Most of these robots have to operate in environments where human intervention is expensive, slow, unreliable or even impossible. It is therefore essential for robots to monitor their behavior to diagnose and address faults before they result in catastrophic failures. In this paper we introduce a new approach to diagnose faults of autonomous mobile robot systems. The proposed methodology firstly computes the poses of the robot by using the onboard stereo camera, the wheels' encoders and the commanded velocities, respectively. Then, the residuals between each pair of the localization methods are used to evaluate the occurrence of faults. Experimental tests, in ideal fault free cases, have been carried out to find a reference threshold for each residual. A bool value is assigned to each residual by comparing it with the respective threshold. The bool values of all residuals ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
This paper presents a novel three-axis force sensor based on optical photo interrupters and integrated with the robot arm STIFF-FLOP (STIFFness controllable Flexible and Learnable Manipulator for Surgical Operations) to measure external... more
This paper presents a novel three-axis force sensor based on optical photo interrupters and integrated with the robot arm STIFF-FLOP (STIFFness controllable Flexible and Learnable Manipulator for Surgical Operations) to measure external interacting forces and torques. The ring-shape bio-compatible sensor presented here embeds the distributed actuation and sensing system of the STIFF-FLOP manipulator and is applicable to the geometry of its structure as well to the structure of any other similar soft robotic manipulator. Design and calibration procedures of the device are introduced: experimental results allow defining a stiffness sensor matrix for real-time estimation of force and torque components and confirm the usefulness of the proposed optical sensing approach.
Research Interests:
Research Interests:
Research Interests:
This paper explores a novel stiffness sensor which is mounted on the tip of a laparoscopic camera. The proposed device is able to compute stiffness when interacting with soft surfaces. The sensor can be used in Minimally Invasive Surgery,... more
This paper explores a novel stiffness sensor which is mounted on the tip of a laparoscopic camera. The proposed device is able to compute stiffness when interacting with soft surfaces. The sensor can be used in Minimally Invasive Surgery, for instance, to localise tumor tissue which commonly has a higher stiffness when compared to healthy tissue. The purely mechanical sensor structure utilizes the functionality of an endoscopic camera to the maximum by visually analyzing the behavior of trackers within the field of view. Two pairs of spheres (used as easily identifiable features in the camera images) are connected to two springs with known but different spring constants. Four individual indenters attached to the spheres are used to palpate the surface. During palpation, the spheres move linearly towards the objective lens (i.e. the distance between lens and spheres is changing) resulting in variations of their diameters in the camera images. Relating the measured diameters to the di...
Research Interests:
Research Interests:
This paper presents new findings concerning a hand-held stiffness probe for the medical diagnosis of abnormalities during palpation of soft-tissue. Palpation is recognized by the medical community as an essential and low-cost method to... more
This paper presents new findings concerning a hand-held stiffness probe for the medical diagnosis of abnormalities during palpation of soft-tissue. Palpation is recognized by the medical community as an essential and low-cost method to detect and diagnose disease in soft-tissue. However, differences are often subtle and clinicians need to train for many years before they can conduct a reliable diagnosis. The probe presented here fills this gap providing a means to easily obtain stiffness values of soft tissue during a palpation procedure. Our stiffness sensor is equipped with a multi degree of freedom (DoF) Aurora magnetic tracker, allowing us to track and record the 3D position of the probe whilst examining a tissue area, and generate a 3D stiffness map in real-time. The stiffness probe was integrated in a robotic arm and tested in an artificial environment representing a good model of soft tissue organs; the results show that the sensor can accurately measure and map the stiffness...