The recognition of object categories in 3D scenes is still a challenging problem in computer vision. Many state of the art approaches use Implicit Shape Models, as addressed in [8] and [14], to learn shapes of object categories and a probabilistic Hough Space Voting for the detection of instances of the learned category. In this paper we present a novel 3D Hough Space Voting approach for recognizing object categories, learned from artificial 3D models, in 3D scenes. The proposed method uses rays instead of points to vote for object reference points. The usage of ray voting allows a clustering of votes, showing in similar directions, to a single vote with an appropriate vote weight. The main advantage for the Implicit Shape Model is that it can be trained with an unlimited amount of training data, while keeping the upper bound of computation effort constant. In addition, it is also able to abstract from the model sizes which is very helpful when training with artificial models taken from different sources and modelled in different scales. We validate our approach in two tasks: an object categorization is performed on a standard 3D dataset of artificial models and a recognition of furniture categories is evaluated on a dataset of captured indoor room scenes.

Facilitating efficient programming-by-demonstration methods for advanced robot systems is an ongoing research challenge. This paper addresses one important challenge in this area, which is the programming of kinematically redundant robots. We argue that standard programming-by-demonstration methods for teaching task-space trajectories on a redundant robot using physical human-robot interaction are too complex for non-expert human tutors. We therefore introduce a new interaction and control concept for redundant robot systems, Assisted Gravity Compensation, based on a hierarchical control scheme, separating task-space programming from the redundancy resolution. The user is actively assisted by a given redundancy resolution while kinesthetically teaching task-space trajectories. This control scheme is implemented on our experimental robot system called FlexIRob and we briefly present results of a kinesthetic teaching experiment obtained in a larger field study on physical Human-Robot Interaction with 48 industrial workers. These results show, that the Assisted Gravity Compensation reduces the complexity of a kinesthetic teaching task, which is revealed by an improved task performance, making kinesthetic teaching an efficient programming-by-demonstration method for redundant robots.

The recent advent of compliant and kinematically redundant robots poses new research challenges for human-robot interaction. While these robots provide a great degree of flexibility for the realization of complex applications, the flexibility gained generates the need for additional modeling steps and definition of criteria for redundancy resolution constraining the robot's movement generation. The explicit modeling of such criteria usually require experts to adapt the robot's movement generation subsystem. A typical way of dealing with this configuration challenge is to utilize kinesthetic teaching by guiding the robot to implicitly model the specific constraints in task and configuration space. We argue that current programming-by-demonstration approaches are not efficient for kinesthetic teaching of redundant robots and show that typical teach-in procedures are too complex for novice users. In order to enable non-experts to master the configuration and programming of a redundant robot in the presence of non-trivial constraints such as confined spaces, we propose a new interaction scheme combining kinesthetic teaching and learning within an integrated system architecture. We evaluated this approach in a user study with 49 industrial workers at HARTING, a medium-sized manufacturing company. The results show that the interaction concepts implemented on a KUKA Lightweight Robot IV are easy to handle for novice users, demonstrate the feasibility of kinesthetic teaching for implicit constraint modeling in configuration space, and yield significantly improved performance for the teach-in of trajectories in task space.

In this paper we present a new system for a mobile robot to generate an articulated scene model by analyzing complex dynamic 3D scenes. The system extracts essential knowledge about the foreground, like moving persons, and the background, which consists of all visible static scene parts. In contrast to other 3D reconstruction approaches, we suggest to additionally distinguish between static parts, like walls, and movable objects like chairs or doors. The discrimination supports the reconstruction process and additionally, delivers important information about interaction objects. Here, the movable object detection is realized object independent by analyzing changes in the scenery. Furthermore, in the proposed system the background scene is feedbacked to the tracking part yielding a much better tracking and detection result which improves again the 3D reconstruction. We show in our experiments that we are able to provide a sound background model and to extract simultaneously persons and object regions representing chairs, doors, and even smaller movable objects.

Navigation and obstacle avoidance in robotics using planar laser scans has matured over the last decades. They basically enable robots to penetrate highly dynamic and populated spaces, such as people's home, and move around smoothly. However, in an unconstrained environment the two-dimensional perceptual space of a fixed mounted laser is not sufficient to ensure safe navigation. In this paper, we present an approach that pools a fast and reliable motion generation approach with modern 3D capturing techniques using a time-of-flight camera. Instead of attempting to implement full 3D motion control, which is computationally more expensive and simply not needed for the targeted scenario of a domestic robot, we introduce a ldquovirtual laserrdquo. For the originally solely laser-based motion generation the technique of fusing real laser measurements and 3D point clouds into a continuous data stream is 100% compatible and transparent. The paper covers the general concept, the necessary extrinsic calibration of two very different types of sensors, and exemplarily illustrates the benefit which is to avoid obstacles not being perceivable in the original laser scan.

This paper presents a new method for detecting and merging redundant points in registered range data. Given a global representation from sequences of 3D points, the points are projected onto a virtual image plane computed from the intrinsic parameters of the sensor. Candidates for redundancy are collected per pixel which then are clustered locally via region growing and replaced by the clusterpsilas mean value. As data is provided in a certain manner defined by camera characteristics, this processing step preserves the structural information of the data. For evaluation, our approach is compared to two other algorithms. Applied to two different sequences, it is shown that the presented method gives smooth results within planar regions of the point clouds by successfully reducing noise and redundancy and thus improves registered range data.

Human-robot collaboration requires both communicative and decision making skills of a robot. To enable flexible coordination and turn-taking between human users and a robot in joint tasks, the robot's dialog and decision making mechanism have to be synchronized in a meaningful way. In this paper, we propose a integration framework to combine the dialog and the decision making processes. With this framework, we investigate various task negotiation situations for a social robot in a fetch-and-carry scenario. For the technical realization of the framework, the interface specification between the dialog and the decision making systems is also presented. Further, we discuss several challenging issues identified in our integration effort that should be adddressed in the future.

The paper introduces an online user study on applications for social robots with 127 participants. The potential users proposed 570 application scenarios based on the appearance and functionality of four robots presented (AIBO, BARTHOC, BIRON, iCat). The items were grouped into 13 categories which are interpreted and discussed by means of four dimensions: public vs. private use, intensity of interaction, complexity of interaction model, and functional vs. human-like appearance. The interpretation lead to three classes of applications for social robots according to the degree of social interaction: (1) Specialized Applications where the robot has to perform clearly defined tasks which are delegated by a user, (2) Public Applications which are directed to the communication with many users, and (3) Individual Applications with the need of a highly elaborated social model to maintain a variety of situations with few people.