Sören Schwertfeger

Fast 3D mapping by matching planes extracted from range sensor point-clouds

This article addresses fast 3D mapping by a mobile robot in a predominantly planar environment. It is based on a novel pose registration algorithm based entirely on matching features composed of plane-segments extracted from point-clouds sampled from a 3D sensor. The approach has advantages in terms of robustness, speed and storage as compared to the voxel based approaches. Unlike previous approaches, the uncertainty in plane parameters is utilized to compute the uncertainty in the pose computed by scan-registration. The algorithm is illustrated by creating a full 3D model of a multi-level robot testing arena.

3D forward sensor modeling and application to occupancy grid based sensor fusion

This paper presents a new technique for the update of a probabilistic spatial occupancy grid map using a forward sensor model. Unlike currently popular inverse sensor models, forward sensor models can be found experimentally and can represent sensor characteristics better. The formulation is applicable to both 2D and 3D range sensors and does not have some of the theoretical and practical problems associated with the current approaches which use forward models. As an illustration of this procedure, a new prototype 3D forward sensor model is derived using a beam represented as a spherical sector. Furthermore, this model is used for fusion of point-clouds obtained from different 3D sensors, in particular, time-of-flight sensors (Swiss-ranger, laser range finders), and stereo vision cameras. Several techniques are described for an efficient data-structure representation and implementation. The range beams from different sensors are fused in a common local Cartesian occupancy map. Experimental results of this fusion are presented and evaluated using Hough-transform performed on the grid.

A networking framework for teleoperation in safety, security, and rescue robotics

Safety, security, and rescue robotics is an important application field that can be viewed as a prototypical example of a domain where networked mobile robots are used for the exploration of unstructured environments that are inaccessible to or dangerous for humans. Teleoperation, based on wireless networks, is much more complex than what one might expect at first glance because it goes well beyond mere mappings of low-level user inputs - like joystick commands - to motor activations on a robot. Teleoperation for SSRR must move up to the behavior and mission levels where a single operator triggers short-time, autonomous behaviors, respectively, and supervises a whole team of autonomously operating robots. Consequently, a significant amount of heterogeneous data - video, maps, goal points, victim data, and so on - must be transmitted between robots and mission control. In this article, a networking framework for teleoperation in SSRR is presented. It was evaluated in a series of field tests and competitions, including the European Land Robot Trials and RoboCup events.

Efficient Representation in Three-Dimensional Environment Modeling for Planetary Robotic Exploration

Good situational awareness is an absolute must when operating mobile robots for planetary exploration. Three-dimensional (3-D) sensing and modeling data gathered by the robot are, hence, crucial for the operator. However, standard methods based on stereo vision have their limitations, especially in scenarios where there is no or only very limited visibility, e.g., due to extreme light conditions. Three-dimensional laser range finders (3-D-LRFs) provide an interesting alternative, especially as they can provide very accurate, high-resolution data at very high sampling rates. However, the more 3-D range data are acquired, the harder it becomes to transmit the data to the operator station. Here, a fast and robust method to fit planar surface patches into the data is presented. The usefulness of the approach is demonstrated in two different sets of experiments. The first set is based on data from our participation at the European Space Agency Lunar Robotics Challenge 2008. The second one is based on data from a Velodyne 3-D-LRF in a high-fidelity simulation with ground truth data from Mars.

Safety, Security, and Rescue Missions with an Unmanned Aerial Vehicle (UAV)

Several missions with an Unmanned Aerial Vehicle (UAV) in different realistic safety, security, and rescue field tests are presented. First, results from two safety and security missions at the 2009 European Land Robot Trials (ELROB) are presented. A UAV in form of an Airrobot AR100-B is used in a reconnaissance and in a camp security scenario. The UAV is capable of autonomous waypoint navigation using onboard GPS processing. A digital video stream from the vehicle is used to create photo maps—also known as mosaicking—in real time at the operator station. This mapping is done using an enhanced version of Fourier Mellin based registration, which turns out to be very fast and robust. Furthermore, results from a rescue oriented scenario at the 2010 Response Robot Evaluation Exercises (RREE) at Disaster City, Texas are presented. The registration for the aerial mosaicking is supplemented by an uncertainty metric and embedded into Simultaneous Localization and Mapping (SLAM), which further enhances the photo maps as main mission deliveries.

Maximum likelihood mapping with spectral image registration

A core challenge in probabilistic mapping is to extract meaningful uncertainty information from data registration methods. While this has been investigated in ICP-based scan matching methods, other registration methods have not been analyzed. In this paper, an uncertainty analysis of a Fourier Mellin based image registration algorithm is introduced, which to our knowledge is the first of its kind involving spectral registration. A covariance matrix is extracted from the result of a Phase-Only Matched Filter, which is interpreted as a probability mass function. The method is embedded in a pose graph implementation for Simultaneous Localization and Mapping (SLAM) and validated with experiments in the underwater domain.

Advancing the State of Urban Search and Rescue Robotics Through the RoboCupRescue Robot League Competition

The RoboCupRescue Robot League is an international competition that has grown to be an effective driver for the dissemination of solutions to the challenges posed by Urban Search and Rescue Robotics and accelerated the development of the performance standards that are crucial to widespread effective deployment of robotic systems for these applications. In this paper, we will discuss how this competition has come to be more than simply a venue where teams compete to find a champion and is now “A League of Teams with one goal: to Develop and Demonstrate Advanced Robotic Capabilities for Emergency Responders.”

Using competitions to advance the development of standard test methods for response robots

Competitions are an effective aid to the development and dissemination of standard test methods, especially in rapidly developing, fields with a wide variety of requirements and capabilities such as Urban Search and Rescue robotics. By exposing the development process to highly developmental systems that push the boundaries of current capabilities, it is possible to gain an insight into how the test methods will respond to the robots of the future. The competition setting also allows for the rapid iterative refinement of the test methods and apparatuses in response to new developments. For the research community, introducing the concepts behind the test methods at the research and development stage can also help to guide their work towards the operationally relevant requirements embodied by the test methods and apparatuses. This also aids in the dissemination of the test methods themselves as teams fabricate them in their own laboratories and re-use them in work outside the competition. In this paper, we discuss how international competitions, and in particular the RoboCupRescue Robot League competition, have played a crucial role in the development of standard test metrics for response robots as part of the ASTM International Committee of Homeland Security Applications; Operational Equipment; Robots (E54.08.01). We will also discuss how the competition has helped to drive a vibrant robot developer community towards solutions that are relevant to first responders.

Evaluation of map quality by matching and scoring high-level, topological map structures

Mapping is an important task for mobile robots. But assessing the quality of maps in a simple, efficient and automated way is not trivial and an ongoing research topic. A new approach on map evaluation is presented here. It is based on Topology Graphs as a topological, abstracted representation of 2D grid maps. The Topology Graphs are derived from Voronoi Diagrams that get post-processed to capture the high-level spatial structures. Based on a similarity metric on vertices in Topology Graphs, the vertices can be matched across maps and spatial (dis)similarities and hence errors in the mapping can be identified and measured. More precisely, the vertex-similarity is the basis to match the structures of Topology Graphs up to the identification of subgraph isomorphisms through wave-front propagation. This allows to determine important map quality attributes up to very challenging structural elements like brokenness, i.e., the number of locally correct partitions in the candidate map and their relative placement towards each other. Experiments with real robot generated maps including examples from various teams in the RoboCup Rescue competition are used to validate the usefulness of this method for map quality assessment.

Using a fiducial map metric for assessing map quality in the context of RoboCup Rescue

Mapping is an important task for mobile robots in general and for Safety, Security, and Rescue Robotics (SSRR) in particular. It is hence one core aspect which is evaluated in the RoboCup Rescue league. But assessing the quality of maps in a simple and efficient way is not trivial, especially if no detailed, complete ground truth data of the environment is available. A new approach on map evaluation is presented here. It makes use of artificial objects placed in the environment named “fiducials”. Using the known ground-truth positions and the positions of the fiducials identified in the map, a number of quality attributes can be assigned to that map. Depending on the application domain those attributes can weighed to compute a final score. Results are presented that are based on using this method during the RoboCup Rescue competition 2010 in Singapore where maps were generated by different teams in an maze populated with fiducials. Those maps are evaluated here and compared to a human judgment, showing the effectiveness of the fiducial approach.