Jos Lehmann

Bio: Jos Lehmann is an academic researcher from University of Hamburg. The author has contributed to research in topics: Ontology (information science) & Robot. The author has an hindex of 3, co-authored 3 publications receiving 39 citations.

The RACE Project : Robustness by Autonomous Competence Enhancement

Abstract: This paper reports on the aims, the approach, and the results of the European project RACE. The project aim was to enhance the behavior of an autonomous robot by having the robot learn from conceptualized experiences of previous performance, based on initial models of the domain and its own actions in it. This paper introduces the general system architecture; it then sketches some results in detail regarding hybrid reasoning and planning used in RACE, and instances of learning from the experiences of real robot task execution. Enhancement of robot competence is operationalized in terms of performance quality and description length of the robot instructions, and such enhancement is shown to result from the RACE system.

A Robot Waiter Learning from Experiences

Abstract: In this contribution, we consider learning tasks of a robot simulating a waiter in a restaurant. The robot records experiences and creates or adapts concepts represented in the web ontology language OWL 2, extended by quantitative spatial and temporal information. As a typical task, the robot is instructed to perform a specific activity in a few concrete scenarios and then expected to autonomously apply the conceptualized experiences to a new scenario. Constructing concepts from examples in a formal knowledge representation framework is well understood in principle, but several aspects important for realistic applications in robotics have remained unattended and are addressed in this paper. First, we consider conceptual representations of activity concepts combined with relevant factual knowledge about the environment. Second, the instructions can be coarse, confined to essential steps of a task, hence the robot has to autonomously determine the relevant context. Third, we propose a ”Good Common Subsumer” as opposed to the formal ”Least Common Subsumer” for the conceptualization of examples in order to obtain cognitively plausible results. Experiments are based on work in Project RACE where a PR2 robot is employed for recording experiences, learning and applying the learnt concepts.

A Robot Waiter that Predicts Events by High-level Scene Interpretation

Abstract: Being able to predict events and occurrences which may arise from a current situation is a desirable capability of an intelligent agent. In this paper, we show that a high-level scene interpretation system, implemented as part of a comprehensive robotic system developed in the XXX project, can also be used for prediction. This way, the robot can foresee possible developments of the environment and the effect they may have on its activities. As a guiding example, we consider a robot acting as a waiter in a restaurant and the task of predicting possible occurrences and courses of action, e.g. when serving a coffee to a guest. Our approach requires that the robot possesses conceptual knowledge about occurrences in the restaurant and its own activities, represented in the standardized ontology language OWL and augmented by constraints using SWRL. Conceptual knowledge may be acquired by conceptualizing experiences collected in the robot’s memory. Predictions are generated by a model-construction process which seeks to explain evidence as parts of such conceptual knowledge, this way generating possible future developments. The experimental results show, among others, the prediction of possible obstacle situations and their effect on the robot actions and estimated execution times.

Ego-centered networks and the ripple effect

Abstract: Recent work has demonstrated that many social networks, and indeed many networks of other types also, have broad distributions of vertex degree. Here we show that this has a substantial impact on the shape of ego-centered networks, i.e., sets of network vertices that are within a given distance of a specified central vertex, the ego. This in turn affects concepts and methods based on ego-centered networks, such as snowball sampling and the "ripple effect". In particular, we argue that one's acquaintances, one's immediate neighbors in the acquaintance network, are far from being a random sample of the population, and that this biases the numbers of neighbors two and more steps away. We demonstrate this concept using data drawn from academic collaboration networks, for which, as we show, current simple theories for the typical size of ego-centered networks give numbers that differ greatly from those measured in reality. We present an improved theoretical model which gives significantly better results.

Progress on robotics in hospitality and tourism: a review of the literature

Abstract: This paper aims to provide a comprehensive review of research on robotics in travel, tourism and hospitality, and to identify research gaps and directions for future research.,This paper analyzes 131 publications published during 1993-2019, identified via Scopus, Web of Science, ResearchGate, Academia.edu and Google Scholar. It offers quantitative analysis of frequencies and cross-tables and qualitative thematic analysis of the publications within each of seven identified domains.,The paper identifies “Robot,” “Human,” “Robot manufacturer,” “Travel/tourism/hospitality company,” “Servicescape,” “External environment” and “Education, training and research” as the research domains. Most research studies are dedicated to robots in restaurants, airports, hotels and bars. Papers tend to apply engineering methods, but experiments and surveys grow in popularity. Asia-Pacific countries account for much of the empirical research.,The analysis was limited to publications indexed in four databases and one search engine. Only publications in English were considered. Growing opportunities for those who are anxious to publish in the field are identified. Importantly, emerging research is branching out from the engineering of robots to the possibilities for human/robot interactions and their use for service providers, opening up new avenues of research for tourism and hospitality scholars.,The paper identified a myriad of application areas for robots across various tourism and hospitality sectors. Service providers must critically think about how robots affect the servicescape and how it needs to be adjusted or re-imagined to ensure that robots and employees can augment the service experiences (co-)created within it.,This is the first study to systematically analyze research publications on robotics in travel, tourism and hospitality.,本论文全面评论了在旅游酒店业中的机器人技术的研究, 并指出文献缺口和未来研究方向。,本论文分析了在1993年至2019年发布在Scopus、Web of Science、ResearchGate、Academia.edu、和Google Scholar的131篇文献。本论文对文献做了一系列定量分析, 包括频率分析、交叉表、定性文本分析、在七大确立的领域中对每个领域的文献进行分析。,本论文确立了七个研究领域：机器人、人类、机器生产者、旅游酒店企业、Servicescape、外部环境、和教育培训和研究。大多数文献集中在对饭店、机场、酒店、和酒吧的机器人研究。文献往往采用工程手段进行研究, 但是实验和问卷方式正在呈增长趋势。亚太国家占据大多数实证研究作品。,本论文样本库局限于四个数据库和一个搜索引擎。只有英文文献被采样。本论文为对相关领域感兴趣的学者指出研究方向。重要的是, 本论文发现用工程角度研究机器人的文献有了分支, 有一小部分文献开始着手研究人/机器人交互和其在服务过程中的使用的研究, 这对旅游酒店学者提供新研究视角。,本论文指出了一系列有关旅游酒店领域中机器人的应用。服务商必须重视机器人如何影响Servicescape以及如何审视机器人与人的交互, 确保其与员工加强消费者的服务体验（价值共创）。,本论文是首篇系统评论旅游酒店领域中机器人研究文献的文章。,关键词：机器人、机器人经济、机器人设计、机器人使用、Servicescape、rService、人-机器人交互、研究议程

Interactive Open-Ended Learning for 3D Object Recognition: An Approach and Experiments

Abstract: 3D object detection and recognition is increasingly used for manipulation and navigation tasks in service robots. It involves segmenting the objects present in a scene, estimating a feature descriptor for the object view and, finally, recognizing the object view by comparing it to the known object categories. This paper presents an efficient approach capable of learning and recognizing object categories in an interactive and open-ended manner. In this paper, “open-ended” implies that the set of object categories to be learned is not known in advance. The training instances are extracted from on-line experiences of a robot, and thus become gradually available over time, rather than at the beginning of the learning process. This paper focuses on two state-of-the-art questions: (1) How to automatically detect, conceptualize and recognize objects in 3D scenes in an open-ended manner? (2) How to acquire and use high-level knowledge obtained from the interaction with human users, namely when they provide category labels, in order to improve the system performance? This approach starts with a pre-processing step to remove irrelevant data and prepare a suitable point cloud for the subsequent processing. Clustering is then applied to detect object candidates, and object views are described based on a 3D shape descriptor called spin-image. Finally, a nearest-neighbor classification rule is used to predict the categories of the detected objects. A leave-one-out cross validation algorithm is used to compute precision and recall, in a classical off-line evaluation setting, for different system parameters. Also, an on-line evaluation protocol is used to assess the performance of the system in an open-ended setting. Results show that the proposed system is able to interact with human users, learning new object categories continuously over time.