IROS 2018 Papers

In this paper we describe a control strategy for a user-adaptive human-robot system for an intelligent robotic Mobility Assistive Device (MAD)using raw data from a single laser-range-finder (LRF)mounted on the MAD and scanning the walking area. The proposed control architecture consists of three modules. In the first module, a previously proposed methodology (termed IMM-PDA-PF)delivers the augmented human state estimation of the user by providing robust leg tracking and on-line estimation of the human gait phases. This information is processed at the next module for providing the pathological gait parametrization and characterization, by computing specific gait parameters for each gait cycle. These gait parameters form the feature vector that classifies the user in a certain class related to risk of fall. Those are of particular significance to the system, since the gait parameters and the respective class are used in the third module, i.e. the human-robot formation controller, in order to adapt the desired formation of the human-robot system, by selecting the appropriate control variables. The experimental evaluation comprises gait data from real patients, and demonstrates the stability of the human-robot formation control, indicating the importance of incorporating an on-line gait characterization of the user, using non-wearable and non-invasive methods, in the context of a robotic MAD.

Robotic telemanipulators are already widely used in nuclear decommissioning sites for handling radioactive waste. However, currently employed systems are still extremely primitive, making the handling of these materials prohibitively slow and ineffective. As the estimated cost for the decommissioning and clean-up of nuclear sites keeps rising, it is clear that one would need faster and more effective approaches. Towards this goal, in this paper we present the user evaluation of a recently proposed haptic-enabled shared-control architecture for telemanipulation. An autonomous algorithm regulates a subset of the slave manipulator degrees of freedom (DoF) in order to help the human operator in grasping an object of interest. The human operator can then steer the manipulator along the remaining null-space directions with respect to the main task by acting on a grounded haptic interface. The haptic cues provided to the operator are designed in order to inform about the feasibility of the user's commands with respect to possible constraints of the robotic system. In this paper we compared this shared-control architecture against a classical 6-DOF teleoperation approach in a real scenario by running experiments with 10 subjects. The results clearly show that the proposed shared-control approach is a viable and effective solution for improving currently-available teleoperation systems in remote telemanipulation tasks.

To improve the efficiency of surgical trajectory segmentation for robot learning in robot-assisted minimally invasive surgery, this paper presents a fast unsupervised method using video and kinematic data, followed by a promoting procedure to address the over-segmentation issue. Unsupervised deep learning network, stacking convolutional auto-encoder, is employed to extract more discriminative features from videos in an effective way. To further improve the accuracy of segmentation, on one hand, wavelet transform is used to filter out the noises existed in the features from video and kinematic data. On the other hand, the segmentation result is promoted by identifying the adjacent segments with no state transition based on the predefined similarity measurements. Extensive experiments on a public dataset JIGSAWS show that our method achieves much higher accuracy of segmentation than state-of-the-art methods in the shorter time.

In the last decade, many medical companies and research groups have tried to convert passive capsule endoscopes as an emerging and minimally invasive diagnostic technology into actively steerable endoscopic capsule robots which will provide more intuitive disease detection, targeted drug delivery and biopsy-like operations in the gastrointestinal(GI) tract. In this study, we introduce a fully unsupervised, realtime odometry and depth learner for monocular endoscopic capsule robots. We establish the supervision by warping view sequences and assigning the re-projection minimization to the loss function, which we adopt in multi-view pose estimation and single-view depth estimation network. Detailed quantitative and qualitative analyses of the proposed framework performed on non-rigidly deformable ex-vivo porcine stomach datasets proves the effectiveness of the method in terms of motion estimation and depth recovery.

Object proposal that detects candidate bounding boxes of objects in images is an effective way of accelerating object recognition in the robot/computer vision area. We propose an accurate and fast object proposal method using depth images. Existing proposal methods can be roughly divided into two categories: window scoring and object region extraction. The window scoring methods usually have higher efficiency than object region extraction methods. The previous methods using RGB images detect an excessive number of boxes due to edges of texture objects. These methods also may misdetect overlapping objects as one candidate bounding box. To tackle these problems, we propose a novel and effective objectness measure using depth images. The proposed method evaluates objectness by using depth boundary density difference between inner and outer regions of a candidate bounding box. We also consider the uniformity of the outer boundary density in a candidate bounding box to divide overlapping objects into individual candidate bounding boxes. Our reasonable assumption here is that the depth boundary of an object has a closed loop. Our experiments show significant performance gains over existing RGB and RGB-D object proposal methods on the challenging toy-dataset [1] of complex crowded scenes.

Fusing visual information with inertial measurements for state estimation has aroused major interests in recent years. However, combining a robust estimation with computational efficiency remains challenging, specifically for low-cost aerial vehicles in which the quality of the sensors and the processor power are constrained by size, weight and cost. In this paper, we present an innovative filter for stereo visual inertial odometry building on: (i) the recently introduced stereo multistate constraint Kalman filter; (ii) the invariant filtering theory; and (iii) the unscented Kalman filter (UKF) on Lie groups. Our solution combines accuracy, robustness and versatility of the UKF. We then compare our approach to state-of-art solutions in terms of accuracy, robustness and computational complexity on the EuRoC dataset and a challenging MAV outdoor dataset.

In this paper, we propose the design of an exoskeleton with support at the knee joint and lower torso for sit-to-stand and stand-to-sit (STS) posture transitions; devised for users with spinal cord injury and other complete lower-body impairments. The STS transitions assistance is achieved through a power transfer mechanism that synchronizes knees and lumbar motion through a cable-driven pulley system. We analyze the human body dynamics in the posture transition with a rigid link model and the interaction interface with the exoskeleton through an impedance model for producing a passive system voluntarily controlled by natural motions of the upper body. Therefore, allowing the potential users to achieve STS transitions with their body residual capabilities without an external power source. Instead, transferring power from their upper-body to lower-body, herewith, controlling a passive energy storage. A prototype was constructed and evaluated with seven healthy subjects observing the proposed motion and muscle activity during the STS transitions. The results show a significant reduction in the muscle activity evaluated, at the erector spinae, gluteus maximus and rectus femoris, with reductions between 30% to 50% at the p <; 0.01 level comparing STS transitions with and without the exoskeleton support. Concluding that the STS transitions support is feasible with the passive exoskeleton envisioned for applications in upright locomotion, STS training, and rehabilitation.

Using an Unmanned Aerial Systems (UAS) to autonomously deploy soil sensors enables their installation in otherwise hard to access locations. In this paper, we present a system that integrates a UAS and a digging mechanism which can carry, secure, and install a small sensor into dirt effectively and efficiently. The integrated system includes 1) a low profile, light-weight, inexpensive auger mechanism, 2) a sensor carrying and deploying mechanism with low power consumption, and 3) sensors and software that control and evaluate the auger performance during digging. When tested on a suite of target soils and a target depth of 120mm, the system achieved a success rate of 100% for indoor tests and 92.5% for outdoors, verifying the potential of the approach.

In this paper, we propose to use unit quaternions to represent point features in visual navigation. Contrary to the Cartesian 3D representation, the unit quaternion can well represent features at both large and small distances from the camera without suffering from convergence problems. Contrary to inverse-depth, homogeneous points, or anchored homogeneous points, the unit quaternion has error state of minimum dimension of three. In contrast to prior representations, the proposed method does not need to approximate an initial infinite depth uncertainty. In fact, the unit-quaternion error covariance can be initialized from the initial feature observations without prior information, and the initial error-states are not only bounded, but the bound is identical for all scene geometries. To the best of our knowledge, this is the first time bearing-only recursive estimation (in covariance form) of point features has been possible without using measurements to initialize error covariance. The proposed unit quaternion-based representation is validated on numerical examples.

Bearing only cooperative localization has been used successfully on aerial and ground vehicles. In this paper we present an extension of the approach to the underwater domain. The focus is on adapting the technique to handle the challenging visibility conditions underwater. Furthermore, data from inertial, magnetic, and depth sensors are utilized to improve the robustness of the estimation. In addition to robotic applications, the presented technique can be used for cave mapping and for marine archeology surveying, both by human divers. Experimental results from different environments, including a fresh water, low visibility, lake in South Carolina; a cavern in Florida; and coral reefs in Barbados during the day and during the night, validate the robustness and the accuracy of the proposed approach.

The maintenance and inspection of the flooded shafts, specially coal ones, is an important environmental problem. There are thousands of shafts of this type in Europe with the danger of pollution, flood and collapse. This paper presents some of the main ongoing works of the EU project STAMS that develop an autonomous underwater robotic system for periodic monitoring of flooded shafts in hazardous and complex conditions. The accurate navigation is very cluttered at 1.000 m depth conditions, where minimum visibility and unexpected obstacles are some of the difficulties to overcome. We are going beyond classical navigation approaches using only few sensor information. Another innovation is the installation of Reference Points (RPs) in the shaft's walls by the robot using a special fixation mechanism. The specially designed cases of the RPs allow to house specific sensors and help in the navigation, and will be used in periodic monitoring and assessment of the mine shafts. The positioning and attachment of these RPs is another contribution of this paper.

FroBot can locomote both on land and underwater based on its dual swing-legs propulsion mechanism. This paper presents the dynamic model, experimental studies, and control strategies of FroBot underwater. In this work, an experimental setup consisting of two-degree-of-freedom(2DOF) robotic swing-legs is built to study the model of FroBot underwater. We first improve the dynamic model of caudal fins based on the Morison equation. Combined with experimental data, we optimize the model parameters and then obtain the optimal control strategy of uniform swing. In addition, we apply the CPGs control strategy and improve it based on the FroBot model. These two control strategies have their advantages and demonstrate the potential for future use in control applications.

In real-world robotics, motion planning remains to be an open challenge. Not only robotic systems are required to move through unexplored environments, but also their manoeuvrability is constrained by their dynamics and often suffer from uncertainty. One approach to overcome this problem is to incrementally map the surroundings while, simultaneously, planning a safe and feasible path to a desired goal. This is especially critical in underwater environments, where autonomous vehicles must deal with both motion and environment uncertainties. In order to cope with these constraints, this work proposes an uncertainty-based framework for mapping and planning3 feasible motions online with probabilistic safety-guarantees. The proposed approach deals with the motion, probabilistic safety, and online computation constraints by (i) incrementally representing the environment as a collection of local maps, and (ii) iteratively (re)planning kinodynamically-feasible and probabilistically-safe paths to goal. The proposed framework is evaluated on the Sparus II, a nonholonomic torpedo-shaped AUV, by conducting simulated and real-world trials, thus proving the efficacy of the method and its suitability even for systems with limited on-board computational power.

Leader-Follower is a hierarchical form of multi-robot formation control, where each robot aims to maintain specific predefined angle and distance from one or more robots in the team (referred to as its local leaders), while a single robot is selected to lead the entire formation to a desired destination. When the robots are given a specific formation to maintain, their goal is usually to minimize the deviation from this desired formation (maximizing the accuracy) during their journey. Previous work has considered optimality in an uncertain environment only in centralized setting (or using perfect, or almost perfect communication). In this paper we examine the problem of optimal multi-robot formation control in a distributed setting, while accounting for two challenges: sensory uncertainty and absence of communication. Specifically, we present an algorithm that allows each individual robot to estimate the overall formation accuracy of the other robots in their field of view via a tree reconstruction algorithm. The algorithm is used to select the most accurate local leader, or to generate virtual local leader via a weighted average of all visible robots. We provide both theoretical analysis and an extensive empirical evaluation (in ROS/Gazebo simulated environment) showing the effectiveness of the two approaches.

This paper presents a deep network based unsupervised visual odometry system for 6-DoF camera pose estimation and finding dense depth map for its monocular view. The proposed network is trained using unlabeled binocular stereo image pairs and is shown to provide superior performance in depth and ego-motion estimation compared to the existing state-of-the-art. This is achieved by introducing a novel objective function and training the network using temporally alligned sequences of monocular images. The objective function is based on the Charbonnier penalty applied to spatial and bi-directional temporal reconstruction losses. The overall novelty of the approach lies in the fact that the proposed deep framework combines a disparity-based depth estimation network with a pose estimation network to obtain absolute scale-aware 6-DoF camera pose and superior depth map. According to our knowledge, such a framework with complete unsupervised end-to-end learning has not been tried so far, making it a novel contribution in the field. The effectiveness of the approach is demonstrated through performance comparison with the state-of-the-art methods on KITTI driving dataset.

This paper introduces electrostatic and ultrasonic techniques to clean dust and other contaminants from the surface of a gecko-like, microstrutured adhesive. The result is a non-destructive, non-contact cleaning method that will afford robotic grippers, climbing robots, and perching robots the ability to operate in real-world environments. Experimental results show that the cleaning efficiency for three different sizes of glass beads, 53-75 μm, 75-90 μm, and 90-106 μm, ranges between 75-99% when using a combination of electrostatic and ultrasonic cleaning. This is a far higher efficiency than when using electrostatic repulsion alone. Experiments also demonstrate an approximately 33% recovery in shear stress on a flat glass for a contaminated directional gecko-like adhesive after contact with a dusty table when electrostatic/ultrasonic cleaning was used. Finally, by applying this method on a robotic gripper, we observed an 18% recovery in normal adhesion on a flat glass substrate.

This paper describes the UX-1 underwater mine exploration robotic system under development in the context of the UNEXMIN project. UNEXMIN is an international innovation action funded under the EU H2020 program, aiming to develop new technologies and services allowing the exploration of flooded underground mines. The system is comprised by the UX-1 robot prototype, launch and recovery system, command and control subsystem and a data management and post-processing computational infrastructure. The UX-1 robot is a small spherical robot equipped with a multibeam sonar, five digital cameras and rotating laser line structured light systems. It is capable of obtaining an accurate point cloud of the surrounding environment along with high resolution imagery. A set of mineralogy, water parameters and geophysical sensors was also developed in order to obtain a more comprehensive mine model. These comprise a multi-spectral camera, electro-conductivity, pH, magnetic field sensors, a subbottom sonar, total natural gamma-ray detector, UV-light for fluorescent observation and a water sampling unit. The design of the system is presented along with the robot design. Some preliminary results are also presented and discussed.

We introduce UNDERWORLDS, a novel lightweight framework for cascading spatio-temporal situation assessment in robotics. UNDERWORLDS allows programmers to represent the robot's environment as real-time distributed data structures, containing both scene graphs (for representation of 3D geometries) and timelines (for representation of temporal events). UNDERWORLDS supports cascading representations: the environment is viewed as a set of worlds that can each have different spatial and temporal granularities, and may inherit from each other. UNDERWORLDS also provides a set of high-level client libraries and tools to introspect and manipulate the environment models. This article presents the design and architecture of this open-source tool, and explores some applications, along with examples of use.

This paper considers a new, complex problem of UAV/UGV collaborative efforts to search and capture attackers under uncertainty. The goal of the defenders (UAV/UGV team) is to stop all attackers as quickly as possible, before they arrive at their selected goal. The uncertainty considered is twofold: the defenders do not know the attackers' location and destination, and there is also uncertainty in the defenders' sensing. We suggest a real-time algorithmic framework for the defenders, combining entropy and stochastic-temporal belief, that aims at optimizing the probability of a quick and successful capture of all of the attackers. We have empirically evaluated the algorithmic framework, and have shown its efficiency and significant performance improvement compared to other solutions.