Autor*innen mit den meisten Dokumenten
Auflistung nach:
Neueste Veröffentlichungen
- ZeitschriftenartikelSpecial Issue on Reintegrating Artificial Intelligence and Robotics(KI - Künstliche Intelligenz: Vol. 33, No. 4, 2019) Pecora, Federico; Mansouri, Masoumeh; Hawes, Nick; Kunze, Lars
- ZeitschriftenartikelBenchmarking Functionalities of Domestic Service Robots Through Scientific Competitions(KI - Künstliche Intelligenz: Vol. 33, No. 4, 2019) Basiri, Meysam; Piazza, Enrico; Matteucci, Matteo; Lima, PedroBenchmarking via carefully designed competitions makes it possible to provide a common framework for the rigorous comparison of intelligent and autonomous systems; competitions may play the role of scientific experiments while being appealing both to researchers and to the general public thus promoting critical analysis of systems outside the labs. This paper describes our approach to benchmarking domestic service robots through organizing recurrent competitions under the European Robotics League. It details the tools and benchmarks designed to evaluate the performance of robots at task and functionality levels. In particular, the functionality benchmarks for object perception and navigation are described and an overview of the new benchmarks to appear in the league is presented.
- ZeitschriftenartikelEfficient Supervision for Robot Learning Via Imitation, Simulation, and Adaptation(KI - Künstliche Intelligenz: Vol. 33, No. 4, 2019) Wulfmeier, MarkusRecent successes in machine learning have led to a shift in the design of autonomous systems, improving performance on existing tasks and rendering new applications possible. Data-focused approaches gain relevance across diverse, intricate applications when developing data collection and curation pipelines becomes more effective than manual behaviour design. The following work aims at increasing the efficiency of this pipeline in two principal ways: by utilising more powerful sources of informative data and by extracting additional information from existing data. In particular, we target three orthogonal fronts: imitation learning, domain adaptation, and transfer from simulation.
- ZeitschriftenartikelNews(KI - Künstliche Intelligenz: Vol. 33, No. 4, 2019)
- ZeitschriftenartikelCategorisations: AI(KI - Künstliche Intelligenz: Vol. 33, No. 4, 2019) Timpf, Sabine
- ZeitschriftenartikelAn Introduction to Hyperdimensional Computing for Robotics(KI - Künstliche Intelligenz: Vol. 33, No. 4, 2019) Neubert, Peer; Schubert, Stefan; Protzel, PeterHyperdimensional computing combines very high-dimensional vector spaces (e.g. 10,000 dimensional) with a set of carefully designed operators to perform symbolic computations with large numerical vectors. The goal is to exploit their representational power and noise robustness for a broad range of computational tasks. Although there are surprising and impressive results in the literature, the application to practical problems in the area of robotics is so far very limited. In this work, we aim at providing an easy to access introduction to the underlying mathematical concepts and describe the existing computational implementations in form of vector symbolic architectures (VSAs). This is accompanied by references to existing applications of VSAs in the literature. To bridge the gap to practical applications, we describe and experimentally demonstrate the application of VSAs to three different robotic tasks: viewpoint invariant object recognition, place recognition and learning of simple reactive behaviors. The paper closes with a discussion of current limitations and open questions.
- ZeitschriftenartikelWeed Management of the Future(KI - Künstliche Intelligenz: Vol. 33, No. 4, 2019) Amend, Sandra; Brandt, David; Di Marco, Daniel; Dipper, Tobias; Gässler, Gabriel; Höferlin, Markus; Gohlke, Maurice; Kesenheimer, Katharina; Lindner, Peter; Leidenfrost, Roland; Michaels, Andreas; Mugele, Tobias; Müller, Arthur; Riffel, Tanja; Sampangi, Yeshwanth; Winkler, JanThe methods used to protect agricultural products currently undergo drastic changes. Artificial Intelligence is a prime candidate to overcome two challenges faced by farmers around the world: The increasing cost and decreasing availability of human labor for weed control, and the growing global restriction of herbicides. Deep Learning is one of the most prominent approaches for applying AI to all kinds of use cases in industrial applications, entertainment, and security. Its latest field of application is plant classification that enables automated weed control and precise spot spraying of herbicides. While cheap, powerful platforms for deploying classification mechanisms are widely available, this comes at the cost of expensive and effort rich classifier training. This effectively makes Deep Learning-based approaches unavailable for the majority of the agricultural sector. Deepfield Robotics presents a systematic approach for deploying AI onto fields at large, including the learnings that led to their self-contained AI driven plant classification modules that relieve individuals from having to deploy their own AI solution. The same technology acts as enabler for more agricultural domains, such as targeted fertilization, nano irrigation, and automated phenotyping. This article documents Deepfield Robotics’ findings and vision on how AI can be the workhorse for agricultural weeding labor.
- ZeitschriftenartikelReg3DFacePtCd: Registration of 3D Point Clouds Using a Common Set of Landmarks for Alignment of Human Face Images(KI - Künstliche Intelligenz: Vol. 33, No. 4, 2019) Bagchi, Parama; Bhattacharjee, Debotosh; Nasipuri, MitaThe present work proposes a new method Reg3DFacePtCd for registration of point clouds. The key contribution of the present method is that an unknown face in 3D point cloud form is given to the system and is registered to the already existing known 3D face point clouds using a fast 3D face registration method. The novelty of the present technique is that at first the alignment and registration parameters are found out by initially registering eight key points of the unknown source model to that of the known model. Next, the rest of the point clouds of the unknown model are registered to that of the known model using the same parameters found as above. The main method used for alignment is iterative closest point (ICP) using point-based technique followed by registration in the least squares sense. Mainly there are two significant contributions. Firstly, we have developed a new mathematical model facial landmark point based model across poses to obtain the target or the known model to which all the unknown models will be registered. Secondly, a novel way to accelerate point cloud matching by reducing the number of points has been proposed. Using a small number of points necessarily would speed up the registration process but may inculcate errors. So, to determine the registration quality of the fundamental eight key points on which the entire registration process is based, a new robust metric namely ICV (ICP certainty vector) consisting of several key components have been used. Finally, we have addressed several important face registration issues like pre-processing, convergence and quality of registration of the entire facial point cloud based on the eight key points. Extensive experimentation on Frav3D, GavabDB, and the Bosphorus databases on a high-performance computing environment show the novelty and robustness of the method.
- ZeitschriftenartikelTowards a Theory of Explanations for Human–Robot Collaboration(KI - Künstliche Intelligenz: Vol. 33, No. 4, 2019) Sridharan, Mohan; Meadows, BenThis paper makes two contributions towards enabling a robot to provide explanatory descriptions of its decisions, the underlying knowledge and beliefs, and the experiences that informed these beliefs. First, we present a theory of explanations comprising (i) claims about representing, reasoning with, and learning domain knowledge to support the construction of explanations; (ii) three fundamental axes to characterize explanations; and (iii) a methodology for constructing these explanations. Second, we describe an architecture for robots that implements this theory and supports scalability to complex domains and explanations. We demonstrate the architecture’s capabilities in the context of a simulated robot (a) moving target objects to desired locations or people; or (b) following recipes to bake biscuits.
- ZeitschriftenartikelOn the Applicability of Probabilistic Programming Languages for Causal Activity Recognition(KI - Künstliche Intelligenz: Vol. 33, No. 4, 2019) Lüdtke, Stefan; Popko, Maximilian; Kirste, ThomasRecognizing causal activities of human protagonists, and jointly inferring context information like location of objects and agents from noisy sensor data is a challenging task. Causal models can be used, which describe the activity structure symbolically, e.g. by precondition-effect actions. Recently, probabilistic programming languages (PPLs) arose as an abstraction mechanism that allow to concisely define probabilistic models by a general-purpose programming language, and provide off-the-shelf, general-purpose inference algorithms. In this paper, we empirically investigate whether PPLs provide a feasible alternative for implementing causal models for human activity recognition, by comparing the performance of three different PPLs (Anglican, WebPPL and Figaro) on a multi-agent scenario. We find that PPLs allow to concisely express causal models, but general-purpose inference algorithms that are typically implemented in PPLs are outperformed by an application-specific inference algorithm by orders of magnitude. Still, PPLs can be a valuable tool for developing probabilistic models, due to their expressiveness and simple applicability.