Search

Autonomous robots are required to reason about the behaviour of dynamic agents in their environment. The creation of models to describe these relationships is typically accomplished through the application of causal discovery techniques. However, as it stands observational causal discovery techniques struggle to adequately cope with conditions such as causal sparsity and non-stationarity typically seen during online usage in autonomous agent domains. Meanwhile, interventional techniques are not always feasible due to domain restrictions. In order to better explore the issues facing observational techniques and promote further discussion of these topics we carry out a benchmark across 10 contemporary observational temporal causal discovery methods in the domain of autonomous driving. By evaluating these methods upon causal scenes drawn from real world datasets in addition to those generated synthetically we highlight where improvements need to be made in order to facilitate the application of causal discovery techniques to the aforementioned use-cases. Finally, we discuss potential directions for future work that could help better tackle the difficulties currently experienced by state of the art techniques., Comment: 26 Pages = 13 Pages (Main Content) + 5 Pages (References) + 8 Pages (Appendix), 2 Figures, To be published in the Proceedings of the 2nd Conference on Causal Learning and Reasoning as part of the Journal of Machine Learning Research Workshop and Conference Proceedings series, Final submission version; Updated from initial to final submission version

Collaborative robots (or cobots) will offer significant societal benefits, but their large-scale deployments may also lead to unintended consequences. The ability to query, analyse, and understand data from cobots will be a fundamental requirement for ensuring safety, accountability, and trust. To this end, we propose embodied question answering as a means to enable cobots to explain themselves and make them trustworthy. Our approach is founded in responsible research and innovation and thereby will shape the future of responsible robotics design, development, and deployment for cobots. In this paper, we first provide some background on responsible robotics. Second, we elaborate on the need for explanations. Third, we describe our approach to embodied question answering, and finally, we discuss open challenges before we conclude.

ADE (Autonomous DEcision making in Very Long Traverses) is an ongoing H2020 project aiming to develop key technologies for future space robotics missions. The focus of the project is to develop an exhaustive autonomous system for planetary rover exploration that can traverse at least 1km/sol, perform and maximize the scientific data collection, take appropriate decisions in nominal and contingency situations and ensure its safety at any moment. In this paper we describe the system developed and its capabilities, along with the validation approach and testing facilities.

Scientific opportunities are missed in planetary explorations due to the lack of communication and/or long-time communication delays between rovers and ground stations. By enabling rovers to autonomously detect and explore targets the overall scientific outcome of extraterrestrial missions can be increased. In this paper, we have designed, developed, and evaluated unsupervised as well as semi-supervised approaches to novelty detection based on Variational Autoencoders (VAE). Our VAE model was trained on typical data from previous missions and tested to infer the novelty of scientific targets. In an ablation study, we investigate the effectiveness of different types of loss functions. We compare losses based on reconstruction errors, losses obtained from the VAE’s latent space as well as a combination of both. In our experiments, we have evaluated both unsupervised and semi-supervised approaches on datasets obtained from NASA’s Mars Curiosity rover. Results show that our VAE-based approaches are not only robust but also comparable, or better, than the state-of-the-art.

Understanding change related to the dynamics of people and objects in everyday environments is a challenging problem. At the same time, it is a key requirement in many applications of autonomous mobile service robots. In this paper we present a novel semantic mapping framework which maps locations of objects, regions of interest, and movements of people over time. Our aim with this framework is twofold: (1) we want to allow robots to reason semantically, spatially, and temporally about their environment, and (2) we want to enable researchers to investigate research questions in the context of long-term scenarios in dynamic environments. Experimental results demonstrate the effectiveness of the framework which was deployed on mobile robot systems in real-world environments over several months

Unemployment is associated with a loss in utility. This utility loss can be mitigated through coping strategies, which vary with age and gender. Using highly detailed German county level data, we test whether the social norm effect of unemployment is age-dependent. The well-being differential between the unemployed and the employed is found to increase with the local unemployment rate at the beginning of the working life but to remain steady or even to decrease in older age. Individual unemployment, however, remains an extremely unpleasant experience even if local unemployment is high.

Unemployed individuals may regain identity utility through coping strategies, which however vary with age and gender. Using highly detailed German county level data, we test whether the social norm effect of unemployment is age-dependent. The wellbeing differential between the unemployed and the employed is found to increase with the local unemployment rate at the beginning of the working life but to remain steady or even to decrease in older age. Individual unemployment, however, remains an extremely uncomfortable experience even if local unemployment is high. Eine mögliche Bewältigungsstrategie für von Arbeitslosigkeit betroffene Personen besteht darin, Nutzen aus Identität wiederherzustellen. Derartige Strategien sind allerdings alters- und geschlechtsabhängig. Unter Ausnutzung detaillierter Kreisdaten für Deutschland untersuchen wir, ob der soziale Normeffekt von Arbeitslosigkeit altersabhängig ist. In der Tat finden wir, dass die Wohlbefindenslücke zwischen Arbeitslosen und Erwerbstätigen zu Beginn des Erwerbslebens mit der lokalen Arbeitslosenquote wächst, später allerdings unverändert bleibt oder sogar kleiner wird. Insgesamt betrachtet bleibt individuelle Arbeitslosigkeit aber eine äußerst unangenehme Erfahrung, auch bei einer hohen lokalen Arbeitslosenquote.

International audience; Autonomous robots that are to assist humans in their daily lives are required, among other things, to recognize and understand the meaning of task-related objects. However, given an open-ended set of tasks, the set of everyday objects that robots will encounter during their lifetime is not foreseeable. That is, robots have to learn and extend their knowledge about previously unknown objects on-the-job. Our approach automatically acquires parts of this knowledge (e.g., the class of an object and its typical location) in form of ranked hypotheses from the Semantic Web using contextual information extracted from observations and experiences made by robots. Thus, by integrating situated robot perception and Semantic Web mining, robots can continuously extend their object knowledge beyond perceptual models which allows them to reason about task-related objects , e.g., when searching for them, robots can infer the most likely object locations. An evaluation of the integrated system on long-term data from real office observations, demonstrates that generated hypotheses can effectively constrain the meaning of objects. Hence, we believe that the proposed system can be an essential component in a lifelong learning framework which acquires knowledge about objects from real world observations.

Recognising objects in everyday human environments is a challenging task for autonomous mobile robots. However, actively planning the views from which anobject might be perceived can significantly improve the overall task performance. In this paper we have designed, developed, and evaluated an approach for next best view planning. Our view planning approach is based on online aspect graphs and selects the next best view after having identified an initial object candidate. The approach has two steps. First, we analyse the visibility of the object candidate from a set of candidate views that are reachable by a robot. Secondly, we analyse the visibility of object features by projecting themodel of the most likely object into the scene. Experimental results on a mobile robot platform show that our approach is (I) effective at finding a next view that leads to recognition of an object in 82.5% of cases, (II) able to account for visual occlusions in 85% of the trials, and (III) able to disambiguate between objects that share a similar set of features. Hence, overall, we believe that the proposed approach can provide a general methodology that is applicable to a range of tasks beyond object recognition such as inspection, reconstruction, and task outcome classification.