Below is a list of all relevant publications authored by Robotics Forum members.
- Showing results for:
- Reset all filters
Conference paperWang R, Ciliberto C, Amadori P, et al., 2019,
Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation, Thirty-sixth International Conference on Machine Learning, Publisher: Proceedings of International Conference on Machine Learning (ICML-2019)
We consider the problem of imitation learning from a finite set of experttrajectories, without access to reinforcement signals. The classical approachof extracting the expert's reward function via inverse reinforcement learning,followed by reinforcement learning is indirect and may be computationallyexpensive. Recent generative adversarial methods based on matching the policydistribution between the expert and the agent could be unstable duringtraining. We propose a new framework for imitation learning by estimating thesupport of the expert policy to compute a fixed reward function, which allowsus to re-frame imitation learning within the standard reinforcement learningsetting. We demonstrate the efficacy of our reward function on both discreteand continuous domains, achieving comparable or better performance than thestate of the art under different reinforcement learning algorithms.
Conference paperPatel N, Kogkas A, Ben Glover AD, et al., 2019,
EYE GAZE-CONTROLLED ROBOTIC FLEXIBLE ENDOSCOPY: A FEASIBILITY STUDY, Annual Meeting of the British-Society-of-Gastroenterology (BSG), Publisher: BMJ PUBLISHING GROUP, Pages: A38-A39, ISSN: 0017-5749
- Author Web Link
- Citations: 2
Conference paperClark AB, Rojas N, 2019,
Stiffness-tuneable limb segment with flexible spine for malleable robots, 2019 International Conference on Robotics and Automation (ICRA), Publisher: IEEE, Pages: 3969-3975, ISSN: 2577-087X
Robotic arms built from stiffness-adjustable, con-tinuously bending segments serially connected with revolutejoints have the ability to change their mechanical architectureand workspace, thus allowing high flexibility and adaptation todifferent tasks with less than six degrees of freedom, a conceptthat we call malleable robots. Known stiffening mechanismsmay be used to implement suitable links for these novel roboticmanipulators; however, these solutions usually show a reducedperformance when bending due to structural deformation. Byincluding an inner support structure this deformation can beminimised, resulting in an increased stiffening performance.This paper presents a new multi-material spine-inspired flexiblestructure for providing support in stiffness-controllable layer-jamming-based robotic links of large diameter. The proposedspine mechanism is highly movable with type and range ofmotions that match those of a robotic link using solely layerjamming, whilst maintaining a hollow and light structure. Themechanics and design of the flexible spine are explored, anda prototype of a link utilising it is developed and comparedwith limb segments based on granular jamming and layerjamming without support structure. Results of experimentsverify the advantages of the proposed design, demonstratingthat it maintains a constant central diameter across bendingangles and presents an improvement of more than 203% ofresisting force at 180°.
Journal articleCully A, Demiris Y, 2019,
Online knowledge level tracking with data-driven student models and collaborative filtering, IEEE Transactions on Knowledge and Data Engineering, Vol: 32, Pages: 2000-2013, ISSN: 1041-4347
Intelligent Tutoring Systems are promising tools for delivering optimal and personalised learning experiences to students. A key component for their personalisation is the student model, which infers the knowledge level of the students to balance the difficulty of the exercises. While important advances have been achieved, several challenges remain. In particular, the models should be able to track in real-time the evolution of the students' knowledge levels. These evolutions are likely to follow different profiles for each student, while measuring the exact knowledge level remains difficult given the limited and noisy information provided by the interactions. This paper introduces a novel model that addresses these challenges with three contributions: 1) the model relies on Gaussian Processes to track online the evolution of the student's knowledge level over time, 2) it uses collaborative filtering to rapidly provide long-term predictions by leveraging the information from previous users, and 3) it automatically generates abstract representations of knowledge components via automatic relevance determination of covariance matrices. The model is evaluated on three datasets, including real users. The results demonstrate that the model converges to accurate predictions in average 4 times faster than the compared methods.
Conference paperMatheson E, Watts T, Secoli R, et al., 2019,
Cyclic motion control for programmable bevel-tip needles 3D steering: a simulation study, ROBIO - IEEE International Conference on Robotics and Biomimetics, Publisher: IEEE
Flexible, steerable, soft needles are desirable inMinimally Invasive Surgery to achieve complex trajectorieswhile maintaining the benefits of percutaneous interventioncompared to open surgery. One such needle is the multi-segmentProgrammable Bevel-tip Needle (PBN), which is inspired by themechanical design of the ovipositor of certain wasps. PBNscan steer in 3D whilst minimizing the force applied to thesurrounding substrate, due to the cyclic motion of the segments.Taking inspiration also from the control strategy of the wasp toperform insertions and lay their eggs, this paper presents thedesign of a cyclic controller that can steer a PBN to produce adesired trajectory in 3D. The performance of the controller isdemonstrated in simulation in comparison to that of a directcontroller without cyclic motion. It is shown that, while thesame steering curvatures can be attained by both controllers,the time taken to achieve the configuration is longer for thecyclic controller, leading to issues of potential under-steeringand longer insertion times.
Journal articleBaron N, Philippides A, Rojas N, 2019,
A novel kinematically redundant planar parallel robot manipulator with full rotatability, Journal of Mechanisms and Robotics, Vol: 11, Pages: 011008-011008, ISSN: 1942-4302
This paper presents a novel kinematically redundant planar parallel robot manipulator, which has full rotatability. The proposed robot manipulator has an architecture that corresponds to a fundamental truss, meaning that it does not contain internal rigid structures when the actuators are locked. This also implies that its rigidity is not inherited from more general architectures or resulting from the combination of other fundamental structures. The introduced topology is a departure from the standard 3-RPR (or 3-RRR) mechanism on which most kinematically redundant planar parallel robot manipulators are based. The robot manipulator consists of a moving platform that is connected to the base via two RRR legs and connected to a ternary link, which is joined to the base by a passive revolute joint, via two other RRR legs. The resulting robot mechanism is kinematically redundant, being able to avoid the production of singularities and having unlimited rotational capability. The inverse and forward kinematics analyses of this novel robot manipulator are derived using distance-based techniques, and the singularity analysis is performed using a geometric method based on the properties of instantaneous centers of rotation. An example robot mechanism is analyzed numerically and physically tested; and a test trajectory where the end effector completes a full cycle rotation is reported. A link to an online video recording of such a capability, along with the avoidance of singularities and a potential application, is also provided.
Journal articleKormushev P, Ugurlu B, Caldwell DG, et al., 2019,
Learning to exploit passive compliance for energy-efficient gait generation on a compliant humanoid, Autonomous Robots, Vol: 43, Pages: 79-95, ISSN: 0929-5593
Modern humanoid robots include not only active compliance but also passive compliance. Apart from improved safety and dependability, availability of passive elements, such as springs, opens up new possibilities for improving the energy efficiency. With this in mind, this paper addresses the challenging open problem of exploiting the passive compliance for the purpose of energy efficient humanoid walking. To this end, we develop a method comprising two parts: an optimization part that finds an optimal vertical center-of-mass trajectory, and a walking pattern generator part that uses this trajectory to produce a dynamically-balanced gait. For the optimization part, we propose a reinforcement learning approach that dynamically evolves the policy parametrization during the learning process. By gradually increasing the representational power of the policy parametrization, it manages to find better policies in a faster and computationally efficient way. For the walking generator part, we develop a variable-center-of-mass-height ZMP-based bipedal walking pattern generator. The method is tested in real-world experiments with the bipedal robot COMAN and achieves a significant 18% reduction in the electric energy consumption by learning to efficiently use the passive compliance of the robot.
Conference paperBai G, Rojas N, 2019,
Self-adaptive monolithic anthropomorphic finger with teeth-guided compliant cross-four-bar joints for underactuated hands, 2018 IEEE-RAS International Conference on Humanoid Robots (Humanoids), Publisher: IEEE
This paper presents a novel approach for modelingone-degree-of-freedom human metacarpophalangeal/ interpha-langeal joints based on a teeth-guided compliant cross-four-barlinkage. The proposed model allows developing self-adaptiveanthropomorphic fingers able to be 3D printed in a singlestep without any accessories, except for simple tendon wiringafter the printing process, using basic single-material additivemanufacturing. Teeth-guided compliant cross-four-bar linkagesas finger joints not only provide monolithic fabrication withoutassembly but also increase precision of anthropomorphic robotfingers by removing nonlinear characteristics, thus reducing thecomplexity of control for delicate grasping. Kinematic analysisof the proposed compliant finger joints is detailed and nonlinearfinite element analysis results demonstrating their advantagesare reported. A two-fingered underactuated hand with teeth-guided compliant cross-four-bar joints is also developed andqualitative discussion on grasping is conducted.
Conference paperWang M-Y, Kogkas AA, Darzi A, et al., 2019,
Free-view, 3D gaze-guided, assistive robotic system for activities of daily living, 25th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, Pages: 2355-2361, ISSN: 2153-0858
Patients suffering from quadriplegia have limited body motion which prevents them from performing daily activities. We have developed an assistive robotic system with an intuitive free-view gaze interface. The user's point of regard is estimated in 3D space while allowing free head movement and is combined with object recognition and trajectory planning. This framework allows the user to interact with objects using fixations. Two operational modes have been implemented to cater for different eventualities. The automatic mode performs a pre-defined task associated with a gaze-selected object, while the manual mode allows gaze control of the robot's end-effector position on the user's frame of reference. User studies reported effortless operation in automatic mode. A manual pick and place task achieved a success rate of 100% on the users' first attempt.
Conference paperVrielink TJCO, Puyal JG-B, Kogkas A, et al., 2019,
Intuitive gaze-control of a robotized flexible endoscope, 25th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, Pages: 1776-1782, ISSN: 2153-0858
Flexible endoscopy is a routinely performed procedure that has predominantly remained unchanged for decades despite its many challenges. This paper introduces a novel, more intuitive and ergonomic platform that can be used with any flexible endoscope, allowing easier navigation and manipulation. A standard endoscope is robotized and a gaze control system based on eye-tracking is developed and implemented, allowing hands-free manipulation. The system characteristics and step response has been evaluated using visual servoing. Further, the robotized system has been compared with a manually controlled endoscope during a user study. The users (n=11) showed a preference for the gaze controlled endoscope and a lower task load when the task was performed with the gaze control. In addition, gaze control was related to a higher success rate and a lower time to perform the task. The results presented validate the system's technical performance and demonstrate the intuitiveness of hands-free gaze control in flexible endoscopy.
Conference paperZolotas M, Elsdon J, Demiris Y, 2019,
Head-mounted augmented reality for explainable robotic wheelchair assistance, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, ISSN: 2153-0866
Robotic wheelchairs with built-in assistive fea-tures, such as shared control, are an emerging means ofproviding independent mobility to severely disabled individuals.However, patients often struggle to build a mental model oftheir wheelchair’s behaviour under different environmentalconditions. Motivated by the desire to help users bridge thisgap in perception, we propose a novel augmented realitysystem using a Microsoft Hololens as a head-mounted aid forwheelchair navigation. The system displays visual feedback tothe wearer as a way of explaining the underlying dynamicsof the wheelchair’s shared controller and its predicted futurestates. To investigate the influence of different interface designoptions, a pilot study was also conducted. We evaluated theacceptance rate and learning curve of an immersive wheelchairtraining regime, revealing preliminary insights into the potentialbeneficial and adverse nature of different augmented realitycues for assistive navigation. In particular, we demonstrate thatcare should be taken in the presentation of information, witheffort-reducing cues for augmented information acquisition (forexample, a rear-view display) being the most appreciated.
Conference paperWang R, Amadori P, Demiris Y, 2019,
Real-time workload classification during driving using hyperNetworks, International Conference on Intelligent Robots and Systems (IROS 2018), Publisher: IEEE, ISSN: 2153-0866
Classifying human cognitive states from behavioral and physiological signals is a challenging problem with important applications in robotics. The problem is challenging due to the data variability among individual users, and sensor artifacts. In this work, we propose an end-to-end framework for real-time cognitive workload classification with mixture Hyper Long Short Term Memory Networks (m-HyperLSTM), a novelvariant of HyperNetworks. Evaluating the proposed approach on an eye-gaze pattern dataset collected from simulated driving scenarios of different cognitive demands, we show that the proposed framework outperforms previous baseline methods and achieves 83.9% precision and 87.8% recall during test. We also demonstrate the merit of our proposed architecture by showing improved performance over other LSTM-basedmethods
Book chapterKogkas A, Ezzat A, Thakkar R, et al., 2019,
Free-View, 3D Gaze-Guided Robotic Scrub Nurse, Editors: Shen, Liu, Peters, Staib, Essert, Zhou, Yap, Khan, Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 164-172, ISBN: 978-3-030-32253-3
- Author Web Link
- Citations: 2
Book chapterDi Veroli C, Le CA, Lemaire T, et al., 2019,
LibRob: An autonomous assistive librarian, Pages: 15-26, ISBN: 9783030253318
This study explores how new robotic systems can help library users efficiently locate the book they require. A survey conducted among Imperial College students has shown an absence of a time-efficient and organised method to find the books they are looking for in the college library. The solution implemented, LibRob, is an automated assistive robot that gives guidance to the users in finding the book they are searching for in an interactive manner to deliver a more satisfactory experience. LibRob is able to process a search request either by speech or by text and return a list of relevant books by author, subject or title. Once the user selects the book of interest, LibRob guides them to the shelf containing the book, then returns to its base station on completion. Experimental results demonstrate that the robot reduces the time necessary to find a book by 47.4%, and left 80% of the users satisfied with their experience, proving that human-robot interactions can greatly improve the efficiency of basic activities within a library environment.
Conference paperZhao M, Oude Vrielink J, Kogkas A, et al., 2019,
Prototype Designs of a Cable-driven Parallel Robot for Transoral Laser Surgery, Hamlyn Symposium on Medical Robotics
Journal articleDebrunner T, Saeedi Gharahbolagh S, Kelly P, 2019,
AUKE: Automatic Kernel Code Generation for an analogue SIMD Focal-plane Sensor-Processor Array, ACM Transactions on Architecture and Code Optimization, Vol: 15, ISSN: 1544-3973
Focal-plane Sensor-Processor Arrays (FPSPs) are new imaging devices with parallel Single Instruction Multiple Data (SIMD) computational capabilities built into every pixel. Compared to traditional imaging devices, FPSPs allow for massive pixel-parallel execution of image processing algorithms. This enables the application of certain algorithms at extreme frame rates (>10,000 frames per second). By performing some early-stage processing in-situ, systems incorporating FPSPs can consume less power compared to conventional approaches using standard digital cameras. In this article, we explore code generation for an FPSP whose 256 × 256 processors operate on analogue signal data, leading to further opportunities for power reduction—and additional code synthesis challenges.While rudimentary image processing algorithms have been demonstrated on FPSPs before, progress with higher-level computer vision algorithms has been sparse due to the unique architecture and limits of the devices. This article presents a code generator for convolution filters for the SCAMP-5 FPSP, with applications in many high-level tasks such as convolutional neural networks, pose estimation, and so on. The SCAMP-5 FPSP has no effective multiply operator. Convolutions have to be implemented through sequences of more primitive operations such as additions, subtractions, and multiplications/divisions by two. We present a code generation algorithm to optimise convolutions by identifying common factors in the different weights and by determining an optimised pattern of pixel-to-pixel data movements to exploit them. We present evaluation in terms of both speed and energy consumption for a suite of well-known convolution filters. Furthermore, an application of the method is shown by the implementation of a Viola-Jones face detection algorithm.
Conference paperChoi J, Chang HJ, Fischer T, et al., 2018,
Context-aware deep feature compression for high-speed visual tracking, IEEE Conference on Computer Vision and Pattern Recognition, Publisher: Institute of Electrical and Electronics Engineers, Pages: 479-488, ISSN: 1063-6919
We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in the proposed deep feature compression that is achieved by a context-aware scheme utilizing multiple expert auto-encoders; a context in our framework refers to the coarse category of the tracking target according to appearance patterns. In the pre-training phase, one expert auto-encoder is trained per category. In the tracking phase, the best expert auto-encoder is selected for a given target, and only this auto-encoder is used. To achieve high tracking performance with the compressed feature map, we introduce extrinsic denoising processes and a new orthogonality loss term for pre-training and fine-tuning of the expert auto-encoders. We validate the proposed context-aware framework through a number of experiments, where our method achieves a comparable performance to state-of-the-art trackers which cannot run in real-time, while running at a significantly fast speed of over 100 fps.
Journal articleMoulin-Frier C, Fischer T, Petit M, et al., 2018,
DAC-h3: A Proactive Robot Cognitive Architecture to Acquire and Express Knowledge About the World and the Self, IEEE Transactions on Cognitive and Developmental Systems, Vol: 10, Pages: 1005-1022, ISSN: 2379-8920
This paper introduces a cognitive architecture for a humanoid robot to engage in a proactive, mixed-initiative exploration and manipulation of its environment, where the initiative can originate from both the human and the robot. The framework, based on a biologically-grounded theory of the brain and mind, integrates a reactive interaction engine, a number of state-of-the art perceptual and motor learning algorithms, as well as planning abilities and an autobiographical memory. The architecture as a whole drives the robot behavior to solve the symbol grounding problem, acquire language capabilities, execute goal-oriented behavior, and express a verbal narrative of its own experience in the world. We validate our approach in human-robot interaction experiments with the iCub humanoid robot, showing that the proposed cognitive architecture can be applied in real time within a realistic scenario and that it can be used with naive users.
Journal articleChang HJ, Fischer T, Petit M, et al., 2018,
Learning kinematic structure correspondences using multi-order similarities, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol: 40, Pages: 2920-2934, ISSN: 0162-8828
We present a novel framework for finding the kinematic structure correspondences between two articulated objects in videos via hypergraph matching. In contrast to appearance and graph alignment based matching methods, which have been applied among two similar static images, the proposed method finds correspondences between two dynamic kinematic structures of heterogeneous objects in videos. Thus our method allows matching the structure of objects which have similar topologies or motions, or a combination of the two. Our main contributions are summarised as follows: (i)casting the kinematic structure correspondence problem into a hypergraph matching problem by incorporating multi-order similarities with normalising weights, (ii)introducing a structural topology similarity measure by aggregating topology constrained subgraph isomorphisms, (iii)measuring kinematic correlations between pairwise nodes, and (iv)proposing a combinatorial local motion similarity measure using geodesic distance on the Riemannian manifold. We demonstrate the robustness and accuracy of our method through a number of experiments on synthetic and real data, showing that various other recent and state of the art methods are outperformed. Our method is not limited to a specific application nor sensor, and can be used as building block in applications such as action recognition, human motion retargeting to robots, and articulated object manipulation.
Conference paperWang K, Shah A, Kormushev P, 2018,
SLIDER: A Bipedal Robot with Knee-less Legs and Vertical Hip Sliding Motion, 21st International Conference on Climbing and Walking Robots and Support Technologies for Mobile Machines (CLAWAR 2018)
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.