Cyrill Stachniss

Spatial Cognition is concerned with the acquisition, organization, utilization and revision of knowledge about spatial environments, be it real or abstract, human or machine. Research issues range from the investigation of human spatial cognition to mobile robot navigation. The goal of the SFB/TR 8 is to investigate the cognitive foundations for human-centered spatial assistance systems.

The SFB/TR 8 Spatial Cognition comprises 13 projects which are structured into the three research areas Reasoning, Action, and Interaction. Reasoning projects are concerned with internal and external representations of space and with inference processes using these representations. Action projects are concerned with the acquisition of information from spatial environments and with actions and behavior in these environments. Interaction projects are concerned with communication about space by means of language and maps.

Robotics-enabled Logistics and Assistive Services for the Transformable Factory of the Future (TAPAS) is a project funded by the European Commission within FP7. The goal of TAPAS is to pave the ground for a new generation of transformable solutions to automation and logistics for small and large series production, economic viable and flexible, regardless of changes in volumes and product type.

TAPAS pioneers and validates key components to realize this vision: mobile robots with manipulation arms will automate logistic tasks more flexible and more complete by not only transporting, but also collecting needed parts and delivering them right to the place were needed. TAPAS robots will even go beyond moving parts around the shop floor to create additional value: they will automate assistive tasks that naturally extend the logistic tasks, such as preparatory and post-processing works, e.g., pre-assembly or machine tending with inherent quality control. TAPAS robots might initially be more expensive than other solutions, but through this additional creation of value and by a faster adaptation to changes with new levels of robustness, availability, and completeness of jobs TAPAS robots promise to yield an earlier return of investment.

Flexible Skill Acquisition and Intuitive Robot Tasking for Mobile Manipulation in the Real World is a project funded by the European Commission within FP7. The goal of First-MM to build the basis for a new generation of autonomous mobile manipulation robots that can flexibly be instructed to perform complex manipulation and transportation tasks. The project will develop a novel robot programming environment that allows even non-expert users to specify complex manipulation tasks in real-world environments. In addition to a task specification language, the environment includes concepts for probabilistic inference and for learning manipulation skills from demonstration and from experience. The project will build upon and extend recent results in robot programming, navigation, manipulation, perception, learning by instruction, and statistical relational learning to develop advanced technology for mobile manipulation robots that can flexibly be instructed even by non-expert users to perform challenging manipulation tasks in real-world environments. designed to autonomously navigate in urban environments outdoors as well as in shopping malls and shops to provide various services to users including guidance, delivery, and transportation.

In the field of robotics, there has recently been a tremendous progress in the development of autonomous robots that offer various services to their users. Typical services include support of elderly people, cleaning, transportation and delivery tasks, exploration of unaccessible hazardous environments, or surveillance. Most of the systems developed so far, however, are restricted to indoor scenarios, non-urban outdoor environments, or road usage with cars. There is serious lack of capabilities of mobile robots to navigate safely in highly populated outdoor environments. This ability, however, is a key competence for a series of robotic applications.

The goal of the EUROPA project is to bridge this gap and to develop the foundations for service robots designed to autonomously navigate in urban environments outdoors as well as in shopping malls and shops to provide various services to users including guidance, delivery, and transportation. EUROPA will develop and apply sophisticated probabilistic scene interpretation techniques to deal with the unpredictable and changing environments. Based on data gathered with its sensors, the robot will acquire a detailed model of the environment, detect and track moving objects in the environment, adapt its navigation behavior according to the current situation, and communicate with its users in a natural way, even remotely. Key innovations of the project are made by {\em robustly and reliable} addressing the autonomous navigation problem in complex and populated environments, the ability to build {\em appropriate} spatial models, and by reasoning about them based on the {\em verbal and natural interaction} with users. EUROPA is targeted at developing novel technologies that will open new perspectives for commercial applications of service robots in the future.

To validate the concepts developed in the project, the EUROPA robot will be deployed in populated urban environments such as the downtown area of Zurich, Switzerland, to solve a series of tasks including transportation and guidance.

Contemporary robots and other cognitive artifacts are not yet ready to autonomously operate in complex real world environments. One of the major reasons for this failure in creating cognitive situated systems is the difficulty in the handling of incomplete knowledge and uncertainty.

By taking up inspiration from the brains of mammals, including humans, the BACS project will investigate and apply Bayesian models and approaches in order to develop artificial cognitive systems that can carry out complex tasks in real world environments. The Bayesian approach will be used to model different levels of brain function within a coherent framework, from neural functions up to complex behaviors. The Bayesian models will be validated and adapted as necessary according to neuro-physiological data from rats and humans and through psychophysical experiments on humans. The Bayesian approach will also be used to develop four artificial cognitive systems concerned with (i) autonomous navigation, (ii) multi-modal perception and reconstruction of the environment, (iii) semantic facial motion tracking, and (iv) human body motion recognition and behavior analysis. The conducted research shall result in a consistent Bayesian framework offering enhanced tools for probabilistic reasoning in complex real world situations. The performance will be demonstrated through its applications to drive assistant systems and 3D mapping, both very complex real world tasks. BACS is an Integrated Project under the 6th Framework program of the European Commission running from January 2006 to February 2010.

RAWSEEDS - Robotics Advancements through Web-publishing of Sensorial and Elaborated Extensive Data Sets. The aim of the Rawseeds Project is to stimulate and support progress in autonomous robotics by providing a comprehensive, high-quality Benchmarking Toolkit. The absence of standard benchmarks is a widely acknowledged problem in the robotics field, and is doubly harmful to it: firstly, because it prevents recognition of scientific and technical progress, thus discouraging research and development; and secondly, because it prevents new actors (and particularly companies) from entering the robotic sector, as heavy investments are needed to compensate for that absence. Rawseeds’ datasets are sets of time-synced data streams, generated by the sensors aboard a robot platform when it moves through an environment. The datasets are gathered in real-world locations. The Rawseeds Benchmarking Toolkit is mainly targeted to the problems of localization, mapping and SLAM (i.e. Simultaneous Localization And Mapping) in robotics; but its use is not limited to them. It will be freely downloadable from this website, as soon as it is completed. By the way: “Rawseeds” means “Robotics Advancement through Web-publishing of Sensorial and Elaborated Extensive Data Sets”.

The main goal of the EU project CoSy is to advance the science of cognitive systems through a multi-disciplinary investigation of requirements, design options and trade-offs for human-like, autonomous, integrated, physical (eg., robot) systems, including requirements for architectures, for forms of representation, for perceptual mechanisms, for learning, planning, reasoning and motivation, for action and communication.

The project aims at integrating leading edge technology in the field of service robotics and to develop an open, extensible system architecture. The project is funded by the German ministery of research.

The EU funded project WebFAIR addresses the marketing and promotion requirements of large commercial exhibitions by providing broad access to information, services and commodities exhibited at the event. Essentially, WebFAIR aims at providing the means to remote corporate and private users for active and personalised workplace exploration and information visualisation for commercial purposes.

CARMEN an open-source collection of software for mobile robot control. CARMEN is modular software designed to provide basic navigation primatives including: module communication infrastructure, base and sensor control, obstacle avoidance, localization, path planning, and mapping.

• Visit the CARMEN homepage
  
• Download the latest CARMEN release
  
• See the CARMEN Binary as well as source code/API documentation
  

The simultaneous localization and mapping (SLAM) problem has been intensively studied in the robotics community in the past. Different techniques have been proposed but only a few of them are available as implementations to the community. The goal of OpenSLAM.org is to provide a platform for SLAM researchers which gives them the possibility to publish and promote their algorithms.

HOG-Man is a hierarchical optimization solution to the graph-based simultaneous localization and mapping problem. During online mapping, the approach corrects only the coarse structure of the scene and not the overall map. In this way, only updates for the parts of the map that need to be considered for making data associations are carried out. The hierarchical approach provides accurate non-linear map estimates while being highly efficient. The error minimization approach furthermore exploits the manifold structure of the underlying space. In this way, it avoids singularities in the state space parameterization. The overall approach is accurate, efficient, designed for online operation, overcomes singularities, provides a hierarchical representation, and outperforms a series of other state-of-the-art methods.

TORO is an optimization approach for constraint-network. It provides a highly efficient, gradient descent-based error minimization procedure. In 2006, Olson et al. presented a novel approach to solve the graph-based SLAM problem by applying stochastic gradient descent to minimize the error introduced by constraints. TORO is an extension of Olson's algorithm. It applies a tree parameterization of the nodes in the graph that significantly improves the performance and enables a robot to cope with arbitrary network topologies. The latter allows us to bound the complexity of the algorithm to the size of the mapped area and not to the length of the trajectory.

GMapping is highly efficient Rao-Blackwellized particle filer to learn grid maps I developed together with Giorgio Grisetti. The project is hosted on www.openslam.org and the sourcecode is available.

This project is a cooperation between the ETH Zurich, the EPLF in Lausanne, and the University of Freiburg. The goal is to build an automous (Smart) car.

I am acutually not an official contributor of Radish, however, I like it and submitted a series of robotic datasets into that repository.

The Robotics Data Set Repository provides a collection of standard robotics data sets. You will find there:

• Logs of odometry, laser and sonar data taken from real robots.
• Logs of all sorts of sensor data taken from simulated robots.
• Environment maps generated by robots.
• Environment maps generated by hand (i.e., re-touched floor-plans).

By making these data sets available to the community, Radish aims to facilitate the development, evaluation and comparison of robotics algorithms. While the current focus is clearly on localization and mapping, Radish will ultimately expand to reflect the interests of the broader robotics community.

Radish is a community effort. Researchers are invited to download and make use of the data sets, and, in return, to make their own contributions to the repository.