Below is a list of all relevant publications authored by Robotics Forum members.

Search or filter publications

Filter by type:

Filter by publication type

Filter by year:

to

Results

  • Showing results for:
  • Reset all filters

Search results

  • Journal article
    Tsai Y-Y, Xiao B, Johns E, Yang G-Zet al., 2020,

    Constrained-space optimization and reinforcement learning for complex tasks

    , IEEE Robotics and Automation Letters, Vol: 5, Pages: 683-690, ISSN: 2377-3766

    Learning from demonstration is increasingly used for transferring operator manipulation skills to robots. In practice, it is important to cater for limited data and imperfect human demonstrations, as well as underlying safety constraints. This article presents a constrained-space optimization and reinforcement learning scheme for managing complex tasks. Through interactions within the constrained space, the reinforcement learning agent is trained to optimize the manipulation skills according to a defined reward function. After learning, the optimal policy is derived from the well-trained reinforcement learning agent, which is then implemented to guide the robot to conduct tasks that are similar to the experts' demonstrations. The effectiveness of the proposed method is verified with a robotic suturing task, demonstrating that the learned policy outperformed the experts' demonstrations in terms of the smoothness of the joint motion and end-effector trajectories, as well as the overall task completion time.

  • Journal article
    He L, Lu Q, Abad S-A, Rojas N, Nanayakkara DPTet al., 2020,

    Soft fingertips with tactile sensing and active deformation for robust grasping of delicate objects

    , IEEE Robotics and Automation Letters, Vol: 5, Pages: 2714-2721, ISSN: 2377-3766

    Soft fingertips have shown significant adaptability for grasping a wide range of object shapes, thanks to elasticity. This ability can be enhanced to grasp soft, delicate objects by adding touch sensing. However, in these cases, the complete restraint and robustness of the grasps have proved to be challenging, as the exertion of additional forces on the fragile object can result in damage. This letter presents a novel soft fingertip design for delicate objects based on the concept of embedded air cavities, which allow the dual ability of tactile sensing and active shape-changing. The pressurized air cavities act as soft tactile sensors to control gripper position from internal pressure variation; and active fingertip deformation is achieved by applying positive pressure to these cavities, which then enable a delicate object to be kept securely in position, despite externally applied forces, by form closure. We demonstrate this improved grasping capability by comparing the displacement of grasped delicate objects exposed to high-speed motions. Results show that passive soft fingertips fail to restrain fragile objects at accelerations as low as 0.1 m/s 2 , in contrast, with the proposed fingertips delicate objects are completely secure even at accelerations of more than 5 m/s 2 .

  • Journal article
    Lu Q, Clark A, Shen M, Rojas Net al., 2020,

    An origami-inspired variable friction surface for increasing the dexterity of robotic grippers

    , IEEE Robotics and Automation Letters, Vol: 5, Pages: 2538-2545, ISSN: 2377-3766

    While the grasping capability of robotic grippers has shown significant development, the ability to manipulate objects within the hand is still limited. One explanation for this limitation is the lack of controlled contact variation between the grasped object and the gripper. For instance, human hands have the ability to firmly grip object surfaces, as well as slide over object faces, an aspect that aids the enhanced manipulation of objects within the hand without losing contact. In this letter, we present a parametric, origami-inspired thin surface capable of transitioning between a high friction and a low friction state, suitable for implementation as an epidermis in robotic fingers. A numerical analysis of the proposed surface based on its design parameters, force analysis, and performance in in-hand manipulation tasks is presented. Through the development of a simple two-fingered two-degree-of-freedom gripper utilizing the proposed variable-friction surfaces with different parameters, we experimentally demonstrate the improved manipulation capabilities of the hand when compared to the same gripper without changeable friction. Results show that the pattern density and valley gap are the main parameters that effect the in-hand manipulation performance. The origami-inspired thin surface with a higher pattern density generated a smaller valley gap and smaller height change, producing a more stable improvement of the manipulation capabilities of the hand.

  • Journal article
    Zhao M, Oude Vrielink TJC, Kogkas A, Runciman M, Elson D, Mylonas Get al., 2020,

    LaryngoTORS: a novel cable-driven parallel robotic system for transoral laser phonosurgery

    , IEEE Robotics and Automation Letters, Vol: 5, Pages: 1516-1523, ISSN: 2377-3766

    Transoral laser phonosurgery is a commonly used surgical procedure in which a laser beam is used to perform incision, ablation or photocoagulation of laryngeal tissues. Two techniques are commonly practiced: free beam and fiber delivery. For free beam delivery, a laser scanner is integrated into a surgical microscope to provide an accurate laser scanning pattern. This approach can only be used under direct line of sight, which may cause increased postoperative pain to the patient and injury, is uncomfortable for the surgeon during prolonged operations, the manipulability is poor and extensive training is required. In contrast, in the fiber delivery technique, a flexible fiber is used to transmit the laser beam and therefore does not require direct line of sight. However, this can only achieve manual level accuracy, repeatability and velocity, and does not allow for pattern scanning. Robotic systems have been developed to overcome the limitations of both techniques. However, these systems offer limited workspace and degrees-of-freedom (DoF), limiting their clinical applicability. This work presents the LaryngoTORS, a robotic system that aims at overcoming the limitations of the two techniques, by using a cable-driven parallel mechanism (CDPM) attached at the end of a curved laryngeal blade for controlling the end tip of the laser fiber. The system allows autonomous generation of scanning patterns or user driven freepath scanning. Path scan validation demonstrated errors as low as 0.054±0.028 mm and high repeatability of 0.027±0.020 mm (6×2 mm arc line). Ex vivo tests on chicken tissue have been carried out. The results show the ability of the system to overcome limitations of current methods with high accuracy and repeatability using the superior fiber delivery approach.

  • Journal article
    Liow L, Clark A, Rojas N, 2020,

    OLYMPIC: a modular, tendon-driven prosthetic hand with novel finger and wrist coupling mechanisms

    , IEEE Robotics and Automation Letters, Vol: 5, Pages: 299-306, ISSN: 2377-3766

    Prosthetic hands, while having shown significant progress in affordability, typically suffer from limited repairability, specifically by the user themselves. Several modular hands have been proposed to address this, but these solutions require handling of intricate components or are unsuitable for prosthetic use due to the large volume and weight resulting from added mechanical complexity to achieve this modularity. In this paper, we propose a fully modular design for a prosthetic hand with finger and wrist level modularity, allowing the removal and attachment of tendon-driven fingers without the need for tools, retendoning, and rewiring. Our innovative design enables placement of the motors behind the hand for remote actuation of the tendons, which are contained solely within the fingers. Details of the novel coupling-transmission mechanisms enabling this are presented; and the capabilities of a prototype using a control-independent grasping benchmark are discussed. The modular detachment torque of the fingers is also computed to analyse the trade-off between intentional removal and the ability to withstand external loads. Experiment results demonstrate that the prosthetic hand is able to grasp a wide range of household and food items, of different shape, size, and weight, without resulting in the ejection of fingers, while allowing a user to remove them easily using a single hand.

  • Conference paper
    Nunes UM, Demiris Y, 2020,

    Online unsupervised learning of the 3D kinematic structure of arbitrary rigid bodies

    , IEEE/CVF International Conference on Computer Vision (ICCV), Publisher: IEEE Computer Soc, Pages: 3808-3816, ISSN: 1550-5499

    This work addresses the problem of 3D kinematic structure learning of arbitrary articulated rigid bodies from RGB-D data sequences. Typically, this problem is addressed by offline methods that process a batch of frames, assuming that complete point trajectories are available. However, this approach is not feasible when considering scenarios that require continuity and fluidity, for instance, human-robot interaction. In contrast, we propose to tackle this problem in an online unsupervised fashion, by recursively maintaining the metric distance of the scene's 3D structure, while achieving real-time performance. The influence of noise is mitigated by building a similarity measure based on a linear embedding representation and incorporating this representation into the original metric distance. The kinematic structure is then estimated based on a combination of implicit motion and spatial properties. The proposed approach achieves competitive performance both quantitatively and qualitatively in terms of estimation accuracy, even compared to offline methods.

  • Conference paper
    Pardo F, Levdik V, Kormushev P, 2020,

    Scaling all-goals updates in reinforcement learning using convolutional neural networks

    , 34th AAAI Conference on Artificial Intelligence (AAAI 2020), Publisher: Association for the Advancement of Artificial Intelligence, Pages: 5355-5362, ISSN: 2374-3468

    Being able to reach any desired location in the environmentcan be a valuable asset for an agent. Learning a policy to nav-igate between all pairs of states individually is often not fea-sible. Anall-goals updatingalgorithm uses each transitionto learn Q-values towards all goals simultaneously and off-policy. However the expensive numerous updates in parallellimited the approach to small tabular cases so far. To tacklethis problem we propose to use convolutional network archi-tectures to generate Q-values and updates for a large numberof goals at once. We demonstrate the accuracy and generaliza-tion qualities of the proposed method on randomly generatedmazes and Sokoban puzzles. In the case of on-screen goalcoordinates the resulting mapping from frames todistance-mapsdirectly informs the agent about which places are reach-able and in how many steps. As an example of applicationwe show that replacing the random actions inε-greedy ex-ploration by several actions towards feasible goals generatesbetter exploratory trajectories on Montezuma’s Revenge andSuper Mario All-Stars games.

  • Conference paper
    Saputra RP, Rakicevic N, Kormushev P, 2020,

    Sim-to-real learning for casualty detection from ground projected point cloud data

    , 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019), Publisher: IEEE

    This paper addresses the problem of human body detection-particularly a human body lying on the ground (a.k.a. casualty)-using point cloud data. This ability to detect a casualty is one of the most important features of mobile rescue robots, in order for them to be able to operate autonomously. We propose a deep-learning-based casualty detection method using a deep convolutional neural network (CNN). This network is trained to be able to detect a casualty using a point-cloud data input. In the method we propose, the point cloud input is pre-processed to generate a depth image-like ground-projected heightmap. This heightmap is generated based on the projected distance of each point onto the detected ground plane within the point cloud data. The generated heightmap-in image form-is then used as an input for the CNN to detect a human body lying on the ground. To train the neural network, we propose a novel sim-to-real approach, in which the network model is trained using synthetic data obtained in simulation and then tested on real sensor data. To make the model transferable to real data implementations, during the training we adopt specific data augmentation strategies with the synthetic training data. The experimental results show that data augmentation introduced during the training process is essential for improving the performance of the trained model on real data. More specifically, the results demonstrate that the data augmentations on raw point-cloud data have contributed to a considerable improvement of the trained model performance.

  • Conference paper
    Chacon-Quesada R, Demiris Y, 2020,

    Augmented reality controlled smart wheelchair using dynamic signifiers for affordance representation

    , 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE

    The design of augmented reality interfaces for people with mobility impairments is a novel area with great potential, as well as multiple outstanding research challenges. In this paper we present an augmented reality user interface for controlling a smart wheelchair with a head-mounted display to provide assistance for mobility restricted people. Our motivation is to reduce the cognitive requirements needed to control a smart wheelchair. A key element of our platform is the ability to control the smart wheelchair using the concepts of affordances and signifiers. In addition to the technical details of our platform, we present a baseline study by evaluating our platform through user-trials of able-bodied individuals and two different affordances: 1) Door Go Through and 2) People Approach. To present these affordances to the user, we evaluated fixed symbol based signifiers versus our novel dynamic signifiers in terms of ease to understand the suggested actions and its relation with the objects. Our results show a clear preference for dynamic signifiers. In addition, we show that the task load reported by participants is lower when controlling the smart wheelchair with our augmented reality user interface compared to using the joystick, which is consistent with their qualitative answers.

  • Journal article
    Runciman M, Avery J, Zhao M, Darzi A, Mylonas GPet al., 2020,

    Deployable, variable stiffness, cable driven robot for minimally invasive surgery

    , Frontiers in Robotics and AI, Vol: 6, Pages: 1-16, ISSN: 2296-9144

    Minimally Invasive Surgery (MIS) imposes a trade-off between non-invasive access and surgical capability. Treatment of early gastric cancers over 20 mm in diameter can be achieved by performing Endoscopic Submucosal Dissection (ESD) with a flexible endoscope; however, this procedure is technically challenging, suffers from extended operation times and requires extensive training. To facilitate the ESD procedure, we have created a deployable cable driven robot that increases the surgical capabilities of the flexible endoscope while attempting to minimize the impact on the access that they offer. Using a low-profile inflatable support structure in the shape of a hollow hexagonal prism, our robot can fold around the flexible endoscope and, when the target site has been reached, achieve a 73.16% increase in volume and increase its radial stiffness. A sheath around the variable stiffness structure delivers a series of force transmission cables that connect to two independent tubular end-effectors through which standard flexible endoscopic instruments can pass and be anchored. Using a simple control scheme based on the length of each cable, the pose of the two instruments can be controlled by haptic controllers in each hand of the user. The forces exerted by a single instrument were measured, and a maximum magnitude of 8.29 N observed along a single axis. The working channels and tip control of the flexible endoscope remain in use in conjunction with our robot and were used during a procedure imitating the demands of ESD was successfully carried out by a novice user. Not only does this robot facilitate difficult surgical techniques, but it can be easily customized and rapidly produced at low cost due to a programmatic design approach.

  • Conference paper
    Johns E, Liu S, Davison A, 2020,

    End-to-end multi-task learning with attention

    , The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, Publisher: IEEE

    We propose a novel multi-task learning architecture, which allows learning of task-specific feature-level attention. Our design, the Multi-Task Attention Network (MTAN), consists of a single shared network containing a global feature pool, together with a soft-attention module for each task. These modules allow for learning of task-specific features from the global features, whilst simultaneously allowing for features to be shared across different tasks. The architecture can be trained end-to-end and can be built upon any feed-forward neural network, is simple to implement, and is parameter efficient. We evaluate our approach on a variety of datasets, across both image-to-image predictions and image classification tasks. We show that our architecture is state-of-the-art in multi-task learning compared to existing methods, and is also less sensitive to various weighting schemes in the multi-task loss function. Code is available at https://github.com/lorenmt/mtan.

  • Journal article
    Escribano Macias J, Angeloudis P, Ochieng W, 2020,

    Optimal hub selection for rapid medical deliveries using unmanned aerial vehicles

    , Transportation Research Part C: Emerging Technologies, Vol: 110, Pages: 56-80, ISSN: 0968-090X

    Unmanned Aerial Vehicles (UAVs) are being increasingly deployed in humanitarian response operations. Beyond regulations, vehicle range and integration with the humanitarian supply chain inhibit their deployment. To address these issues, we present a novel bi-stage operational planning approach that consists of a trajectory optimisation algorithm (that considers multiple flight stages), and a hub selection-routing algorithm that incorporates a new battery management heuristic. We apply the algorithm to a hypothetical response mission in Taiwan after the Chi-Chi earthquake of 1999 considering mission duration and distribution fairness. Our analysis indicates that UAV fleets can be used to provide rapid relief to populations of 20,000 individuals in under 24 h. Additionally, the proposed methodology achieves significant reductions in mission duration and battery stock requirements with respect to conservative energy estimations and other heuristics.

  • Journal article
    Zambelli M, Cully A, Demiris Y, 2020,

    Multimodal representation models for prediction and control from partial information

    , Robotics and Autonomous Systems, Vol: 123, ISSN: 0921-8890

    Similar to humans, robots benefit from interacting with their environment through a number of different sensor modalities, such as vision, touch, sound. However, learning from different sensor modalities is difficult, because the learning model must be able to handle diverse types of signals, and learn a coherent representation even when parts of the sensor inputs are missing. In this paper, a multimodal variational autoencoder is proposed to enable an iCub humanoid robot to learn representations of its sensorimotor capabilities from different sensor modalities. The proposed model is able to (1) reconstruct missing sensory modalities, (2) predict the sensorimotor state of self and the visual trajectories of other agents actions, and (3) control the agent to imitate an observed visual trajectory. Also, the proposed multimodal variational autoencoder can capture the kinematic redundancy of the robot motion through the learned probability distribution. Training multimodal models is not trivial due to the combinatorial complexity given by the possibility of missing modalities. We propose a strategy to train multimodal models, which successfully achieves improved performance of different reconstruction models. Finally, extensive experiments have been carried out using an iCub humanoid robot, showing high performance in multiple reconstruction, prediction and imitation tasks.

  • Conference paper
    Buizza C, Fischer T, Demiris Y, 2020,

    Real-time multi-person pose tracking using data assimilation

    , IEEE Winter Conference on Applications of Computer Vision, Publisher: IEEE

    We propose a framework for the integration of data assimilation and machine learning methods in human pose estimation, with the aim of enabling any pose estimation method to be run in real-time, whilst also increasing consistency and accuracy. Data assimilation and machine learning are complementary methods: the former allows us to make use of information about the underlying dynamics of a system but lacks the flexibility of a data-based model, which we can instead obtain with the latter. Our framework presents a real-time tracking module for any single or multi-person pose estimation system. Specifically, tracking is performed by a number of Kalman filters initiated for each new person appearing in a motion sequence. This permits tracking of multiple skeletons and reduces the frequency that computationally expensive pose estimation has to be run, enabling online pose tracking. The module tracks for N frames while the pose estimates are calculated for frame (N+1). This also results in increased consistency of person identification and reduced inaccuracies due to missing joint locations and inversion of left-and right-side joints.

  • Conference paper
    Liu S, Davison A, Johns E, 2019,

    Self-supervised generalisation with meta auxiliary learning

    , 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Publisher: Neural Information Processing Systems Foundation, Inc.

    Learning with auxiliary tasks can improve the ability of a primary task to generalise.However, this comes at the cost of manually labelling auxiliary data. We propose anew method which automatically learns appropriate labels for an auxiliary task,such that any supervised learning task can be improved without requiring access toany further data. The approach is to train two neural networks: a label-generationnetwork to predict the auxiliary labels, and a multi-task network to train theprimary task alongside the auxiliary task. The loss for the label-generation networkincorporates the loss of the multi-task network, and so this interaction between thetwo networks can be seen as a form of meta learning with a double gradient. Weshow that our proposed method, Meta AuXiliary Learning (MAXL), outperformssingle-task learning on 7 image datasets, without requiring any additional data.We also show that MAXL outperforms several other baselines for generatingauxiliary labels, and is even competitive when compared with human-definedauxiliary labels. The self-supervised nature of our method leads to a promisingnew direction towards automated generalisation. Source code can be found athttps://github.com/lorenmt/maxl.

  • Journal article
    Rakicevic N, Kormushev P, 2019,

    Active learning via informed search in movement parameter space for efficient robot task learning and transfer

    , Autonomous Robots, Vol: 43, Pages: 1917-1935, ISSN: 0929-5593

    Learning complex physical tasks via trial-and-error is still challenging for high-degree-of-freedom robots. Greatest challenges are devising a suitable objective function that defines the task, and the high sample complexity of learning the task. We propose a novel active learning framework, consisting of decoupled task model and exploration components, which does not require an objective function. The task model is specific to a task and maps the parameter space, defining a trial, to the trial outcome space. The exploration component enables efficient search in the trial-parameter space to generate the subsequent most informative trials, by simultaneously exploiting all the information gained from previous trials and reducing the task model’s overall uncertainty. We analyse the performance of our framework in a simulation environment and further validate it on a challenging bimanual-robot puck-passing task. Results show that the robot successfully acquires the necessary skills after only 100 trials without any prior information about the task or target positions. Decoupling the framework’s components also enables efficient skill transfer to new environments which is validated experimentally.

  • Conference paper
    Vespa E, Funk N, Kelly PHJ, Leutenegger Set al., 2019,

    Adaptive-resolution octree-based volumetric SLAM

    , 7th International Conference on 3D Vision (3DV), Publisher: IEEE COMPUTER SOC, Pages: 654-662, ISSN: 2378-3826

    We introduce a novel volumetric SLAM pipeline for the integration and rendering of depth images at an adaptive level of detail. Our core contribution is a fusion algorithm which dynamically selects the appropriate integration scale based on the effective sensor resolution given the distance from the observed scene, addressing aliasing issues, reconstruction quality, and efficiency simultaneously. We implement our approach using an efficient octree structure which supports multi-resolution rendering allowing for online frame-to-model alignment. Our qualitative and quantitative experiments demonstrate significantly improved reconstruction quality and up to six-fold execution time speed-ups compared to single resolution grids.

  • Conference paper
    Ezzat A, Thakkar R, Kogkas A, Mylonas Get al., 2019,

    Perceptions of surgeons and scrub nurses towards a novel eye-tracking based robotic scrub nurse platform

    , International Surgical Congress of the Association-of-Surgeons-of-Great-Britain-and-Ireland (ASGBI), Publisher: WILEY, Pages: 81-82, ISSN: 0007-1323
  • Conference paper
    Bujanca M, Gafton P, Saeedi S, Nisbet A, Bodin B, O'Boyle MFP, Davison AJ, Paul HJ K, Riley G, Lennox B, Lujan M, Furber Set al., 2019,

    SLAMBench 3.0: Systematic automated reproducible evaluation of SLAM systems for robot vision challenges and scene understanding

    , 2019 International Conference on Robotics and Automation (ICRA), Publisher: Institute of Electrical and Electronics Engineers, ISSN: 1050-4729

    As the SLAM research area matures and the number of SLAM systems available increases, the need for frameworks that can objectively evaluate them against prior work grows. This new version of SLAMBench moves beyond traditional visual SLAM, and provides new support for scene understanding and non-rigid environments (dynamic SLAM). More concretely for dynamic SLAM, SLAMBench 3.0 includes the first publicly available implementation of DynamicFusion, along with an evaluation infrastructure. In addition, we include two SLAM systems (one dense, one sparse) augmented with convolutional neural networks for scene understanding, together with datasets and appropriate metrics. Through a series of use-cases, we demonstrate the newly incorporated algorithms, visulation aids and metrics (6 new metrics, 4 new datasets and 5 new algorithms).

  • Conference paper
    Avery J, Runciman M, Darzi A, Mylonas GPet al., 2019,

    Shape sensing of variable stiffness soft robots using electrical impedance tomography

    , International Conference on Robotics and Automation (ICRA), Publisher: IEEE, Pages: 9066-9072, ISSN: 1050-4729

    Soft robotic systems offer benefits over traditional rigid systems through reduced contact trauma with soft tissues and by enabling access through tortuous paths in minimally invasive surgery. However, the inherent deformability of soft robots places both a greater onus on accurate modelling of their shape, and greater challenges in realising intraoperative shape sensing. Herein we present a proprioceptive (self-sensing) soft actuator, with an electrically conductive working fluid. Electrical impedance measurements from up to six electrodes enabled tomographic reconstructions using Electrical Impedance Tomography (EIT). A new Frequency Division Multiplexed (FDM) EIT system was developed capable of measurements of 66 dB SNR with 20 ms temporal resolution. The concept was examined in two two-degree-of-freedom designs: a hydraulic hinged actuator and a pneumatic finger actuator with hydraulic beams. Both cases demonstrated that impedance measurements could be used to infer shape changes, and EIT images reconstructed during actuation showed distinct patterns with respect to each degree of freedom (DOF). Whilst there was some mechanical hysteresis observed, the repeatability of the measurements and resultant images was high. The results show the potential of FDM-EIT as a low-cost, low profile shape sensor in soft robots.

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.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-t4-html.jsp Request URI: /respub/WEB-INF/jsp/search-t4-html.jsp Query String: id=1128&limit=20&page=3&respub-action=search.html Current Millis: 1642510177211 Current Time: Tue Jan 18 12:49:37 GMT 2022