Fusion of ranging data from robot teams operating in confined areas

  title={Fusion of ranging data from robot teams operating in confined areas},
  author={D. Lyons and Karma Shrestha and Tsung-Ming Liu},
  booktitle={Defense, Security, and Sensing},
We address the problem of fusing laser ranging data from multiple mobile robots that are surveying an area as part of a robot search and rescue or area surveillance mission. We are specifically interested in the case where members of the robot team are working in close proximity to each other. The advantage of this teamwork is that it greatly speeds up the surveying process; the area can be quickly covered even when the robots use a random motion exploration approach. However, the disadvantage… Expand
Eliminating mutual views in fusion of ranging and RGB-D data from robot teams operating in confined areas
An approach based on a model of human visual attention is presented and compared with prior work and with other related work on the problem of fusing laser and RGB-Data from multiple robots operating in close proximity to one another. Expand
Evaluation of parallel reduction strategies for fusion of sensory information from a robot team
A communication and fusion approach based on the parallel reduction operation, where data is combined in a series of steps of increasing subsets of the team, is proposed and evaluated, indicating that selecting groups to combine based on similar pose but distant location yields the best results. Expand
Leveraging area bounds information for autonomous decentralized multi-robot exploration
The D-SBPF approach yields a simple potential field control strategy for all robots but nonetheless has good dispersion and overlap performance in exploring areas with convex geometry while avoiding potential minima. Expand
Leveraging Area Bounds Information for Autonomous Multirobot Exploration
The SBPF method is based on a potential field approach that leverages knowledge of the overall bounds of the area to be explored to allow a simpler potential field control strategy for all robots but which nonetheless has good dispersion and overlap performance in all the multirobot scenarios while avoiding potential minima. Expand


Gaussian Multi-Robot SLAM
The algorithm enables teams of robots to build joint maps, even if their relative starting locations are unknown and landmarks are ambiguous, through a sparse information filter technique that represents maps and robot poses by Gaussian Markov random fields. Expand
3D Laser scan registration of dual-robot system using vision
A novel particle filter algorithm is proposed to identify the real pose of the wall-climbing robot out of up to four possible solutions to P3P problem using Grunert's algorithm and the initial estimate ensures convergence of the ICP algorithm to a global minimum at all times. Expand
Globally Consistent Range Scan Alignment for Environment Mapping
The problem of consistent registration of multiple frames of measurements (range scans), together with therelated issues of representation and manipulation of spatialuncertainties are studied, to maintain all the local frames of data as well as the relative spatial relationships between localframes. Expand
Merging maps via Hough transform
  • Stefano Carpin
  • Computer Science
  • 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2008
It turns out that the proposed algorithm for merging multiple occupancy grid maps computed by multiple robots independently exploring a shared indoor environment is robust and positively influenced by the use of more refined approaches to compute the Hough transform. Expand
Large-scale multi-robot mapping in MAGIC 2010
  • R. Reid, T. Bräunl
  • Computer Science
  • 2011 IEEE 5th International Conference on Robotics, Automation and Mechatronics (RAM)
  • 2011
A large-scale decentralised multi-robot mapping system that outputs globally optimised metric maps in real-time that scales linearly with map size and on commodity hardware can easily map a 500m×500m urban area. Expand
Efficient Sparse Pose Adjustment for 2D mapping
This paper compares their method, called Sparse Pose Adjustment (SPA), with competing indirect methods, and shows that it outperforms them in terms of convergence speed and accuracy, and demonstrates its effectiveness on a large set of indoor real-world maps, and a very large simulated dataset. Expand
Parallelization of Scan Matching for Robotic 3D Mapping
The solution to the 3D mapping problem by parallelization is extended and the availability of multi-core processors as well as efficient programming schemes as OpenMP permit the parallel execution of robotics task with on-board means. Expand
Removing Moving Objects from Point Cloud Scenes
This work presents an algorithm to explicitly detect and remove moving objects from multiple views of a scene by finding corresponding objects in twoViews, and presents results on scenes collected around a university building. Expand
Avoiding moving outliers in visual SLAM by tracking moving objects
This paper describes the parallel implementation of monoSLAM with a 3D object tracker, allowing reasoning about moving objects and occlusion, and investigates the impact on camera pose in mono SLAM of including and avoiding moving features. Expand
Segmentation of Dynamic Objects from Laser Data
A method to segment dynamic objects from high-resolution low-rate laser scans by tagging data points as static or dynamic based on the classification of pixel data from registered imagery. Expand