“REINFORCEMENT LEARNING WITH SPATIAL APPLICATIONS”
Smart cities offer more and more real-time information
provided by sensor networks and traffic cameras. This information can be
very valuable for transportation planing and analysing user behaviour.
For instance, knowing which parking spots are currently available close
to my destination is very valuable in order to reduce the travel time
and thus, maximize the resource usage and minimize the traffic load. The
future development of this information is usually uncertain (i.e.
non-deterministic). However, algorithms for routing applications should
consider that new information will become available during travelling
along the computed path. In order to exploit the provided information to
a full extend, it is not sufficient to compute a static route or travel
plan because the optimality of the plan might degrade as the state of
the environment might consistently change.
In order to plan transportation and understand observed trajectories in
smart environments, it is necessary to compute action policies instead
of static routes. A policy provides the most promising action for all
situations and in particular, the encountered situations. Analogously,
it makes sense to understand human behaviour based on the sequence of
decisions in the encountered situations. To compute and analyse
policies, the field of reinforcement learning already provides a rich
set of tools.
Matthias Schubert’s Bio:
Matthias Schubert is a professor for Computer Science at the LMU
Munich. He is one of the founders of the Data Science Lab @LMU Munich
and a member of the Munich Competence Center for Machine Learning. His
research interests comprise spatial information systems, representation
learning and artificial intelligence in non-deterministic environments.
With the proliferation of location-aware mobile devices and the emergence of everyday analytics, geospatial technology now spans every market, crosses national boundaries, and affects every trending issue. There is no doubt that cloud-based solutions are increasing in demand, requiring next generation, customizable technology to harness multisource data and transform it into focused solutions to be consumed by users of every level. The M.App Portfolio platform is designed to create smart, lightweight, customized market applications that address unique business and industry problems by combining geospatial analytics with cloud technology, as well as enterprise-level deployment environments. These applications, known as Hexagon Smart M.Apps, link sophisticated analytics and spatial models to geospatially relevant information, conveying data about solutions through intuitive, customizable, interactive and innovative displays. In this presentation, you will see several Smart M.Apps in action to better understand how this platform is changing the way we visualize, interpret, and interact with spatial information. Learn how Hexagon Geospatial has teamed with the World Antiquities Coalition to use Smart M.App technology to track missing and stolen cultural artifacts. See how the Green Space Analyzer provides a new way for decision makers to influence policy. Understand how a Smart M.App helps count endangered species in Africa. See how Smart M.Apps address the problems of refugee camps and can be used in country-wide census. Hexagon Geospatial’s technology provides the ability to address the challenge of linking business information with multisource multi-sensor data, in near real-time to answer questions and make decisions about our dynamically changing Earth.
“Industry 4.0” is shorthand for what the World Economic Forum calls “the Fourth Industrial Revolution.” The invention of the steam engine and construction of railroads brought the first industrial revolution in the 18th century. A second industrial revolution began in the 19th century with the advent of mass production. Digital computers heralded a third industrial revolution beginning in the 1960s. Today, the drivers of Industry 4.0 include “a ubiquitous and mobile internet, smaller, cheaper, and more powerful sensors, and artificial intelligence and machine learning.” Industry 4.0 is manifest in an Internet of Things that’s connecting billions of devices, and is likely to attract trillions in spending, in the coming decade. Many IoT devices “know where they are can act on their locational knowledge.” Foresman’s and Luscombe’s proposed Second Law of Geography claims that spatially enabled things have increased financial and functional utility. This increased utility, they argue, creates the basis for a spatially enabled economy.
However, other thought leaders worry that the Fourth Industrial Revolution may threaten many of today’s workers with “technological unemployment.” Not just the IoT, but international finance, social media, other human activities generate an unprecedented and ever-increasing volume, velocity and variety of data. Some foresee that human analysts and their employers will rely increasingly on machine learning and artificial intelligence to cope with the data deluge. Many already do. A body of research by economists, tech leaders, and forward-looking historians anticipates fundamental disruption of traditional employment by increasingly capable machines. This presentation will consider the implications of the IoT, and broader trends in data-driven discovery, for GIS work and workforce development.