The usefulness and versatility of a robotic end-effector depends on the diversity of grasps it can accomplish and also on the complexity of the control methods required to achieve them. We believe that soft hands are able to provide diverse and robust grasping with low control complexity. They possess many mechanical degrees of freedom and are able to implement complex deformations. At the same time, due to the inherent compliance of soft materials, only very few of these mechanical degrees have to be controlled explicitly. Soft hands therefore may combine the best of both worlds. In this paper, we present RBO Hand 2, a highly compliant, underactuated, robust, and dexterous anthropomorphic hand. The hand is inexpensive to manufacture and the morphology can easily be adapted to specific applications. To enable efficient hand design, we derive and evaluate computational models for the mechanical properties of the hand's basic building blocks, called PneuFlex actuators. The versatility of RBO Hand 2 is evaluated by implementing the comprehensive Feix taxonomy of human grasps. The manipulator's capabilities and limits are demonstrated using the Kapandji test and grasping experiments with a variety of objects of varying weight. Furthermore, we demonstrate that the effective dimensionality of grasp postures exceeds the dimensionality of the actuation signals, illustrating that complex grasping behavior can be achieved with relatively simple control.

/pdf/a-novel-type-of-compliant-and-underactuated-robotic-hand-for-28trfw7f6g.pdf

A novel type of compliant and underactuated robotic hand for dexterous grasping

Dense semantic segmentation of 3D point clouds is a challenging task. Many approaches deal with 2D semantic segmentation and can obtain impressive results. With the availability of cheap RGB-D sensors the field of indoor semantic segmentation has seen a lot of progress. Still it remains unclear how to deal with 3D semantic segmentation in the best way. We propose a novel 2D-3D label transfer based on Bayesian updates and dense pairwise 3D Conditional Random Fields. This approach allows us to use 2D semantic segmentations to create a consistent 3D semantic reconstruction of indoor scenes. To this end, we also propose a fast 2D semantic segmentation approach based on Randomized Decision Forests. Furthermore, we show that it is not needed to obtain a semantic segmentation for every frame in a sequence in order to create accurate semantic 3D reconstructions. We evaluate our approach on both NYU Depth datasets and show that we can obtain a significant speed-up compared to other methods.

Dense 3D semantic mapping of indoor scenes from RGB-D images

In recent years, the videogame industry has been characterized by a great boost in gesture recognition and motion tracking, following the increasing request of creating immersive game experiences. The Microsoft Kinect sensor allows acquiring RGB, IR and depth images with a high frame rate. Because of the complementary nature of the information provided, it has proved an attractive resource for researchers with very different backgrounds. In summer 2014, Microsoft launched a new generation of Kinect on the market, based on time-of-flight technology. This paper proposes a calibration of Kinect for Xbox One imaging sensors, focusing on the depth camera. The mathematical model that describes the error committed by the sensor as a function of the distance between the sensor itself and the object has been estimated. All the analyses presented here have been conducted for both generations of Kinect, in order to quantify the improvements that characterize every single imaging sensor. Experimental results show that the quality of the delivered model improved applying the proposed calibration procedure, which is applicable to both point clouds and the mesh model created with the Microsoft Fusion Libraries.

/pdf/calibration-of-kinect-for-xbox-one-and-comparison-between-19n1br77ez.pdf

Calibration of Kinect for Xbox One and Comparison between the Two Generations of Microsoft Sensors

We address the difficult problem of catching in-flight objects with uneven shapes This requires the solution of three complex problems: accurate prediction of the trajectory of fastmoving objects, predicting the feasible catching configuration, and planning the arm motion, and all within milliseconds We follow a programming-by-demonstration approach in order to learn, from throwing examples, models of the object dynamics and arm movement We propose a new methodology to find a feasible catching configuration in a probabilistic manner We use the dynamical systems approach to encode motion from several demonstrations This enables a rapid and reactive adaptation of the arm motion in the presence of sensor uncertainty We validate the approach in simulation with the iCub humanoid robot and in real-world experiments with the KUKA LWR 4+ (7-degree-of-freedom arm robot) to catch a hammer, a tennis racket, an empty bottle, a partially filled bottle, and a cardboard box

Catching Objects in Flight

This article presents a comprehensive survey of deep learning applications for object detection and scene perception in autonomous vehicles. Unlike existing review papers, we examine the theory underlying self-driving vehicles from deep learning perspective and current implementations, followed by their critical evaluations. Deep learning is one potential solution for object detection and scene perception problems, which can enable algorithm-driven and data-driven cars. In this article, we aim to bridge the gap between deep learning and self-driving cars through a comprehensive survey. We begin with an introduction to self-driving cars, deep learning, and computer vision followed by an overview of artificial general intelligence. Then, we classify existing powerful deep learning libraries and their role and significance in the growth of deep learning. Finally, we discuss several techniques that address the image perception issues in real-time driving, and critically evaluate recent implementations and tests conducted on self-driving cars. The findings and practices at various stages are summarized to correlate prevalent and futuristic techniques, and the applicability, scalability and feasibility of deep learning to self-driving cars for achieving safe driving without human intervention. Based on the current survey, several recommendations for further research are discussed at the end of this article.

Deep learning for object detection and scene perception in self-driving cars: Survey, challenges, and open issues

The peg-in-hole assembly is a representative robotic task that involves physical contact with the external environment. In this paper, in contrast to past research in the area, which has involved the utilization of such expensive devices as force/torque sensors or remote compliance mechanisms, an inexpensive method is proposed for peg-in-hole assembly without force feedback or passive compliance mechanisms. The method consists of an analysis of the state of contact between the peg and the hole as well as a strategy to overcome the inevitable positional uncertainty of the hole incurred in the recognition process. A control scheme was developed to yield compliant behavior from the robot with physical contact under the condition of hybrid position/force control. The effectiveness of the proposed method was experimentally verified using a robot manipulator with 8-degrees of freedom and a peg-in-hole apparatus with a small clearance (0.1 mm).

Compliance-Based Robotic Peg-in-Hole Assembly Strategy Without Force Feedback

This paper presents an anthropomorphic robotic hand named “KITECH-Hand,” along with its kinematic analysis and detailed mechanical features. From a kinematic perspective, the authors particularly focus on the structure of the metacarpophalangeal (MCP) joints of the fingers. The KITECH-Hand adopts a new “roll–pitch”-type MCP structure to replace conventional “yaw–pitch” structures. The proposed structure provides benefits such as enhanced kinematic performance and ease of the mechanical design. Through the kinematic analysis, it is shown that the KITECH-Hand shows remarkably high dexterity, well surpassing that of existing robotic hands with conventional MCP joints. The unique MCP structure also helps modularize the robot at the joint level, which simplifies its mechanical structure and enables the production cost to be reduced. The performance of the KITECH-Hand, including its dexterity feature, was experimentally verified through a series of experiments, which included object in-hand manipulation and a Cutkosky taxonomy test.

KITECH-Hand: A Highly Dexterous and Modularized Robotic Hand

To realize a peg-in-hole assembly with a multi-degree of freedom (DOF) manipulator, the precise position of the hole is required. If the hole is not circular, orientation information is also necessary. A force/torque (F/T) sensor is widely used to sense the position and orientation of the hole. Attaching the F/T sensor on the wrist of a manipulator helps in estimating the position between the peg and hole. However, a person does not need precise information of an object when completing an assembly task. For example, when inserting a plug into an outlet, a person does not need to know the exact information and coordination about the position and orientation of the plug and outlet. A closer look at the process shows that the person tries to place a plug near the outlet and then finds the two holes by rubbing the plug against the outlet without looking. This paper introduces an intuitive assembly strategy inspired by this human behavior. This strategy does not need the precise location of the hole. Instead of an F/T sensor, this strategy adopts hybrid force/position control and passive compliance control for successful peg-in-hole assembly. The feasibility of the proposed strategy was verified through simulation and a hardware experiment.

Intuitive peg-in-hole assembly strategy with a compliant manipulator

This study proposes a mathematical uncertainty model for the spatial measurement of visual features using Kinect™ sensors. This model can provide qualitative and quantitative analysis for the utilization of Kinect™ sensors as 3D perception sensors. In order to achieve this objective, we derived the propagation relationship of the uncertainties between the disparity image space and the real Cartesian space with the mapping function between the two spaces. Using this propagation relationship, we obtained the mathematical model for the covariance matrix of the measurement error, which represents the uncertainty for spatial position of visual features from Kinect™ sensors. In order to derive the quantitative model of spatial uncertainty for visual features, we estimated the covariance matrix in the disparity image space using collected visual feature data. Further, we computed the spatial uncertainty information by applying the covariance matrix in the disparity image space and the calibrated sensor parameters to the proposed mathematical model. This spatial uncertainty model was verified by comparing the uncertainty ellipsoids for spatial covariance matrices and the distribution of scattered matching visual features. We expect that this spatial uncertainty model and its analyses will be useful in various Kinect™ sensor applications.

Spatial Uncertainty Model for Visual Features Using a Kinect™ Sensor

This paper is concerned with constructing a prototype smart home environment which has been built in the research building of Korea Institute of Industrial Technology (KITECH) to demonstrate the practicability of a robot-assisted future home environment. Key functionalities that a home service robot must provide are localization, navigation, object recognition and object handling. A considerable amount of research has been conducted to make the service robot perform these operations with its own sensors, actuators and a knowledge database. With all heavy sensors, actuators and a database, the robot could have performed the given tasks in a limited environment or showed the limited capabilities in a natural environment. We initiated a smart home environment project for light-weight service robots to provide reliable services by interacting with the environment through the wireless sensor networks. This environment consists of the following three main components: smart objects with an radio frequency identification (RFID) tag and smart appliances with sensor network functionality; the home server that connects smart devices as well as maintains information for reliable services; and the service robots that perform tasks in collaboration with the environment. In this paper, we introduce various types of smart devices which are developed for assisting the robot by providing sensing and actuation, and present our approach on the integration of these devices to construct the smart home environment. Finally, we discuss the future directions of our project.

Jae-Han Park

Papers

Compliance-Based Robotic Peg-in-Hole Assembly Strategy Without Force Feedback

KITECH-Hand: A Highly Dexterous and Modularized Robotic Hand

Intuitive peg-in-hole assembly strategy with a compliant manipulator

Spatial Uncertainty Model for Visual Features Using a Kinect™ Sensor

Building a smart home environment for service robots based on RFID and sensor networks