RESUMO
The term "world model" (WM) has surfaced several times in robotics, for instance, in the context of mobile manipulation, navigation and mapping, and deep reinforcement learning. Despite its frequent use, the term does not appear to have a concise definition that is consistently used across domains and research fields. In this review article, we bootstrap a terminology for WMs, describe important design dimensions found in robotic WMs, and use them to analyze the literature on WMs in robotics, which spans four decades. Throughout, we motivate the need for WMs by using principles from software engineering, including "Design for use," "Do not repeat yourself," and "Low coupling, high cohesion." Concrete design guidelines are proposed for the future development and implementation of WMs. Finally, we highlight similarities and differences between the use of the term "world model" in robotic mobile manipulation and deep reinforcement learning.
RESUMO
The Earth's moon is currently an object of interest of many space agencies for unmanned robotic missions within this decade. Besides future prospects for building lunar gateways as support to human space flight, the Moon is an attractive location for scientific purposes. Not only will its study give insight on the foundations of the Solar System but also its location, uncontaminated by the Earth's ionosphere, represents a vantage point for the observation of the Sun and planetary bodies outside the Solar System. Lunar exploration has been traditionally conducted by means of single-agent robotic assets, which is a limiting factor for the return of scientific missions. The German Aerospace Center (DLR) is developing fundamental technologies towards increased autonomy of robotic explorers to fulfil more complex mission tasks through cooperation. This paper presents an overview of past, present and future activities of DLR towards highly autonomous systems for scientific missions targeting the Moon and other planetary bodies. The heritage from the Mobile Asteroid Scout (MASCOT), developed jointly by DLR and CNES and deployed on asteroid Ryugu on 3 October 2018 from JAXA's Hayabusa2 spacecraft, inspired the development of novel core technologies towards higher efficiency in planetary exploration. Together with the lessons learnt from the ROBEX project (2012-2017), where a mobile robot autonomously deployed seismic sensors at a Moon analogue site, this experience is shaping the future steps towards more complex space missions. They include the development of a mobile rover for JAXA's Martian Moons eXploration (MMX) in 2024 as well as demonstrations of novel multi-robot technologies at a Moon analogue site on the volcano Mt Etna in the ARCHES project. Within ARCHES, a demonstration mission is planned from the 14 June to 10 July 2021,1 during which heterogeneous teams of robots will autonomously conduct geological and mineralogical analysis experiments and deploy an array of low-frequency antennas to measure Jovian and solar bursts. This article is part of a discussion meeting issue 'Astronomy from the Moon: the next decades'.
