Refine
Year of publication
Document Type
- Conference Proceeding (36)
- Article (9)
- Part of a Book (3)
Keywords
- Autonomous mobile robots (2)
- Industry 4.0 (2)
- Multi-robot systems (2)
- Smart factory (2)
- Automation (1)
- Benchmark (1)
- Computational modeling (1)
- Control (1)
- Cyber-physical systems (1)
- GPU (1)
- Heuristic algorithms (1)
- Lidar (1)
- Mpc (1)
- Navigation (1)
- Path-following (1)
- RoboCup (1)
- Self-driving (1)
- autonomous driving (1)
- do-it-yourself (1)
- education (1)
Institute
- MASKOR Institut für Mobile Autonome Systeme und Kognitive Robotik (48) (remove)
With autonomous mobile robots receiving increased
attention in industrial contexts, the need for benchmarks
becomes more and more an urgent matter. The RoboCup
Logistics League (RCLL) is one specific industry-inspired scenario
focusing on production logistics within a Smart Factory.
In this paper, we describe how the RCLL allows to assess the
performance of a group of robots within the scenario as a
whole, focusing specifically on the coordination and cooperation
strategies and the methods and components to achieve them.
We report on recent efforts to analyze performance of teams in
2014 to understand the implications of the current grading
scheme, and derived criteria and metrics for performance
assessment based on Key Performance Indicators (KPI) adapted
from classic factory evaluation. We reflect on differences and
compatibility towards RoCKIn, a recent major benchmarking
European project.
In the future, we expect manufacturing companies to follow a new paradigm that mandates more automation and autonomy in production processes. Such smart factories will offer a variety of production technologies as services that can be combined ad hoc to produce a large number of different product types and variants cost-effectively even in small lot sizes. This is enabled by cyber-physical systems that feature flexible automated planning methods for production scheduling, execution control, and in-factory logistics.
During development, testbeds are required to determine the applicability of integrated systems in such scenarios. Furthermore, benchmarks are needed to quantify and compare system performance in these industry-inspired scenarios at a comprehensible and manageable size which is, at the same time, complex enough to yield meaningful results.
In this chapter, based on our experience in the RoboCup Logistics League (RCLL) as a specific example, we derive a generic blueprint for how a holistic benchmark can be developed, which combines a specific scenario with a set of key performance indicators as metrics to evaluate the overall integrated system and its components.
Ground or aerial robots equipped with advanced sensing technologies, such as three-dimensional laser scanners and advanced mapping algorithms, are deemed useful as a supporting technology for first responders. A great deal of excellent research in the field exists, but practical applications at real disaster sites are scarce. Many projects concentrate on equipping robots with advanced capabilities, such as autonomous exploration or object manipulation. In spite of this, realistic application areas for such robots are limited to teleoperated reconnaissance or search. In this paper, we investigate how well state-of-the-art and off-the-shelf components and algorithms are suited for reconnaissance in current disaster-relief scenarios. The basic idea is to make use of some of the most common sensors and deploy some widely used algorithms in a disaster situation, and to evaluate how well the components work for these scenarios. We acquired the sensor data from two field experiments, one from a disaster-relief operation in a motorway tunnel, and one from a mapping experiment in a partly closed down motorway tunnel. Based on these data, which we make publicly available, we evaluate state-of-the-art and off-the-shelf mapping approaches. In our analysis, we integrate opinions and replies from first responders as well as from some algorithm developers on the usefulness of the data and the limitations of the deployed approaches, respectively. We discuss the lessons we learned during the two missions. These lessons are interesting for the community working in similar areas of urban search and rescue, particularly reconnaissance and search.