ICRA 2015 论文列表

Robotic manipulation of highly deformable materials is inherently challenging due to the need to maintain tension and the high dimensionality of the state of the material. Past work in this area mostly focuses on generating a detailed model for the material and its interaction with the robot, then using the model to construct a motion plan. In this paper, we take a different approach by using only sensor feedback to dictate the robot motion. We consider the collaborative manipulation of a deformable sheet between a person and a dual-armed robot (Baxter by Rethink Robotics). The robot is capable of contact sensing via joint torque sensors and is equipped with a head-mounted RGBd sensor. The robot senses contact force to maintain tension of the sheet, and in turn comply to the human motion. This is akin to handling a tablecloth with a partner but with one's eyes closed. To improve the response, we use the RGBd sensor to detect folds, and command the robot to move in an orthogonal direction to smooth them out. This is like handling cloth by looking at the cloth itself. Both controllers are able to follow human motion without excessive crimps in the sheet, but as expected, the hybrid controller combining force and vision outperforms the force controller alone in terms of tension force transient. The ability to quickly detect the state of the deformable material also enables more complex manipulation strategies in the future.

We present a coactive algorithm for learning a human expert's preferences in planning trajectories for information gathering in scientific autonomy domains. The algorithm learns these preferences by iteratively presenting solutions to the expert and updating an estimated utility function based on the expert's improvements. We apply these algorithms, in the context of underwater data collection, using a pair of risk and reward maps. In simulated trials, the algorithm successfully learns the underlying weighting behind a utility map used by a human planning trajectories. We also present experimental trials demonstrating the algorithm using a temperature and depth monitoring task in an inland lake with an autonomous surface vehicle. This work shows it is possible to design algorithms for autonomous navigation with reward functions that capture the essence of a human's preferences.

A new manipulation approach, referred to as interleaved continuum-rigid manipulation, which combines inherently safe, flexible actuated segments with more precise embedded rigid-link joints has recently been introduced [1], [2]. The redundantly actuated manipulator possesses the safety characteristics inherent in flexible segment devices while gaining some of the performance attributes of rigid-link joint systems. In this paper, we describe a general controller developed for an interleaved manipulator. The controller is implemented on a clinically-relevant prototype, the results of which demonstrate the advantages of an interleaved manipulator. We also consider kinematic drivers of the interleaved manipulator workspace, showing that careful kinematic considerations can substantially improve manipulator workspace and task accuracy.

In this work we present a method of systematically selecting regions of a haptic workspace to be used for navigation of large virtual environments. Existing navigational techniques require the partitioning of the workspace into a region of manipulation and a separate region for navigation tasks. These techniques, however, have neglected to describe an effective way to implement these concepts in a device specific manner. We propose a two step technique to define these regions based on the mechanical properties of pre-existing devices. In the first step, the kinematic properties of the device are analyzed across the entirety of the physical workspace. A well-behaved region that favours isotropic mapping from the joint actuators to the generalized forces at the end effector is selected. Having ensured high force fidelity within this region, we then perform a second step analyzing the device dynamic properties. We further subdivide the navigational space into a region with suitable inertial properties in which manipulation tasks may be performed. This procedure generates a haptic display with a highly transparent haptic manipulation region within which a user can interact with a virtual environment. This manipulation region is bounded by a well-behaved navigational region that ensures adequate force transmission. To demonstrate this technique, navigation and manipulation spaces are generated and described for the planar and spatial cases.

Transurethral resection of bladder tumors (TURBT) presents surgeons with challenges of limited tool dexterity. This paper investigates the limitations of dexterity and resection reach and accuracy within the intra-vesicular space of the bladder. The paper assumes the kinematics and geometry of current tools used for TURBT. The study presents a kinematic modeling framework and a simulation evaluation that aim to elucidate the limitations of current surgical tools. The kinematic framework also proposes a method for analyzing resection dexterity and accuracy in different regions of the bladder. The results demonstrate resection dexterity deficiencies in the areas neighboring the bladder neck and substantially higher dexterity in superior regions. In addition, the results of this work provide a currently missing quantified dexterity evaluation baseline for expected performance during manual TURBT against which future devices and robotic-assisted systems for resection can be compared.

This paper presents a robust target tracking algorithm for a mobile sensor with a fan-shaped field of view and finite sensing range. The goal of the mobile robot is to track a moving target such that the probability of losing the target is minimized. We assume that the distribution of the next position of a moving target can be estimated using a motion prediction algorithm. If the next position of a moving target has the Gaussian distribution, the proposed algorithm can guarantee the tracking success probability. In addition, the proposed method minimizes the moving distance of the mobile robot based on a bound on the tracking success probability. While the problem considered in this paper is a non-convex optimization problem, we derive analytical solutions which can be easily solved in real-time. The performance of the proposed method is evaluated extensively in simulation and validated in pedestrian following experiments using a Pioneer mobile robot with a Microsoft Kinect sensor.

This paper describes the propulsion of the catalytic tubular microjet using Navier-Stokes equations. Especially, the thrust capability of the microjet is outstanding compared with the other microsystems, but remains only partially understood. Studies have identified the internal precursory mechanisms of the propulsion of the microjet: its inner wall catalyzes the dismutation of aqueous hydrogen peroxide, and an oxygen bubble is then formed and migrates towards its widest opening. This impulses the propulsion of the microjet towards the opposite direction. However, the precise propellant role of the liquid surrounding the jet remains misunderstood. The same goes for the inner wall of the vessel in which the jet navigates, especially in narrowed environment. This article discusses these aspects in a simplified theoretical framework. Calculations are performed by explicit computation of Navier-Stokes equations. The obtained theoretical outcome are in good agreement with experimental results in the literature.

We approach a problem of motion planning and stabilization for a benchmark example, known as the “Butterfly” robot. It was proposed as a benchmark challenge for developing systematic techniques for nonprehensile rolling manipulation. A dynamical model of the underactuated system with a non-unilateral contact is derived. The recently proposed methodologies, known as virtual-holonomic-constraints-based motion planning and transverse-linearization-based orbital stabilization, are appropriately extended to suit the task. Finally, the feasibility is demonstrated through a hardware implementation and an experimental validation of the concept.

Field robots used in unstructured and dynamic environments - and teleoperation have shifted into the focus of a variety of industrial branches in the past few years. The lack of space in the atomic industry, on oil platforms and in space applications demands additional adaptations to current robotic setups. In this paper a MMSS (Multi-Master-Single-Slave) haptic teleoperation system is proposed through which one operator using two master arms can manipulate objects in a cooperative way via one slave robot and a virtual gripping point. To ease the execution of a peg-in-hole task of big objects, a task allocation in the cartesian frame of the virtual gripping point is introduced additionally. The stability of this multilateral system with time delay is guaranteed by the Time Domain Passivity Approach. Therefore the system is divided into several modular subsystems which renders the system easily adaptable to other scenarios.

The use of shape from silhouette for reconstruction tasks is plagued by two types of real-world errors: camera calibration error and silhouette segmentation error. When either error is present, we call the problem the Shape from Inconsistent Silhouette (SfIS) problem. In this paper, we show how small camera calibration error can be corrected when using a previously-published SfIS technique to generate a reconstruction, by using an Iterative Closest Point (ICP) approach. We give formulations under two scenarios: the first of which is only external camera calibration parameters rotation and translation need to be corrected for each camera and the second of which is that both internal and external parameters need to be corrected. We formulate the problem as a 2D-3D ICP problem and find approximate solutions using a nonlinear minimization algorithm, the Levenberg-Marquadt method. We demonstrate the ability of our algorithm to create more representative reconstructions of both synthetic and real datasets of thin objects as compared to uncorrected datasets.

Robot calibration is to improve the accuracy of the robot model so as to achieve better positioning accuracy within the robot work cell. Model based calibration approaches are in general limited to compensating for geometric errors and are unable to compensate for error sources that do not fit within the proposed robot model. In order to compensate for the unmodeled error sources, a Radial Basis Function (RBF) Neural Network (NN) augmented robot model is proposed together with a two stage calibration process for training the NN. A simulation and an experimental study are conducted to verify the effectiveness of the proposed solution.

Automatic reconstruction of 3D models from images using multi-view Structure-from-Motion methods has been one of the most fruitful outcomes of computer vision. These advances combined with the growing popularity of Micro Aerial Vehicles as an autonomous imaging platform, have made 3D vision tools ubiquitous for large number of Architecture, Engineering and Construction applications among audiences, mostly unskilled in computer vision. However, to obtain high-resolution and accurate reconstructions from a large-scale object using SfM, there are many critical constraints on the quality of image data, which often become sources of inaccuracy as the current 3D reconstruction pipelines do not facilitate the users to determine the fidelity of input data during the image acquisition. In this paper, we present and advocate a closed-loop interactive approach that performs incremental reconstruction in real-time and gives users an online feedback about the quality parameters like Ground Sampling Distance (GSD), image redundancy, etc on a surface mesh. We also propose a novel multi-scale camera network design to prevent scene drift caused by incremental map building, and release the first multi-scale image sequence dataset as a benchmark. Further, we evaluate our system on real outdoor scenes, and show that our interactive pipeline combined with a multi-scale camera network approach provides compelling accuracy in multi-view reconstruction tasks when compared against the state-of-the-art methods.

This paper reports on a 3D photomosaicing pipeline using data collected from an autonomous underwater vehicle performing simultaneous localization and mapping (SLAM). The pipeline projects and blends 2D imaging sonar data onto a large-scale 3D mesh that is either given a priori or derived from SLAM. Compared to other methods that generate a 2D-only mosaic, our approach produces 3D models that are more structurally representative of the environment being surveyed. Additionally, our system leverages recent work in underwater SLAM using sparse point clouds derived from Doppler velocity log range returns to relax the need for a prior model. We show that the method produces reasonably accurate surface reconstruction and blending consistency, with and without the use of a prior mesh. We experimentally evaluate our approach with a Hovering Autonomous Underwater Vehicle (HAUV) performing inspection of a large underwater ship hull.

Symbolic reasoners generate plans which are often not exploiting the robot capabilities and are sensitive to runtime disturbances. This work proposes a scheduler as an interface between a discrete, symbolic plan and a motion control based on constraint optimization. Acting as a local reasoner, the scheduler valuates a set of predicates to decide when an action will be executed. Given a task specification which describes how the action should be realized, the scheduler configures the controller at runtime. A demonstration will be provided considering an “open drawer” scenario.

This work aims for bottom-up and autonomous development of symbolic planning operators from continuous interaction experience of a manipulator robot that explores the environment using its action repertoire. Development of the symbolic knowledge is achieved in two stages. In the first stage, the robot explores the environment by executing actions on single objects, forms effect and object categories, and gains the ability to predict the object/effect categories from the visual properties of the objects by learning the nonlinear and complex relations among them. In the next stage, with further interactions that involve stacking actions on pairs of objects, the system learns logical high-level rules that return a stacking-effect category given the categories of the involved objects and the discrete relations between them. Finally, these categories and rules are encoded in Planning Domain Definition Language (PDDL), enabling symbolic planning. We realized our method by learning the categories and rules in a physics-based simulator. The learned symbols and operators are verified by generating and executing non-trivial symbolic plans on the real robot in a tower building task.

Controllers based on neuromuscular models hold the promise of energy-efficient and human-like walkers. However, most of them rely on optimizations or cumbersome hand-tuning to find controller parameters which, in turn, are usually working for a specific gait or forward speed only. Consequently, designing neuromuscular controllers for a large variety of gaits is usually challenging and highly sensitive. In this contribution, we propose a neuromuscular controller combining reflexes and a central pattern generator able to generate gaits across a large range of speeds, within a single optimization. Applying this controller to the model of COMAN, a 95 cm tall humanoid robot, we were able to get energy-efficient gaits ranging from 0.4 m/s to 0.9 m/s. This covers normal human walking speeds once scaled to the robot height. In the proposed controller, the robot speed could be continuously commanded within this range by changing three high-level parameters as linear functions of the target speed. This allowed large speed transitions with no additional tuning. By combining reflexes and a central pattern generator, this approach can also predict when the next strike will occur and modulate the step length to step over a hole.

Drawing inspiration from flight behavior in biological settings (e.g. territorial battles in dragonflies, and flocking in starlings), this paper demonstrates two strategies for coverage and flocking. Using earlier theoretical studies on mutual motion camouflage, an appropriate steering control law for area coverage has been implemented in a laboratory test-bed equipped with wheeled mobile robots and a Vicon high speed motion capture system. The same test-bed is also used to demonstrate another strategy (based on local information), termed topological velocity alignment, which serves to make agents move in the same direction. The present work illustrates the applicability of biological inspiration in the design of multi-agent robotic collectives.

Activity prediction is an essential task in practical human-centered robotics applications, such as security, assisted living, etc., which targets at inferring ongoing human activities based on incomplete observations. To address this challenging problem, we introduce a novel bio-inspired predictive orientation decomposition (BIPOD) approach to construct representations of people from 3D skeleton trajectories. Our approach is inspired by biological research in human anatomy. In order to capture spatio-temporal information of human motions, we spatially decompose 3D human skeleton trajectories and project them onto three anatomical planes (i.e., coronal, transverse and sagittal planes); then, we describe short-term time information of joint motions and encode high-order temporal dependencies. By estimating future skeleton trajectories that are not currently observed, we endow our BIPOD representation with the critical predictive capability. Empirical studies validate that our BIPOD approach obtains promising performance, in terms of accuracy and efficiency, using a physical TurtleBot2 robotic platform to recognize ongoing human activities. Experiments on benchmark datasets further demonstrate that our new BIPOD representation significantly outperforms previous approaches for real-time activity classification and prediction from 3D human skeleton trajectories.

This paper presents a new control strategy to control a group of dog-like robots to drive a herd of non-cooperative sheep-like agents to a goal region in the environment. The sheep-like agents, which may be biological or robotic, respond to the presence of the dog-like robots with a repelling potential field common in biological models of the behavior of herding animals. Our key insight in designing control laws for the dog-like robots is to enforce geometrical relationships that allow for the combined dynamics of the dogs and sheep to be mapped to a simple unicycle robot model. We prove convergence of a single sheep to a desired goal region using two or more dogs, and we propose a control strategy for the case of any number of sheep driven by two or more dogs. Simulations in Matlab and hardware experiments with Pololu m3pi robots demonstrate the effectiveness of our control strategy.