IROS 2016 论文列表

Robots could benefit from maps that represent haptic properties of their surroundings. By touching locations with tactile sensors, robots can infer haptic properties of their surroundings, but touching all locations would be prohibitive. We present an algorithm that uses touch and vision to efficiently produce a dense haptic map. Our approach assumes that surfaces near a robot that are visually similar are more likely to have similar haptic properties. Given an image and sparse haptic labels, our algorithm uses a dense conditional random field (CRF) to produce a haptic map with labels for all image pixels. In an evaluation using images with idealized haptic labels, our algorithm substantially outperformed a previous algorithm. It also enabled a real robot to label leaves and trunks after reaching into artificial foliage. In addition, we show that our algorithm can use a convolutional neural network (CNN) for material recognition from Bell et al. [1] that we modified and fine-tuned. This CNN provides estimated probabilities for haptic labels using vision alone, which enables the algorithm to infer haptic labels before the robot makes contact with anything. In our evaluation, using this CNN further improved performance.

This paper presents preliminary results of a new robotic wrist for minimally invasive surgery. This wrist is a high-dexterity miniature robot, able to provide simultaneously the grasping/cutting (1-DoF) and rotations capabilities with 3-DoF. The grasping function is insured by the folding of the top platform of a parallel structure. The grasping capability of the wrist is part of the mechanical structure itself and can be fully controlled by external actuators. In order to validate this original approach, an experimental prototype has been fabricated using 3D printing technology at a larger scale. The inverse kinematic model has been developed and the workspace analysis was accomplished to assess the capabilities of the realized system. Finally, experimental tests have been also carried out for validating the proposed structure.

This paper describes the holistic phase model of the `4 Robotic Revolutions' - disruptive waves of evolution in robotics and automation - and their impact on society, economy and other areas of human life over the next 50 years. Furthermore, an explanation is provided, why a new Generation `R' of Robotic Natives will grow up in daily contact with automation technology perceiving technology as valuable enrichments for their lives. The paper closes with an outlook into reasons why humankind has to ignite a holistic discourse about the responsible application of these disruptive technologies in order to shape a sustainable future enhanced (and not threatened) by robotics and automation. In consequence, the need for self-regulation in the sense of Technology and Robotic Governance will arise.

A `region' is an important concept in interpreting 3D point cloud data since regions may correspond to objects in a scene. To correctly interpret 3D point cloud data, we need to partition the dataset into regions that correspond to objects or parts of an object. In this paper, we present a region growing approach that combines global (topological) and local (color, surface normal) information to segment 3D point cloud data. Using ideas from persistent homology theory, our algorithm grows a simplicial complex representation of the point cloud dataset. At each step in the growth process we compute the zeroth homology group of the complex, which corresponds to the number of connected components, and use color and surface normal statistics to build regions. Lastly, we extract out the segmented regions of the dataset. We show that this method provides a stable segmentation of point cloud data in the presence of noise and poorly sampled data, thus providing advantages over contemporary region-based segmentation techniques.

Epidural anaesthesia is a medical gesture commonly performed by an anaesthesiologist. However, it remains one of the most difficult gestures to master for medical students. Given the lack of sufficiently realistic training devices available for future physicians, we propose a new haptic simulator which reproduces the haptic sensations felt by anaesthesiologists when performing this kind of operation. The originality of this simulator is the coupling of a Geomagic Touch® device with a pneumatic cylinder to reproduce the “Loss of Resistance” phenomenon which helps the physician to control the needle depth. In this paper, we introduce the parametric 3D model of the region of interest and the control laws used jointly. Even though this device could not reproduce the right level of forces required in this type of anaesthesia, an anaesthesiologist involved in the project gave positive feedback about its haptic tissue rendering.

Perception is the main key in enabling robots to react to and interact with their environment. Particularly, for multi-floor operations, the robot must robustly detect and localize stairs to allow for safe climbing. In this paper, we develop a graph-based stairway detection method for point cloud data, that can detect a large variety of stairways. Our approach first segments planar regions and extracts the stair tread- and stair riser-shaped segments. With these segments, a dynamic graph model is initialized that is used to detect stairs including the railing system in the surroundings. We show that our system can accurately detect and localize different stairways from a variety of different positions, including descending stairs. Our system's accuracy is higher than those of most state-of-the-art stairway detection methods even in case of sparse point cloud data.

In this paper we've equipped a cylindrical end-effector with an array of capacitive sensors in order to implement 3D contour following. During the task, using proximity servoing, the sensors are aligned parallel to the surface and kept at a target distance. In addition, due to the spatial resolution, it's possible to estimate the surface's curvature in two dimensions along the rows and columns of the array. We show how a compound movement can be derived from both curvatures that pre-aligns the end-effector in each step, yielding a predictive component for the control scheme. We evaluate our approach with different geometries and show that the curvature information produces smooth contour following paths. We show that the system can handle speeds up to 150mms−1.

Single port surgery is an innovative approach in the field of minimally invasive surgery. Although several telemanipulators exist to perform operations through only a single incision they all suffer from the lack of haptic feedback. To generate kinesthetic feedback the intracorporeal forces need to be measured, which is a challenging task. To overcome these limitations we investigate in this paper the force sensing capability of a new single port robot that has two parallelkinematic manipulators. Because of the rigidity and excellent controllability the tip force is measured using proximally arranged force sensors. To minimize friction effects a longitudinal vibration of 6 Hz with an amplitude of 20 µm is applied to the manipulator while the tip force is varied in the three main coordinate axes. Within the analysis 32320 values are investigated showing that a vibration has a significant impact and dramatically improves the signal quality by minimizing the crosstalk by a factor of up to 12.7 enabling to measure the tip force exactly.

Optical depth cameras, including both time-of-flight and structured-light sensors, have led to dramatic improvements in robot sensing and perception. We propose the use of millimeter-wave (mmW) radar as an important complement to optical sensors. While the millimeter wavelengths of radar sensors do not support as high resolution as the nanometer wavelength of optical sensors, the ability of mmW signals to penetrate smoky and foggy environments as well as see through many opaque objects makes them a compelling sensor for navigation as well as manipulation in challenging environments. We present a series of 2D and 3D mmW images made with a hand-held antenna grasped by a PR2 robot. The radar image sensor uses a mechanical “painting” motion to acquire multiple views of the target object over the 15 – 26.5 GHz K-band. A GPU-based reconstruction algorithm synthesizes 2D and 3D images of the target object. We demonstrate a ground range resolution of 13.6 mm and a cross-range resolution of 7.1 mm for objects up to 0.5 m away from the robot. We further demonstrate imaging objects through fog, as well as through opaque paper.