KI - Künstliche Intelligenz
Permanent URI for this communityhttps://dl.gi.de/handle/20.500.12116/11025
The Scientific journal "KI – Künstliche Intelligenz" is the official journal of the division for artificial intelligence within the "Gesellschaft für Informatik e.V." (GI) – the German Informatics Society – with contributions from throughout the field of artificial intelligence. The journal presents all relevant aspects of artificial intelligence – the fundamentals and tools, their use and adaptation for scientific purposes, and applications which are implemented using AI methods – and thus provides the reader with the latest developments in and well-founded background information on all relevant aspects of artificial intelligence. For all members of the AI community the journal provides quick access to current topics in the field and promotes vital interdisciplinary interchange.
Authors with most Documents
Browse
601 results
Search Results
Journal Article An Introduction to Hyperdimensional Computing for Robotics(Springer, 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.Journal Article News(Springer, 2019)Journal Article Special Issue on Reintegrating Artificial Intelligence and Robotics(Springer, 2019) Pecora, Federico; Mansouri, Masoumeh; Hawes, Nick; Kunze, LarsJournal Article Benchmarking Functionalities of Domestic Service Robots Through Scientific Competitions(Springer, 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.Journal Article Efficient Supervision for Robot Learning Via Imitation, Simulation, and Adaptation(Springer, 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.Journal Article Categorisations: AI(Springer, 2019) Timpf, SabineJournal Article On the Applicability of Probabilistic Programming Languages for Causal Activity Recognition(Springer, 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.Journal Article Shakey Ever After? Questioning Tacit Assumptions in Robotics and Artificial Intelligence(Springer, 2019) Kirsch, AlexandraShakey the robot was a milestone of autonomous robots and artificial intelligence. Its design principles have dominated research until now. Tacit philosophical and architectural assumptions have impoverished the space of research topics and methods. I point out ways to overcome this impasse with sideglances to other scientific fields.Journal Article Deskilling Robots in Logistics Environments(Springer, 2019) Davies, Martin RaymondRobots are installed in logistics environments because they are adaptive; unlike their rigid mechanized counterparts, e.g. conveyors and lifts. Maintaining this adaptability post installation; and leaving it to the customer to reconfigure and maintain the system is still a difficult proposal. Deskilling the introduction and sustainability of robotic systems therefore is a key success factor for replacing traditional static capital equipment.Journal Article Weed Management of the Future(Springer, 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.