IROS 2017 论文列表

Knowledge of externally applied forces is crucial for compliant robotic manipulators in minimally-invasive and endoluminal robotic surgery for both patient safety and controllability of the device. We developed a novel continuum manipulator which comprises hydraulic actuation. In this work we investigate the use of the hydrostatic pressure feedback inside the inflatable actuation chambers to determine the normal and shear forces which are applied to the tip of the robot. For that purpose a nonlinear finite element model is derived and experimentally validated, showing a good approximation between experiment and simulation. The model is then used to derive descriptions for the normal and shear forces applied to the robot tip. The normal force estimation shows good results over the range of experimentally validated tip angles, while the shear force estimation shows good results for small tip deflection angles with an increasing error, with the tip orientation. The algorithm indicates good applicability to force control tasks as the forces are fast to compute.

Individual team members are the building blocks of successful multi-robot teams in dynamic competitive domains. The current approach to designing a team is to divide the planning into a hierarchy by separating team coordination and task assignment - global planning - from task planning and execution - local planning. The global planner must make assumptions based on simplified models of dynamics and/or opponents, and as such certain conditions are assumed true when globally planning but are not always true at local execution time. In this paper, we describe several algorithms for intra-robot replanning that allow the individual robots to enable the conditions of their tasks. We then demonstrate improvements in task completion when the robots are capable of replanning their task(s) and their teammates' task(s) in a simplified robot soccer domain. We further show preliminary results on learning when to replan.

Service robots are being developed as a solution for the implications associated with the aging population. They are intended to be operated by non-expert users and hence human friendly interaction abilities are preferred. Humans prefer to use voice instructions that include uncertain information, lexical symbols and notions instead of instructions with precise quantitative values. Hence, service robots must be capable of interpreting such instructions in human like manner. This paper proposes a method in order to navigate a service robot inside a domestic environment in human friendly manner by using voice instructions that include phrases with uncertain information associated with relative references such as “large table”, “table left of the door” and “table close to the door”. A module called Relative Uncertainty Interpretation (RUI) module has been introduced in order to evaluate the relative references related uncertainties. The RUI module has been implemented by considering the natural tendencies of humans. Experiments have been carried out in an artificially created domestic environment and the results of the proposed system have been compared with the results of a user study in order to evaluate the performance of the proposed system.

In this paper we present a planner that interleaves free-space motion with motion in contact to reduce uncertainty. The planner finds such motions by growing a search tree in the combined space of collision-free and contact configurations. The planner reasons efficiently about the accumulated uncertainty by factoring the state in a belief over configuration and a fully observable contact state. We show the uncertainty-reducing capabilities of the planner on manipulation benchmark from the POMDP literature. The planner scales up to more complex problems like manipulation under uncertainty in seven-dimensional configuration space. We validate our planner in simulation and on a real robot.

While there has been tremendous progress in autonomous robot manipulation, environments with clutter and unknown objects remain challenging particularly for the perception algorithms that support manipulation. This paper adopts a human-aided perception paradigm and investigates alternative interactive segmentation methods to allow users to segment a target object or object part. Through a first user study (N=24) we compare four interactive segmentation methods and characterize the tradeoff between efficiency and accuracy. Next we develop a hybrid segmentation interface and integrate it into an end-to-end human-in-the-loop manipulation system. In a second user study (N=12) we compare the performance of this system to a direct gripper-control system that allows similar manipulation tasks to be performed in challenging scenes. We find that this system enables more efficient manipulation with a lower mental load on the user, while offering a similar task success rate.

Kinematic redundancy is a characteristic and beneficial property in collaborative robots nowadays as it enhances the flexibility and dexterity of the system. While the robot is manipulating an object, it is often necessary to kinematically reconfigure the robot, for example, when it obstructs the human. For this, internal or so-called null space motions can be carried out which do not affect the main task. In general, it is desirable that the human coworker can anticipate how the robot will move at any time. However, for null space motions this is typically not the case as they are non-intuitive and not suitable for interaction. In this work, we develop intuitive null space interaction behaviors for redundant manipulators, where the human can easily guide the robot. We want to provide users with a tool, that is straightforward to implement and solves real-world problems effectively. Two practical applications for an eight- and ten-DOF robot demonstrate the performance of the proposed method.

This paper demonstrates a new haptic display based on soft actuator and soft sensor. The device consists of an array rigid coupling actuator and an array tactile sensor which configured sensor located on the top of actuator. The actuator includes a frame with rigid coupling made by silicone and a dielectric elastomer actuator(DEA). The movement of the DEA is transferred to touch pad via rigid coupling. Thus, it provides a soft, comport touch feeling and eliminates the danger of applying high voltage to the human skin. The actuator can work at a wide range frequency of 0–150 Hz and produce sufficient force of 50 mN over the human hand threshold. The tactile sensor can measure the pressure, locate the objects and send the feedback signals to control the actuator. In this work, a 8×12 haptic tactile display is made with high resolution. In addition, the high voltage signal processing also developed to generate variable 0–3.5 kV, and can control individual cell by using the dynamic scanning actuation algorithm. Then, it can display any shape such as a circle, a smile/sad face, a star, etc. In the future, we will build the “emotion touch pad” system which can transfer a person's emotion to another one via internet.

Beside the output-input hysteresis, the longitudinally loaded cables of medical robotics such as RAVEN II exhibit asymmetric saturated strain-load hysteresis loops. This study investigates modeling the hysteresis nonlinearities of these cables using a stop-operator based Prandtl-Ishlinskii (SPI) model that is integrated with a memoryless function. The stop-operator based model is employed to account for the hysteresis nonlinearities, while the memoryless function is introduced to characterize saturation and asymmetric effects. A numerical example is presented to compare the properties of the proposed model with the classic SPI model. The response of the suggested model was evaluated on the hysteresis properties of two different cables subjected to triangular harmonic input of 0 to 0.001 with 6.25 × 10-5 strain/s. The characterization error of the thick cable was found as 1.55 %, while the error was calculated as 1.25 % for the thin cable. The relative significance of the proposed model was further examined by comparing the measured data with the classic SPI model. The results showed that the classic model yields substantial characterization errors when the asymmetry and saturation effects of the strain-load hysteresis loops are ignored.

Accurate insertion of fine needles is difficult due to needle deflection. Needle deflection in the lower abdomen is particularly complex, as the needle has to pass through various tissues. As the area of the bowel is dominant in lower abdominal insertion, it is important to analyze the deflection during bowel insertion and to control the needle to minimize deflection. Few studies have focused on bowel insertion. We performed a fundamental deflection analysis of needle insertion in the bowel. Moreover, we have proposed an insertion method for minimizing the needle deflection based on our analysis. First, we performed needle insertion at various insertion positions and insertion angles into the hollow-shaped bowel, and determined the trend of the needle deflection during bowel insertion. The results revealed that the needle deflection was increased due to an increase in insertion angle, and therefore insertion angle should be minimized as much as possible. However, during actual bowel needle insertion, there are many situations in which the ideal path cannot be selected due to the arrangement of the bowel loops. We proposed an insertion method that can eliminate the total needle deflections during bowel insertion by controlling the needle tip direction at the breaching of each bowel wall. The results suggest that the needle deflection can be minimized by selecting the insertion path in which the sum of each insertion angle is zero. We verified the results of this insertion method in multiple bowels in in vivo experiments, and showed that it has the potential to be used in clinical practice.

This paper presents a kinetostatic framework to analyze the grasping and in-hand object manipulation abilities of two-finger underactuated hands. The framework includes a procedure to compute the Grasp Matrix and the Hand Jacobian for objects and fingertips of arbitrary shape considering rolling contacts without slipping. The usefulness of the proposed approach is illustrated in a case study of a pair of underactuated fingers driven by a tendon-pulley differential transmission mechanism and capable of performing in-hand object manipulation. The manipulability region for different object and fingertip shapes is computed and the results are discussed.

This paper revisits the formation control problem, whereby a team of mobile robots assemble and maintain a desired geometric shape. However, the types of shapes that are realizable by a given robot team depends directly on the sensing modalities of the individual robots. For example, rigidity-based approaches make use of distance measurements, and the idea is to restrict the motion of the robots so that all inter-robot distances are maintained, thereby ensuring purely rigid motion. Rather than distances, we notice that for certain sensor classes, such as monocular pinhole cameras, only relative angle measurements are available. To this end, we introduce the notion of shape-similar motions, which constitutes a class of angle preserving motions that also preserve the shape of the formation in the sense that rigid motions as well as uniform scalings are permissible. We construct the shape-similarity matrix, whose null-space captures angle preserving motions, and show that by restricting the dimension of the null-space, we can guarantee that motions of the formation preserve the shape. Lastly, we implement a shape-similar controller on a team of differential drive mobile robots.

Structure from motion algorithms have an inherent limitation that the reconstruction can only be determined up to the unknown scale factor. Modern mobile devices are equipped with an inertial measurement unit (IMU), which can be used for estimating the scale of the reconstruction. We propose a method that recovers the metric scale given inertial measurements and camera poses. In the process, we also perform a temporal and spatial alignment of the camera and the IMU. Therefore, our solution can be easily combined with any existing visual reconstruction software. The method can cope with noisy camera pose estimates, typically caused by motion blur or rolling shutter artifacts, via utilizing a Rauch-Tung-Striebel (RTS) smoother. Furthermore, the scale estimation is performed in the frequency domain, which provides more robustness to inaccurate sensor time stamps and noisy IMU samples than the previously used time domain representation. In contrast to previous methods, our approach has no parameters that need to be tuned for achieving a good performance. In the experiments, we show that the algorithm outperforms the state-of-the-art in both accuracy and convergence speed of the scale estimate. The accuracy of the scale is around 1% from the ground truth depending on the recording. We also demonstrate that our method can improve the scale accuracy of the Project Tango's build-in motion tracking.

This paper presents a path following method for autonomous wheeled vehicles that combines iterative learning control (ILC) with nonlinear feedback linearization (FBL) to provide anticipatory control action based on stored path following errors over repeated driving trials. By implementing ILC in a fully feedback-linearized space, control corrections are applied to a transformed input, thus allowing for a single back-computation to the nonlinear vehicle's control input. Hence, the approach is comparatively easy to implement and also computationally inexpensive. We first outline the mathematical formulation for this control method and then describe field results from tests conducted by using an industrial-scale wheeled underground mining vehicle in a representative environment to demonstrate effectiveness.

We present a system to generate building information models (BIMs) of house interiors from 3D scans. The strength of our approach is its simplicity and low runtime which allows for mobile processing applications. We consider scans of single floor, Manhattan-like indoor scenes for which our method creates metric room layouts by detecting walls and performing a subsequent reasoning about their neighborhood relations. The output of our method is a 3D BIM with hierarchical semantic annotations for individual rooms being refined by walls, ceilings, floors and doors. A variety of experiments demonstrate the effectiveness of our approach. Our reconstruction results compare well to other state-of-art methods in both reconstruction quality as well as runtime.

We aim to automatically identify all individual leaves in a monocotyledon image. Leaf identification is one of key technologies to acquire plant phenotypes such as a leaf length, a leaf count, and a growth rate. However, it is challenging to identify individual leaves from a monocotyledonous plant image due to their complicated occlusion and similar colors. We adopt a graph-theoretical approach to overcome the leaf occlusion and the color similarity between leaves, and apply a combinatorial optimization technique to simultaneously identify all individual leaves based on local and global characteristics of plants. We propose a plant-wide global optimization to identify all true leaves in a plant, which is formulated as a minimum path cover problem that we call the phytomorphological graph reconstruction. A phytomorphological graph of a plant image is a graph reflecting the plant's structure and is constructed through a plant region extraction and a skeletonization. All candidate leaf paths in the graph are extracted and their leaf path likelihoods are computed from the graph, where the leaf path likelihood means a measure of similarity with true leaves. The candidate leaf paths and their path likelihoods are used in the graph reconstruction process in order to find an optimal subset of the leaf paths which are similar to true leaves and can restore the phytomorphological graph as completely as possible. Experiments show that our proposed system effectively identifies individual leaves from a single 2-dimensional image of rice plants, which enables us to take an accurate and efficient high-throughput measurement of phenotypes for plants.

Visual scene understanding is a crucial skill for robots, yet difficult to achieve. Recently, Convolutional Neural Networks (CNN), have shown success in this task. However, there is still a gap between their performance on image datasets and real-world robotics scenarios. In particular, a-priori training is on a bounded set of object categories, while in many unstructured tasks new objects are encountered. We present a novel paradigm for incrementally improving a robot's visual perception through active human-robot interaction. In this paradigm, the user introduces novel objects to the robot by means of pointing and voice commands. Given this information, the robot visually explores the object and adds images from it to re-train the perception module. Our method leverages state of the art Convolutional Neutal Networks — CNNs from offline batch learning, human guidance, robot exploration and incremental on-line learning.

Industrial robotic manipulators can be augmented by a micro-positioning unit in order to increase their precision resulting in a so called macro-micro-manipulator. The micro-positioning unit is typically driven by piezoelectric actuators due to their beneficial properties. However, contact forces during interaction tasks induce deviations from the nominal path that can not be observed due to compliance, lack of sensors in the micro-positioning unit, or unknown interaction dynamics in constrained environments. In this paper, a model-free and decoupled disturbance rejection controller via visual feedback for macro-micro-manipulators is presented. An external stereoscopic vision system is employed to detect deviations from the nominal trajectory. We outline an image segmentation algorithm and the utilized camera calibration technique is based on two-view geometry. Afterwards, the disturbance rejection controller including visual feedback for the macro-micro-manipulator is described. In order to demonstrate the 3D capability of the proposed approach, a microscopic staircase is milled. For comparison, the milling experiment is executed without and with active disturbance rejection by the micro-positioning unit in order to show the increase in precision during the milling task. Results show that the arithmetic mean roughness falls below 2 μm for the step profiles and the maximum surface height deviation is less than ±10 μm for each steps.

In human-robot collaborative tasks, incorporating qualitative information provided by humans can greatly enhance the robustness and efficacy of robot state estimation. We introduce an algorithmic framework to model qualitative information as quantitative constraints on and between states. Our approach, named Sequentially Constrained Hamiltonian Monte Carlo, integrates Hamiltonian dynamics into Sequentially Constrained Monte Carlo sampling. We are able to generate samples that satisfy arbitrarily complex, non-smooth and discontinuous constraints, which in turn allows us to support a wide range of qualitative information. We evaluate our approach for constrained sampling qualitatively and quantitatively with several classes of constraints. SCHMC significantly outperforms the Metropolis-Hastings algorithm (a standard Markov Chain Monte Carlo (MCMC) method) and the Hamiltonian Monte Carlo (HMC) method, in terms of both the accuracy of the sampling (for satisfying constraints) and the quality of approximation. Compared to Sequentially Constrained Monte Carlo (SCMC), which supports similar kinds of constraints, our SCHMC approach has faster convergence rates and lower parameter sensitivity.

Local scan registration approaches commonly only utilize ego-motion estimates (e.g. odometry) as an initial pose guess in an iterative alignment procedure. This paper describes a new method to incorporate ego-motion estimates, including uncertainty, into the objective function of a registration algorithm. The proposed approach is particularly suited for feature-poor and self-similar environments, which typically present challenges to current state of the art registration algorithms. Experimental evaluation shows significant improvements in accuracy when using data acquired by Automatic Guided Vehicles (AGVs) in industrial production and warehouse environments.