Robot mapping in large-scale mixed indoor and outdoor environments

Abstract

Tactical situational awareness in unstructured and mixed indoor/ outdoor scenarios is needed for urban combat as well as rescue operations. Two of the key functionalities needed by robot systems to function in an unknown environment are the ability to build a map of the environment and to determine its position within that map. In this paper, we present a strategy to build dense maps and to automatically close loops from 3D point clouds; this has been integrated into a mapping system dubbed OmniMapper. We will present both the underlying system, and experimental results from a variety of environments such as office buildings, at military training facilities and in large scale mixed indoor and outdoor environments.

Autonomous Exploration Using an Information Gain Metric

“…Specifically, the iSAM2 14 implementation within GTSAM is used as the map optimizer in this work. OmniMapper has been used in prior work to build maps of indoor and outdoor environments 11 and for multirobot mapping. [15][16][17] OmniMapper builds a pose graph where nodes are poses along the robot's trajectory and edges are measurements between poses.…”

“…Our technique is most similar to this work; the key difference being that we use the iSAM2 nonlinear optimization engine to efficiently compute the effect of potential loop closures, which are discovered by executing kinematically feasible trajectories, while the previous work 9,10 used an approximate sparse information filter to compute the value of the information, which can be added through loop closure while following a probabilistic road map. It is not clear from Valencia et al 9 if their approach is scalable to areas larger than a few rooms, whereas our approach has been evaluated on medium-sized floor plans in this work, and our mapping system on large buildings in Rogers et al 11 Here, we document a method of autonomous exploration that uses an information gain metric and SLAM techniques to map an unknown area. We show that this technique improves the efficiency and accuracy of existing techniques and that it can be implemented on widely available robot hardware.…”

Mapping with a ground robot in GPS denied and degraded environments

“…OmniMapper has been used in prior work to build maps of indoor and outdoor environments [17], to determine mapping performance with sensory degradation [11], for multi-robot mapping [12], [9], and multi-robot mapping with heterogenous sensory modalities [10]. The system has also been used to support semantic mapping, where additional high-level information is included within a map as it is observed by the robot.…”

“…A final GPS operational regime is where a robot is unable to ever get a GPS fix, such as when it remains indoors for its entire operation. This scenario is eqivalent to mapping without GPS measurements, please refer to our prior work for details on indoor mapping without GPS [17], [10], [20], [21], [11]. The first experiment is designed to establish the usefulness of the GPS plugin in an open setting which admits continuous GPS signal visibility.…”