IROS 2019 Papers

In this paper, we propose a novel penetration metric, called deformable penetration depth PDd, to define a measure of inter-penetration between two linearly deforming tetrahedra using the object norm [1]. First of all, we show that a distance metric for a tetrahedron deforming between two configurations can be found in closed form based on object norm. Then, we show that the PDd between an intersecting pair of static and deforming tetrahedra can be found by solving a quadratic programming (QP) problem in terms of the distance metric with non-penetration constraints. We also show that the PDd between two, intersected, deforming tetrahedra can be found by solving a similar QP problem under some assumption on penetrating directions, and it can be also accelerated by an order of magnitude using pre-calculated penetration direction. We have implemented our algorithm on a standard PC platform using an off-the-shelf QP optimizer, and experimentally show that both the static/deformable and deformable/deformable tetrahedra cases can be solvable in from a few to tens of milliseconds. Finally, we demonstrate that our penetration metric is three-times smaller (or tighter) than the classical, rigid penetration depth metric in our experiments.

Current grasping methods for aerial vehicles are slow, inaccurate and they cannot adapt to any target object. Thus, they do not allow for on-the-fly, ultra-fast grasping. In this paper, we present a passive closing, adaptive robot hand design that offers ultra-fast, aerial grasping for a wide range of everyday objects. We investigate alternative uses of structural compliance for the development of simple, adaptive robot grippers and hands and we propose an appropriate quick release mechanism that facilitates an instantaneous grasping execution. The quick release mechanism is triggered by a simple distance sensor. The proposed hand utilizes only two actuators to control multiple degrees of freedom over three fingers and it retains the superior grasping capabilities of adaptive grasping mechanisms, even under significant object pose or other environmental uncertainties. The hand achieves a grasping time of 96 ms, a maximum grasping force of 56 N and it is able to secure objects of various shapes at high speeds. The proposed hand can serve as the end-effector of grasping capable Unmanned Aerial Vehicle (UAV) platforms and it can offer perching capabilities, facilitating autonomous docking.

For a robotic gripper to perform as well as the human hand, the performance of the tactile sensing and grasping of the gripper must be improved. In this study, a parallel gripper with a universal fingertip device that combines both object holding using jamming transition and optical sensing is proposed. By using a transparent material along with the jamming transition, both a tactile sense is achieved via optical sensing and the holding stability is improved by tightly restraining the object. Because the hardness of the contact region of the membrane can be adjusted, the gripper can grasp heavy objects as well as light objects. In this paper, the structure of the developed gripper and its grasping characteristics are described, and the experimental results from grasping and sensing are presented. It is experimentally shown that the proposed gripper is capable of both grasping fragile objects (such as an egg and tofu) by using tactile sensing and grasping dumbbells (with weights between 1-3 kg) by using jamming transition. Additionally, grasping a plastic cup, the proposed gripper demonstrated the potential of combining tactile sensing and more-constrained grasping.

This paper describes a novel small-scale turtle-inspired Amphibious Spherical Robot (ASRobot) to accomplish exploration tasks in the restricted environment, such as amphibious areas and narrow underwater cave. A Legged, Multi-Vectored Water-Jet Composite Propulsion Mechanism (LMVWCPM) is designed with four legs, one of which contains three connecting rod parts, one water-jet thruster and three joints driven by digital servos. Using this mechanism, the robot is able to walk like amphibious turtles on various terrains and swim flexibly in submarine environment. A simplified kinematic model is established to analyze crawling gaits. With simulation of the crawling gait, the driving torques of different joints contributed to the choice of servos and the size of links of legs. Then we also modeled the robot in water and proposed several underwater locomotion. In order to assess the performance of the proposed robot, a series of experiments were carried out in the lab pool and on flat ground using the prototype robot. Experiments results verified the effectiveness of LMVWCPM and the amphibious control approaches.

In this paper, a novel semi-autonomous control framework is presented for enabling probe-based confocal laser endomicroscopy (pCLE) scan of the retinal tissue. With pCLE, retinal layers such as nerve fiber layer (NFL) and retinal ganglion cell (RGC) can be scanned and characterized in real-time for an improved diagnosis and surgical outcome prediction. However, the limited field of view of the pCLE system and the micron-scale optimal focus distance of the probe, which are in the order of physiological hand tremor, act as barriers to successful manual scan of retinal tissue.Therefore, a novel sensorless framework is proposed for real-time semi-autonomous endomicroscopy scanning during retinal surgery. The framework consists of the Steady-Hand Eye Robot (SHER) integrated with a pCLE system, where the motion of the probe is controlled semi-autonomously. Through a hybrid motion control strategy, the system autonomously controls the confocal probe to optimize the sharpness and quality of the pCLE images, while providing the surgeon with the ability to scan the tissue in a tremor-free manner. Effectiveness of the proposed architecture is validated through experimental evaluations as well as a user study involving 9 participants. It is shown through statistical analyses that the proposed framework can reduce the work load experienced by the users in a statistically-significant manner, while also enhancing their performance in retaining pCLE images with optimized quality.

Extrinsic calibration is a necessary step when using heterogeneous sensors for robotics applications. Most existing methods work under the assumption that the prior data correspondence is known. Considering data loss and false measurements, the correspondence may not be accessible in practice. To solve this problem without knowing the correspondence, several probabilistic methods have been proposed. However, an implicit restriction on input data limits their application. Therefore, in this paper, we propose a more stable correspondence-free method with two improvements that can relax the restrictions on inputs and improve the calibration accuracy. The first improvement finds consistent sets from raw inputs using screw invariants, which significantly improve the robustness in case of outliers and data loss. A new optimization method on matrix Lie group is proposed as the second improvement, which demonstrates better accuracy. The experimental results on both numerical and real data show the superiority and robustness of the proposed method.

This paper presents the novel capabilities of a quadruped robot by performing horizontal-vertical-horizontal movement transition through vertical ladder without handrailing supporter. To overcome the proposed problem, we propose a multi-behavior generation model using independent stepping and pose control in the quadruped robot. The model is able to generate appropriate behavior depending on external (3D point clouds) and internal sensors (ground touch sensor, and Inertial Measurement Unit). Posture condition, safe movement area, possible touchpoint, grasping possibility, and target movement are the information that is analyzed from the sensors. There are four options developed in behavior generation, which are, Approaching, Body Placing, Stepping, and Grasping behavior. In order to prove the effectiveness of the proposed algorithm, the model was implemented on the computer simulation and the real application. Before being applied in the real robot, the proposed model is optimized in the computer simulation. Then, the optimized parameter is used for applying in the real robot. As a result, the robot succeeded to move through the ladder without handrail from lower stair to upper stair. From the analysis, the body placing behavior is the most important strategy in the proposed case.

In the past few decades machine learning and data analysis have been having a huge growth and they have been applied in many different problems in the field of robotics. Data are usually the result of sensor measurements and, as such, they might be subjected to noise and outliers. The presence of outliers has a huge impact on modelling the acquired data, resulting in inappropriate models. In this work a novel approach for outlier detection and rejection for input/output mapping in regression problems is presented. The robustness of the method is shown both through simulated data for linear and nonlinear regression, and real sensory data. Despite being validated by using artificial neural networks, the method can be generalized to any other regression method.

In this study, a novel four degrees of freedom (DoF) robotic link mechanism and its torque analysis based on extended coaxial spherical joint module (E-CoSMo) are introduced. The E-CoSMo is a previously developed 4-DoF point-centered rotational parallel mechanism with coaxial actuators. The use of the E-CoSMo on robotic system is expected to improve dynamic performance since all actuators are mounted on fixed base. Furthermore, output torque is amplified in a specific axial direction, due to a coaxial parallel mechanism. Torque analysis of the mechanism is derived based on kinematics of a virtual 4-DoF serial linkages and the E-CoSMo. A virtual force-based position control simulation is performed for verifying the torque analysis. Due to the valid torque analysis, the norm of position error is less than 0. 7 mm. It is confirmed that the output torque is amplified compare to actuator torques, which is a special feature of the E-CoSMo. Control experiments using prototype are also carried out to validate the feasibility.

In this paper, we propose a novel time-varying feedback control strategy based on the Robust Integral of the Sign of the Error (RISE). The main motivation is to enhance the tracking performance of RISE controller at high dynamic operating conditions. RISE control law ensures a semi-global asymptotic tracking without introducing severe restrictions on the uncertain and nonlinearly parametrized systems. More nonlinearities are added to the original RISE control law by replacing the static feedback gains with nonlinear ones which depend on the system state variables. The proposed contribution is implemented in real-time experiments on a non-redundant three-degrees-of-freedom parallel manipulator named Delta. Comparing to the standard RISE controller, experimental results show better tracking performances of the proposed time-varying feedback RISE controller.

Most of the existing soft locomotive robots are capable of moving on horizontal planes and small-angled slopes, but few of them can accomplish the large-angled slope climbing or wall climbing. We introduce an inchworm inspired soft crawling-climbing robot capable of continuous motion from a horizontal plane to a slope of up to 75 degrees and it can perform multiple locomotion including crawling, climbing, and the transition between them. This soft crawling-climbing robot is powered by three pneumatic actuators connected in series that deforms with two degrees of freedom, negative pressure sucker feet that generate periodical adhesion, and a semi-automatic controlling system synchronizing the body shape and anchoring of the feet. The robot mimics the body deformation and feet anchoring pattern exhibited by inchworms and can be applied in inspection, surveillance, and rescuing.

With rapid advances in social robotics, humanoids and autonomy, robot assistants appear to be within reach. However, robots are still unable to effectively interact with humans in activities of daily living. One of the challenges is in the frequent use of multiple communication modalities when humans engage in collaborative activities. In this paper, we propose a Multimodal Interaction Manager, a framework for an assistive robot that maintains an active multimodal interaction with a human partner while performing physical collaborative tasks. The heart of our framework is a Hierarchical Bipartite Action-Transition Network (HBATN), which allows the robot to infer the state of the task and the dialogue given spoken utterances and observed pointing gestures from a human partner, and to plan its next actions. Finally, we implemented this framework on a robot to provide preliminary evidence that the robot can successfully participate in a task-oriented multimodal interaction.

Brain-computer interface is a framework which provides a communicating pathway between the human brain and neuroprosthetic devices. In this work, we have performed signal smoothing to fix unregulated electroencephalogram (EEG) fluctuations and to effectively collect hidden patterns in corresponding EEG spectra. To do it, we have applied a Savitzky Golay function because of its ability to preserve spectral properties without distorting it much. For feature selection, we have applied the Filter Bank Common Spatial Pattern (FBCSP) algorithm with the Principle Component Analysis (PCA). FBCSP creates 11352 features from EEG signals and PCA gradually reduces the features to 185 most significant features. These features are utilized in the classification process by the eXtreme Gradient Boosting (XGBoost) algorithm with suitable node split criteria to manage optimal tree height. A five-fold cross-validation approach concludes the superior performance of XGBoost in terms of minimizing execution time (3.7 times faster in the training phase) and providing improved accuracy as compared to existing results. Our approach enhances classification accuracy (88.80%) by approximately 10% over regularized common spatial patterns (78.01% accuracy), 15% over shift variance approximation (73.84% accuracy) and 15% over Riemannian approach (74.77% accuracy). It also concludes that the pre-consideration of the noise level in EEG spectra provides a better approximation.

Autonomous robotic grasping plays an important role in intelligent robotics. However, how to help the robot grasp specific objects in object stacking scenes is still an open problem, because there are two main challenges for autonomous robots: (1) it is a comprehensive task to know what and how to grasp; (2) it is hard to deal with the situations in which the target is hidden or covered by other objects. In this paper, we propose a multi-task convolutional neural network for autonomous robotic grasping, which can help the robot find the target, make the plan for grasping and finally grasp the target step by step in object stacking scenes. We integrate vision-based robotic grasping detection and visual manipulation relationship reasoning in one single deep network and build the autonomous robotic grasping system. Experimental results demonstrate that with our model, Baxter robot can autonomously grasp the target with a success rate of 90.6%, 71.9% and 59.4% in object cluttered scenes, familiar stacking scenes and complex stacking scenes respectively.

In this paper, the development of a two-degrees-of-freedom (DOF) human-powered robot using regenerative clutches and constant-force springs is described. A regenerative clutch can control a transmitted torque precisely and it includes a regenerative brake and a differential gear mechanism. The single-clutch human-powered joint-drive mechanism developed in this study is a system that can output forward and reverse torques and, to control the joint angle, performs servo control of the joint with one regenerative clutch by offsetting the torque using a constant-force spring. A crank-speed-sensitive spring-locking system has also been developed to implement a safe emergency stop function when the operator stops supplying power. The two-DOF human-powered robot using our systems realized planar trajectory tracking, suggesting that the position control of the end point of a multi-DOF human-powered robot is possible.

The continuous automatic calibration of musical robots is an important step toward enabling them to create accurate, reliable, and expressive performances. Several attempts have been made to achieve this using external laptops, single-board computers and off-the-shelf hardware, but these solutions have various drawbacks that preclude their use in many musical robotics contexts. This paper presents a new, custom-built embedded DSP system that is capable of up to 32 channels of high quality audio input and output, created to carry out musical information retrieval tasks on the sonic output of musical robots in real time while they are performing. The results of these analyses are continuously fed to musical robot control hardware in order to inform their performance. The design and construction of the circuit board is described, the Musical Information Retrieval (MIR)-based algorithms carried out by the board are outlined, the system's performance in representative applications are evaluated, and its various implications to the field of musical robotics and beyond are discussed. By integrating this system into new musical robots, the result is instruments that are able to `listen' to the audible results of their own actuations in real time, and continuously calibrate their actions to best represent the intentions of the programmed musical composition or live input.

Human activity recognition is a crucial ingredient in safe and efficient human-robot collaboration. In this paper, we present a new model-based human activity recognition system called logical activity recognition system (LCARS). LCARS requires much less training data compared to learning-based works. Compared to other model-based works, LCARS requires minimal domain-specific modeling effort from users. The minimal modeling is for two reasons: i) we provide a systematic and intuitive way to encode domain knowledge for LCARS and ii) LCARS automatically constructs a probabilistic estimation model from the domain knowledge. Requiring minimal training data and modeling effort allows LCARS to be easily applicable to various scenarios. We verify this through simulations and experiments.

In this paper we present a model for simulating the pushing of dirt. This is a complex problem requiring the study of the action space for the robot, a deformable model for movable earth, the interaction between the robot's pushing surface and the environment, and techniques that will allow this model to simulate such a scenario. We present our novel framework for studying this problem including the grid-based model of the environment, a simplified earth pushing robot model, and action strategies to model the pushing of dirt from one area of the environment to another.

Inspection and maintenance of equipment inside buildings, such as exit signs, bared pipelines, air vents, and fire alarms often requires a robot to reach high, hidden, or confined areas that are difficult for humans to access. Even though these tasks are easy and repeatable, they are still not automated. The Mobile Extendable Robot Arm (MERA) is a movable robot arm with a novel 2-DOF scissor mechanism for reaching a high place and positioning an end-effector. MERA is composed of a locomotion vehicle with a rotation table and a 4-DOF extender arm, itself made of two layers of the 2-DOF scissor mechanism arranged in series. Placing the end-effector at an arbitrary point in space, the 4-DOF arm possesses two degrees of redundancy, allowing access to a point from various directions and enabling obstacle avoidance. In this paper, we present the design and analysis of the 2-DOF scissor mechanism. The 2-DOF scissor mechanism has two rotary actuators for driving the base links individually; consequently, the mechanism can elongate the entire body and tilt at the center of the base shaft. However, we found that the 2-DOF scissor mechanism had a singularity; after analyzing the singularity, we propose two novel solutions to the problem.