BADGER at the 2018 International conference on Intelligent Robots and Systems (IROS 2018)

BADGER participated in this year’s IROS conference, which was held in Madrid, Spain, on October 1-5, 2018, through a BADGER booth at the IROS 2018 exhibition space, as well as a scientific paper orally presented during the conference’s technical program.

The BADGER booth at IROS 2018 gave us the opportunity to present the conference audience with a series of preliminary modules that have already been developed for the BADGER robot. Further to this hands-on experience, rolling videos showed results from the multifaceted R&D project efforts, in a series of research fields, from underground robot mechatronic design and navigation approaches, through to underground robot novel perception and cognition methods.

The scientific paper of BADGER in IROS 2018, presented a novel approach for 3D Underground Mapping with a Mobile Robot and a Ground Penetrating Radar antenna array integrated on it. The paper, entitled “3D Underground Mapping with A Mobile Robot and a GPR Antenna” was authored by G. Kouros (1), I. Kotavelis (1), E. Skartados (1), D. Giakoumis (1), A. Simi (2), G. Manacorda (2) and D. Tzovaras (1), of CERTH-ITI (1) and IDS (2) respectively. The paper was presented in IROS by I. Kostavelis and D. Tzovaras of CERTH-ITI.

The abstract of the BADGER IROS paper on underground mapping follows:

Automatic subsurface mapping is essential in the construction services, as it is anticipated to become the main operational environment of the future robots to be realized in the respective domain. Towards this direction, the paper at hand, introduces for the first time herein, an integrated framework for subsurface mapping by exploiting a surface operating mobile robot with a Ground Penetrating Radar (GPR). The mobile robot tows the GPR antenna, which is mounted on a specifically designed trailer, and is utilized as the mean to cover the surface area, while at the same time the antenna scans the subsurface by emitting electromagnetic pulses. The gathered data are processed for the construction of a subsurface 3D map. Specifically, image processing techniques, that involve background segmentation, HOG feature extraction, hypothesis verification and matching are applied on the 2D radargram (B-Scan) for the detection of the salient points that correspond to buried utilities. By employing the pulse propagation velocity into the subsurface and the soil utilities, the salient points are expressed in world coordinates and used for the composition of the 3D subsurface map. Our method has been evaluated on a real test site, accompanied by groundtruth annotation data of experts and revealed remarkable performance, exhibiting not only the feasibility of underground mapping but also the capacity to obtain exploitable results for underground robotic applications.