As one of the most fundamental control modes in robotics, force/torque (F/T) control plays an essential role in a wide range of applications. However, classical F/T control fails to offer effective means to regulate the convergence sequence of the controlled states, which is beneficial in many real-world tasks, e.g., unknown surface contact, where the force should preferably converge later than the alignment angles to ensure sufficient contact and avoid dangerous misalignment. In this work, a novel nested fast terminal sliding mode control approach is proposed. This approach establishes a hierarchical structure for the controlled states, such that the Lyapunov stabilities of controlled states can be achieved in both a sequential and a time-synchronized manner within finite time, which is named as ‘Sequen-Sync’. Extensive experiments are conducted for various tasks in two different environments. The experimental results show that the proposed approach successfully achieves Sequen-Sync stability, which leads to improved contact quality and enhanced safety.

Impedance control can be achieved within a model predictive control (MPC) framework for optimization and constraint compliance. However, user-defined or optimization-derived impedance models can be too conservative to achieve a timely convergence, or too aggressive to ensure safety. To address this, an MPC-based impedance control framework with learning-based tuning for predefined-time (PdT) convergence is proposed. On the low level, the framework dynamically selects between a task-oriented and a safety-oriented impedance model based on real-time interaction force modeling and safety assessments, ensuring optimal performance and maintaining safety while interacting with unknown and complex environments. On the high level, the framework achieves PdT convergence via reinforcement learning for meta-parameter tuning, allowing users to specify the desired convergence time upper bound. Lastly, the superiority of the proposed framework is validated on interaction safety and PdT convergence via experiments.

The potential of tactile sensing for dexterous robotic manipulation has been demonstrated by its ability to enable nuanced real-world interactions. In this study, the retrieval of unknown objects from confined spaces, which is unsuitable for conventional visual perception and gripper-based manipulation, is identified and addressed. Specifically, a tactile-sensorized tool stick that well fits in the narrow space is utilized to provide multi-point contact sensing for object manipulation. A reinforcement learning (RL) agent with a hybrid action space is then proposed to acquire the optimal policy for manipulating the objects without prior knowledge of their physical properties. To accelerate on-hardware training, a focused training strategy is adopted with the hypothesis that an agent trained on a small set of representative shapes can be generalized to a wide range of everyday objects. Additionally, a curriculum on terminal goals is designed to further accelerate the hardware-based training process. Comparative experiments and ablation studies have been conducted to evaluate the effectiveness and robustness of the proposed approach, which highlights the high success rate of our solution for retrieving everyday objects.

Although object detection has achieved significant progress in the past decade, detecting small objects is still far from satisfactory due to the high variability of object scales and complex backgrounds. The common way to enhance small object detection is to use high-resolution (HR) images. However, this method incurs huge computational resources which grow squarely with the resolution of images. To achieve both accuracy and efficiency, we propose a novel reinforcement learning framework that employs an efficient policy network consisting of a Spatial Transformation Network to enhance the state representation learning and a Transformer model with early convolution to improve feature extraction. Our method has two main steps: (1) coarse location query (CLQ), where an RL agent is trained to predict the locations of small objects on low-resolution (LR) (down-sampled version of HR) images; (2) context-sensitive object detection where HR image patches are used to detect objects on the selected coarse locations and LR image patches on background areas (containing no small objects). In this way, we can obtain high detection performance on small objects while avoiding unnecessary computation on background areas. The proposed method has been tested and benchmarked on various datasets. On the Caltech Pedestrians Detection and Web Pedestrians datasets, the proposed method improves the detection accuracy by 2%, while reducing the number of processed pixels. On the Vision meets Drone object detection dataset and the Oil and Gas Storage Tank dataset, the proposed method outperforms the state-of-the-art (SotA) methods. On MS COCO mini-val set, our method outperforms SotA methods on small object detection, while also achieving comparable performance on medium and large objects.

In deep reinforcement learning (DRL), the agent is usually trained on seen environments by optimizing a policy network. However, it is difficult to be generalized to unseen environments properly, even when the environmental variations are insignificant. This is partly because the policy network cannot effectively learn the representation of visual difference that is subtle among highly similar states in the environments. Because a bilinear structured model containing two feature extractors allows pairwise feature interactions in a translation-ally invariant manner which makes it particularly useful for subtle difference recognition among highly similar states, in this work, a bilinear policy network is employed to enhance representation learning, and thus to improve generalization of the DRL. The proposed bilinear policy network is tested on various DRL task, including a control task on path planning for active object detection, and Grid World, an AI game task. The test results show that the generalization of DRL can be improved by the proposed network.

Planar pushing is a fundamental robot manipulation task with most algorithms built upon the quasi-static as-sumption. Under this assumption the end-effector should apply force on the pushed object along the full moving trajectory. This means that the target position must lie in the robot's workspace. To enable a robot to deliver objects outside of its workspace and facilitate faster delivery, the quasi-static assumption should be lifted in favour of dynamical manipulation. In this work, we propose a two-staged data-driven manipulation method to hit an unknown object to reach a target position. This expands the reachability of the manipulated object beyond the robot's workspace. The robot equipped with a tactile sensor first explores for the stable pushing region (SPR) on the given object by using a gain-scheduling PD control with the contact centre estimated to maintain full contact between the object and the end-effector. In the second stage, a learning-based approach is used to generate the impulse the object should receive at the SPR to reach a target sliding distance. The performance of proposed method is evaluated on a KUKA LBR iiwa 14 R820 robot manipulator and a XELA tactile sensor.

When deploying a robot to a new task, one often has to train it to detect novel objects, which is time-consuming and labor- intensive. We present TAILOR - a method and system for ob- ject registration with active and incremental learning. When instructed by a human teacher to register an object, TAILOR is able to automatically select viewpoints to capture informa- tive images by actively exploring viewpoints, and employs a fast incremental learning algorithm to learn new objects without potential forgetting of previously learned objects. We demonstrate the effectiveness of our method with a KUKA robot to learn novel objects used in a real-world gearbox as- sembly task through natural interactions.

Manipulation in a densely cluttered environment creates complex challenges in perception to close the control loop, many of which are due to the sophisticated physical interaction between the environment and the manipulator. Drawing from biological sensory-motor control, to handle the task in such a scenario, tactile sensing can be used to provide an additional dimension of the rich contact information from the interaction for decision making and action selection to manoeuvre towards a target. In this paper, a new tactile-based motion planning and control framework based on bioinspiration is proposed and developed for a robot manipulator to manoeuvre in a cluttered environment. An iterative two-stage machine learning approach is used in this framework: an autoencoder is used to extract important cues from tactile sensory readings while a reinforcement learning technique is used to generate optimal motion sequence to efficiently reach the given target. The framework is implemented on a KUKA LBR iiwa robot mounted with a SynTouch BioTac tactile sensor and tested with real-life experiments. The results show that the system is able to move the end-effector through the cluttered environment to reach the target effectively.

Active vision is a desirable perceptual feature for robots. Existing approaches usually make strong assumptions about the task and environment, thus are less robust and efficient. This study proposes an adaptive view planning approach to boost the efficiency and robustness of active object detection. We formulate the multi-object detection task as an active multiview object detection problem given the initial location of the objects. Next, we propose a novel adaptive action prediction (A2P) method built on a deep Q-learning network with a dueling architecture. The A2P method is able to perform view planning based on visual information of multiple objects; and adjust action ranges according to the task status. Evaluated on the AVD dataset, A2P leads to 21.9% increase in detection accuracy in unfamiliar environments, while improving efficiency by 22.7%. On the T-LESS dataset, multi-object detection boosts efficiency by more than 30% while achieving equivalent detection accuracy.

To address the problem of the non-holonomic reference trajectory in trajectory tracking controller design for mechanical systems, we design a novel RBF-Udwadia controller in this paper. The framework of the Udwadia controller is employed to design the controller, which helps to deal with the non-holonomic reference trajectory. The radial basis function (RBF) neural network is employed to approximately model the uncertainty. The stability of the designed controller is analyzed by the Lyapunov method, and the effectiveness of the designed controller is verified by a numerical experiment.

In this paper, a neural network-based (NN-based) integral sliding mode control approach is presented for a piezoelectric ultrasonic motor. The precision motion performance of the motor can be adversely affected in the presence of nonlinearities including friction and disturbance, as well as parameters uncertainties. Integral sliding mode control is effective in dealing with uncertainties and disturbances. To achieve better performance on tracking desired motion trajectories, a neural network structure with modified jump basis functions are used to model and compensate the discontinuous friction in the motor control systems. This structure can approximate friction with high accuracy but require few NN nodes. Stability of the proposed control strategy is analyzed. The simulation studies are provided to demonstrate the precise tracking performance of the proposed control scheme.

Robotic systems are increasingly required not only to generate precise motions to complete their tasks but also to handle the interactions with the environment or human. Significantly, soft interaction brings great challenges on the force control due to the nonlinear, viscoelastic and inhomogeneous properties of the soft environment. In this paper, a robust impedance control scheme utilizing integral backstepping technology and integral terminal sliding mode control is proposed to achieve force tracking for an ultrasonic motor-actuated end-effector in a soft environment. In particular, the steady-state performance of the target impedance while in contact with soft environment is derived and analyzed with the nonlinear Hunt-Crossley model. Finally, the dynamic force tracking performance of the proposed control scheme is verified via several experiments.

Even though path planning is a well-studied problem in 2D environment, finding an optimal or near-optimal path in a complex and unknown 3D environment has great prospect, but it is hard to find the optimal path quickly. In this paper, we propose a new algorithm called Hierarchical Lazy Theta* (HLT*), which can plan the near-optimal path efficiently for real-time operation based on the heuristic-based path-finding algorithm Lazy Theta* with a hierarchical path planning approach. Path refinement, smoothing, and polishing are used to refine the path to ensure the feasibility of computed path. Its computation time and path quality are dependent on parameters, such as map size, environment complexity, sensor detection range, refinement range, computation time limits, and any restriction on planning time. Simulation experiments are used to assess the performance, and the simulation results show that HLT* algorithm is capable of planning a high-quality path in a shorter time.

We propose a biomimetic approach for steering motion control of a snake robot. Inspired by a vertebrate biological motor system paradigm, a hierarchical control scheme is adopted. In the control scheme, an artificial central pattern generator (CPG) is employed to generate serpentine locomotion in the robot. This generator outputs the coordinated desired joint angle commands to each lower-level effector controller, while the locomotion can be controlled through CPG modulation by a higher-level motion controller. The motion controller consists of a cerebellar model articulation controller (CMAC) and a proportional-derivative (PD) controller. Because of the fast learning ability of the CMAC, the proposed motion controller can drive the robot to track the desired orientation and adapt to unexpected perturbations. The PD controller is employed to expedite the convergence speed of the motion controller. Finally, both numerical studies and experiments proved that the proposed approach can help the snake robot achieve good tracking performance and adaptability in a varying environment.

The handling of ultrathin wafers (<;100 μm thickness) is a challenging task since these are among the thinnest and most fragile materials. This paper provides a soft-acting and noncontact gripping technology for ultrathin wafer based on the distributed Bernoulli principle, and also proposes an experimental measurement method for evaluating the performance. A distributed Bernoulli gripper for ultrathin wafers is designed, and the characteristics of the gripper are studied via theoretical analysis and experiments. Three performance indices for evaluating the properties of the soft gripping: deformation, vibration, and stress are presented. Through measurement experiments, the effects of the key operational parameters consisting of air flow rate and gap height on the performance indices are investigated. Based on the experimental data, the appropriate parameters settings are obtained. The comparison to present grippers reveals that the proposed gripping technology is superior in soft gripping thin and fragile materials. This paper provides guidance for implementing the distributed Bernoulli principle in practical applications of soft-acting and noncontact gripping for thin and fragile materials.

The dual-drive H-gantry is widely used for high-speed, high-precision Cartesian motion. Compared with the conventional rigid-linked design, the flexure-linked counterpart is able to prevent the damage of joints for its smaller interaxial coupling force. However, there are still barriers to further push up its precision, such as parametric uncertainties due to the inaccurate dynamical model, the possible induced vibration during high-speed motion, and the decentralized control structure required by industries. To maintain the tracking precision of carriages and minimize the vibration of the end effector, we aim to optimize parameters in decentralized controllers with choices of flexure pieces. We find that such decentralized feedback structure yields some uncontrollable but stabilizable states in the closed-loop system, and no direct solution from solving the algebraic Riccati equation is available in this case. Such structural constraint, together with constraints due to stability requirement and model uncertainties facilitates us to formulate an H2guaranteed cost control problem within a projected convex domain. From here, efficient numerical procedures are developed to obtain the global optimum by iterative linear programming. The real-time experiment validates the optimality and the robustness of the proposed method.

Soft robots have recently evoked extensive attention due to their abilities to work effectively in unstructured environments. As an actuation technology of soft robots, dielectric elastomers exhibit many intriguing attributes such as large strain and high energy density. This work presents a novel dielectric elastomer based soft crawling robot inspired by inchworms. To fill the need of control of the soft robot, a model describing the interaction between the dielectric elastomer actuator and the environment is proposed, which takes inertia, viscoelasticity and friction into consideration. The model can well describe the robot's dynamic performances and the modelling approach used here can be extended to other dielectric elastomer actuators with complicated geometries for control purposes. The obtained model allows us to design a feedforward plus feedback control scheme for the robot to achieve desired motion. Simulation shows fast response and good tracking performances which are further confirmed by the experiments.

Ultrasonic motors (USMs) are widely used in many applications that precise and fast motions are required, such as precision machines and medical devices, etc. In this paper, a USM -driven ear surgical device is introduced. To address the control challenges of the USM, an intelligent controller consisting of a cerebellar model articulation controller (CMAC) and a sliding mode compensator (SMC) is designed. Therein, the CMAC serves as the main controller due to its fast learning ability while the SMC is used to eliminate the approximation error between the CMAC and the desired perfect controller. Several experiments are carried out to validate the effectiveness of the proposed control scheme, and the results show that the proposed control scheme is able to achieve good tracking performance and guaranteed robustness.

This paper discusses pain-related considerations when transforming an operation typically performed under general anesthesia in an operating room, to an office-based procedure by utilizing the automated Ventilation Tube Applicator (VTA). Literature showed that it is advantageous to keep the total procedure time to under 450ms and peak force to under 0.445N for pain mitigation and to minimize middle ear damage. Experiments were carried out to compare manual versus automated procedure and results showed that the automated procedure using VTA has some improvements over the manual one in terms of total time taken and total applied force. However, VTA's peak force is higher than desired. Hence, further optimization of the VTA's parameters is needed to achieve faster time and lower peak force. In-depth experiments were carried out using Taguchi's Design of Experiments to distinguish the contributing factors. Using multiple-objective optimization, the optimal parameters for VTA are found.

Design of experiments (DOE) is a systematic, rigorous approach to engineering problem-solving that applies principles and techniques at the data collection stage so as to ensure the generation of valid, defensible and supportable engineering conclusions. It has been used in manufacturing environment for decades to investigate factors affecting a process response under the constraint of a minimal expenditure of engineering runs, time and money. The main purpose is first qualifying the important factors among a number of variables in the process and secondly achieving a desired outcome of the response by choosing the correct settings for those factors. In this technical report, we apply factorial design in DOE to select key features to be implemented in an office-based ventilation tube applicator (VTA). These features will directly affect the success rate of the automated tube insertion to cure patients having otitis media with effusion. The results of experiment are analysed using classification tree analysis. The analysis yields the optimal combination of factors to produce optimised output which is qualified for the prototyping phase.

In this paper, an automatic office-based ear surgical device for the treatment of Otitis Media with Effusion (OME) which overcomes the disadvantages of the conventional surgical treatment is introduced. Since the device carries out the surgery automatically under the guidance of force sensing information, this information must be reliable so that the safety of the device can be ensured. Hence, a force detection method based on the disturbance observer is proposed in this paper. To overcome the disadvantages of the conventional disturbance observer, an advanced disturbance observer is designed and its stability is analyzed. Finally, the simulation study on the disturbance observer is carried out. The results show that the advanced disturbance observer can estimate the disturbance correctly and precisely.

Otitis media with effusion (OME), a worldwide common ear disease, affecting adults and children when the middle ear is infected. Grommet insertion treatment leads to the development and design of a medical device allowing fast and automatic grommet insertion in an earlier work. In the medical device design, a precision motion system is used to provide the accurate movements for the precise grommet insertion procedure. Besides that, a fiberscope is used to provide the vision for the device. Medical imaging is a technique or process to create visual representations of body for clinical analysis and medical intervention. This paper addresses the design consideration and evaluation of a built-in visual analysis platform equipped on the eardrum microsurgery device. In this special configuration, a fiberscope is placed within the tip of a cutting tool to facilitate image analysis of the motorised surgery with high precision movement. Images from this fiberscope are analysed to build important features during the operation such as proximity estimation, angle measurement and touch detection. These enhanced features are hardly achieved in the traditional approach where a common microscope is used. The platform is implemented under a computerised system and evaluated through experimental results.

Otitis Media with Effusion, a common ear disease, occurs in adults and children when the middle ear is infected, resulting in accumulation of fluid in the middle ear space. The conventional treatment is to surgically insert a ventilation tube into the tympanic membrane (TM) to suction out the fluid. An office-based robotic device allowing fast tube insertion has been designed in an earlier work of the authors. However, as the malleus bone attaches to the inner surface of the TM, and this part of the membrane is thus to be avoided during the insertion process. The previous device requires manual manipulation to avoid hitting the malleus bone before tube insertion. To accomplish the procedure automatically, a switching control scheme using intelligent vision-servo and tactile sensing is proposed in this paper. The new device is able to guide the insertion channel to move effectively and intelligently in the ear canal. Pre-clinical tests on the pig ears verify the feasibility and efficacy of the proposed approach.

In-vitro fertilization (IVF) and related technologies are arguably the most challenging of all cell culture applications. This paper introduces a new design of an integrated oocyte retrieval solution before the oocytes are further put into laboratory processing during IVF treatment. It facilitates the surgery operation and addresses the temperature inaccuracy of follicular fluid during the transfer to the patient's body. The mechanical design is implemented into a medical-standard conforming platform. An accurate temperature estimation and optimization scheme is also proposed. Comparison before and after the introduction of the new prototype under various operating conditions reveals a significant improvement in performance. This yields a potential application for the medical/healthcare industry.