arXiv subjects

A. Aldo Faisal

Publications and source records attributed to A. Aldo Faisal.

42 records · Page 3Linked to original sources

arXiv2019

Gaze-based, Context-aware Robotic System for Assisted Reaching and Grasping

Assistive robotic systems endeavour to support those with movement disabilities, enabling them to move again and regain functionality. Main issue with these systems is the complexity of their low-level control, and how to translate this to simpler, higher level commands that are easy and intuitive for a human user to interact with. We have created a multi-modal system, consisting of different sensing, decision making and actuating modalities, leading to intuitive, human-in-the-loop assistive robotics. The system takes its cue from the user's gaze, to decode their intentions and implement low-level motion actions to achieve high-level tasks. This results in the user simply having to look at the objects of interest, for the robotic system to assist them in reaching for those objects, grasping them, and using them to interact with other objects. We present our method for 3D gaze estimation, and grammars-based implementation of sequences of action with the robotic system. The 3D gaze estimation is evaluated with 8 subjects, showing an overall accuracy of $4.68\pm0.14cm$. The full system is tested with 5 subjects, showing successful implementation of $100\%$ of reach to gaze point actions and full implementation of pick and place tasks in 96\%, and pick and pour tasks in $76\%$ of cases. Finally we present a discussion on our results and what future work is needed to improve the system.

cs.RO↗

arXiv2019

Understanding the Artificial Intelligence Clinician and optimal treatment strategies for sepsis in intensive care

In this document, we explore in more detail our published work (Komorowski, Celi, Badawi, Gordon, & Faisal, 2018) for the benefit of the AI in Healthcare research community. In the above paper, we developed the AI Clinician system, which demonstrated how reinforcement learning could be used to make useful recommendations towards optimal treatment decisions from intensive care data. Since publication a number of authors have reviewed our work (e.g. Abbasi, 2018; Bos, Azoulay, & Martin-Loeches, 2019; Saria, 2018). Given the difference of our framework to previous work, the fact that we are bridging two very different academic communities (intensive care and machine learning) and that our work has impact on a number of other areas with more traditional computer-based approaches (biosignal processing and control, biomedical engineering), we are providing here additional details on our recent publication.

cs.AI↗

arXiv2018

The Supernumerary Robotic 3rd Thumb for Skilled Music Tasks

Wearable robotics bring the opportunity to augment human capability and performance, be it through prosthetics, exoskeletons, or supernumerary robotic limbs. The latter concept allows enhancing human performance and assisting them in daily tasks. An important research question is, however, whether the use of such devices can lead to their eventual cognitive embodiment, allowing the user to adapt to them and use them seamlessly as any other limb of their own. This paper describes the creation of a platform to investigate this. Our supernumerary robotic 3rd thumb was created to augment piano playing, allowing a pianist to press piano keys beyond their natural hand-span; thus leading to functional augmentation of their skills and the technical feasibility to play with 11 fingers. The robotic finger employs sensors, motors, and a human interfacing algorithm to control its movement in real-time. A proof of concept validation experiment has been conducted to show the effectiveness of the robotic finger in playing musical pieces on a grand piano, showing that naive users were able to use it for 11 finger play within a few hours.

cs.RO↗

arXiv2018

Mechanomyography based closed-loop Functional Electrical Stimulation cycling system

Functional Electrical Stimulation (FES) systems are successful in restoring motor function and supporting paralyzed users. Commercially available FES products are open loop, meaning that the system is unable to adapt to changing conditions with the user and their muscles which results in muscle fatigue and poor stimulation protocols. This is because it is difficult to close the loop between stimulation and monitoring of muscle contraction using adaptive stimulation. FES causes electrical artefacts which make it challenging to monitor muscle contractions with traditional methods such as electromyography (EMG). We look to overcome this limitation by combining FES with novel mechanomyographic (MMG) sensors to be able to monitor muscle activity during stimulation in real time. To provide a meaningful task we built an FES cycling rig with a software interface that enabled us to perform adaptive recording and stimulation, and then combine this with sensors to record forces applied to the pedals using force sensitive resistors (FSRs), crank angle position using a magnetic incremental encoder and inputs from the user using switches and a potentiometer. We illustrated this with a closed-loop stimulation algorithm that used the inputs from the sensors to control the output of a programmable RehaStim 1 FES stimulator (Hasomed) in real-time. This recumbent bicycle rig was used as a testing platform for FES cycling. The algorithm was designed to respond to a change in requested speed (RPM) from the user and change the stimulation power (% of maximum current mA) until this speed was achieved and then maintain it.

cs.RO↗

arXiv2018

FastOrient: Lightweight Computer Vision for Wrist Control in Assistive Robotic Grasping

Wearable and Assistive robotics for human grasp support are broadly either tele-operated robotic arms or act through orthotic control of a paralyzed user's hand. Such devices require correct orientation for successful and efficient grasping. In many human-robot assistive settings, the end-user is required to explicitly control the many degrees of freedom making effective or efficient control problematic. Here we are demonstrating the off-loading of low-level control of assistive robotics and active orthotics, through automatic end-effector orientation control for grasping. This paper describes a compact algorithm implementing fast computer vision techniques to obtain the orientation of the target object to be grasped, by segmenting the images acquired with a camera positioned on top of the end-effector of the robotic device. The rotation needed that optimises grasping is directly computed from the object's orientation. The algorithm has been evaluated in 6 different scene backgrounds and end-effector approaches to 26 different objects. 94.8% of the objects were detected in all backgrounds. Grasping of the object was achieved in 91.1% of the cases and has been evaluated with a robot simulator confirming the performance of the algorithm.

cs.RO↗

arXiv2018

Generalised Structural CNNs (SCNNs) for time series data with arbitrary graph topology

Deep Learning methods, specifically convolutional neural networks (CNNs), have seen a lot of success in the domain of image-based data, where the data offers a clearly structured topology in the regular lattice of pixels. This 4-neighbourhood topological simplicity makes the application of convolutional masks straightforward for time series data, such as video applications, but many high-dimensional time series data are not organised in regular lattices, and instead values may have adjacency relationships with non-trivial topologies, such as small-world networks or trees. In our application case, human kinematics, it is currently unclear how to generalise convolutional kernels in a principled manner. Therefore we define and implement here a framework for general graph-structured CNNs for time series analysis. Our algorithm automatically builds convolutional layers using the specified adjacency matrix of the data dimensions and convolutional masks that scale with the hop distance. In the limit of a lattice-topology our method produces the well-known image convolutional masks. We test our method first on synthetic data of arbitrarily-connected graphs and human hand motion capture data, where the hand is represented by a tree capturing the mechanical dependencies of the joints. We are able to demonstrate, amongst other things, that inclusion of the graph structure of the data dimensions improves model prediction significantly, when compared against a benchmark CNN model with only time convolution layers.

stat.ML↗