-
Corner cases in machine learning processes AI Perspect. Pub Date : 2024-01-02 Florian Heidecker, Maarten Bieshaar, Bernhard Sick
Applications using machine learning (ML), such as highly autonomous driving, depend highly on the performance of the ML model. The data amount and quality used for model training and validation are crucial. If the model cannot detect and interpret a new, rare, or perhaps dangerous situation, often referred to as a corner case, we will likely blame the data for not being good enough or too small in
-
Human-centered AI and robotics AI Perspect. Pub Date : 2022-01-28 Doncieux, Stephane, Chatila, Raja, Straube, Sirko, Kirchner, Frank
Robotics has a special place in AI as robots are connected to the real world and robots increasingly appear in humans everyday environment, from home to industry. Apart from cases were robots are expected to completely replace them, humans will largely benefit from real interactions with such robots. This is not only true for complex interaction scenarios like robots serving as guides, companions or
-
Object detection for automotive radar point clouds – a comparison AI Perspect. Pub Date : 2021-11-16 Scheiner, Nicolas, Kraus, Florian, Appenrodt, Nils, Dickmann, Jürgen, Sick, Bernhard
Automotive radar perception is an integral part of automated driving systems. Radar sensors benefit from their excellent robustness against adverse weather conditions such as snow, fog, or heavy rain. Despite the fact that machine-learning-based object detection is traditionally a camera-based domain, vast progress has been made for lidar sensors, and radar is also catching up. Recently, several new
-
Study of environmental data from vehicle’s sensors and its aplicability to complement climate mapping from automatic meteorological stations and assess covid-19 impact AI Perspect. Pub Date : 2021-10-15 Lopes, Philippe Cedraz, da Silva, Juliana Carla Santos, Guarieiro, Lílian Lefol Nani, Moreira, Davidson Martins
An evolution of smart and connected cars allows the advancement of smart cities and new business models for automakers. The main objective of this article was to understand the capability of Brazilian vehicles to collect meteorological data, through an observational approach of vehicle technologies and an applied study of automatic weather stations. In 2020, when the world was affected by the COVID-19
-
Feasibility analysis on the construction of a web solution for hydrometeorological forecasting considering water body management and indicators for the SARS-COV-2 pandemic AI Perspect. Pub Date : 2021-10-01 Dantas da Silva Júnior, José Roberto, Pedruzzi, Rizzieri, de Souza, Filipe Milani, Ferraz, Patrick Silva, Silva, Daniel Guimarães, Vieira, Carolina Sacramento, de Moraes, Marcelo Romero, Nascimento, Erick Giovani Sperandio, Moreira, Davidson Martins
The current scenario of a global pandemic caused by the virus SARS-CoV-2 (COVID19), highlights the importance of water studies in sewage systems. In Brazil, about 35 million Brazilians still do not have treated water and more than 100 million do not have basic sanitation. These people, already exposed to a range of diseases, are among the most vulnerable to COVID-19. According to studies, places that
-
Supply chain resilience and industry 4.0: a evaluation of the Brazilian northeast automotive OEM scenario post COVID-19 AI Perspect. Pub Date : 2021-08-02 Soares, Milton C., Ferreira, Cristiano V., Murari, Thiago B.
COVID-19 outbreak has heavily impacted the manufacturing industry, including Brazilian Automotive Industry. The effects of COVID-19 created restrictions in several industry processes as supply chain. On the other hand, several industry 4.0 technologies is able to support the industry supply chain activities in the COVID 19 scenarios, as well it may contributed for the automotive industry recovery and
-
CLeaR: An adaptive continual learning framework for regression tasks AI Perspect. Pub Date : 2021-07-16 Yujiang He, Bernhard Sick
Catastrophic forgetting means that a trained neural network model gradually forgets the previously learned tasks when being retrained on new tasks. Overcoming the forgetting problem is a major problem in machine learning. Numerous continual learning algorithms are very successful in incremental learning of classification tasks, where new samples with their labels appear frequently. However, there is
-
A development cycle for automated self-exploration of robot behaviors AI Perspect. Pub Date : 2021-07-05 Thomas M. Roehr, Daniel Harnack, Hendrik Wöhrle, Felix Wiebe, Moritz Schilling, Oscar Lima, Malte Langosz, Shivesh Kumar, Sirko Straube, Frank Kirchner
In this paper we introduce Q-Rock, a development cycle for the automated self-exploration and qualification of robot behaviors. With Q-Rock, we suggest a novel, integrative approach to automate robot development processes. Q-Rock combines several machine learning and reasoning techniques to deal with the increasing complexity in the design of robotic systems. The Q-Rock development cycle consists of
-
Can an AI learn political theory? AI Perspect. Pub Date : 2020-10-07 Stephen J. DeCanio
Alan Turing’s 1950 paper, “Computing Machinery and Intelligence,” contains much more than its proposal of the “Turing Test.” Turing imagined the development of what we today call AI by a process akin to the education of a child. Thus, while Turing anticipated “machine learning,” his prescience brings to the foreground the yet unsolved problem of how humans might teach or shape AIs to behave in ways
-
AI-perspectives: the Turing option AI Perspect. Pub Date : 2020-09-04 Frank Kirchner
This paper presents a perspective on AI that starts with going back to early work on this topic originating in theoretical work of Alan Turing. The argument is made that the core idea - that leads to the title of this paper - of these early thoughts are still relevant today and may actually provide a starting point to make the transition from today functional AI solutions towards integrative or general
-
Applications of AI in classical software engineering AI Perspect. Pub Date : 2020-07-26 Marco Barenkamp, Jonas Rebstadt, Oliver Thomas
Although Artificial Intelligence (AI) has become a buzzword for self-organizing IT applications, its relevance to software engineering has hardly been analyzed systematically. This study combines a systematic review of previous research in the field and five qualitative interviews with software developers who use or want to use AI tools in their daily work routines, to assess the status of development
-
Digital reality: a model-based approach to supervised learning from synthetic data AI Perspect. Pub Date : 2019-09-03 Tim Dahmen, Patrick Trampert, Faysal Boughorbel, Janis Sprenger, Matthias Klusch, Klaus Fischer, Christian Kübel, Philipp Slusallek
Hierarchical neural networks with large numbers of layers are the state of the art for most computer vision problems including image classification, multi-object detection and semantic segmentation. While the computational demands of training such deep networks can be addressed using specialized hardware, the availability of training data in sufficient quantity and quality remains a limiting factor
-
Responsible AI: requirements and challenges AI Perspect. Pub Date : 2019-09-03 Malik Ghallab
This position paper discusses the requirements and challenges for responsible AI with respect to two interdependent objectives: (i) how to foster research and development efforts toward socially beneficial applications, and (ii) how to take into account and mitigate the human and social risks of AI systems.
-
AI-Perspectives: an editorial AI Perspect. Pub Date : 2019-09-03 Frank Kirchner
In this journal we will have to discuss the many challenges and applications that AI in the time of increasing -computational- resources can achieve, how can it be applied and what the consequences of its application are. We will have to discuss about the feedback to basic AI research that is provided by the application of an AI-algorithm or concept to a given and real problem. Furthermore, we will