Izvedba sistema za preprečevanje trkov mobilnega sistema na podlagi detekcije ovir s stereo kamero

ANTIĆ, MILOŠ (avtor), Škrjanc, Igor (mentor)

V magistrskem delu smo raziskali problem zaznavanja okolja s stereo kamero, ki se na področju mobilnih sistemov običajno uporablja za tridimenzionalno zaznavanje okolja v obliki oblaka točk. Problem rekonstrukcije običajno rešujemo s stereo vidom, ki sloni na epipolarni geometriji. Tridimenzionalno informacijo uporabimo za gradnjo lokalnega zemljevida robota, na podlagi katerega smo implementirali algoritme za preprečevanje trkov. Z globinsko kamero D435i pridobivamo globinsko sliko, na podlagi katere smo s triangulacijo rekonstruirali tridimenzionalno predstavitev okolja. S segmentacijo okolja smo zgradili lokalni zemljevid robota, kjer smo z morfološko operacijo dilatacije in filtrom lukenj izboljšali predstavitev dobljenega zemljevida robota. Na zemljevidu smo s segmentacijo dosegli delitev prostora na tla, ovire in nezasedene predele, tj. območja, kjer nismo uspeli pridobiti informacije iz trenutnega prizora. Na podlagi te informacije smo izvedli sistem za preprečevanje trkov pri vožnji naravnost in pri zavijanju. Preprečevanje trkov je zasnovano na proporcionalnem zmanjšanju hitrosti glede na razdaljo do najbližje ovire oz. najmanjšem času do trka. V situacijah, ki lahko privedejo do trka z oviro, sistem za vodenje posreduje in po potrebi privede mobilni sistem v stanje mirovanja. V magistrskem delu smo detekcijo ovir s stereo kamero in delovanje algoritmov vodenja preizkusili na robotu Pioneer 3-AT, ki se običajno uporablja za raziskovalne namene. Sistem za detekcijo ovir in preprečevanje trkov izpolnjujeta zahteve za delovanje v realnem času. Implementirani algoritmi so izvedeni v programskem orodju Matlab, ki preko brezžične povezave komunicirajo z robotom, na katerem teče meta-operacijski sistem ROS. V tem delu smo predstavili kalibracijo sistema za detekcijo ovir, ki omogoča, da robot avtomatsko določi ravnino tal in lego stereo kamere v ravnini. Tovrstna kalibracija mobilnega sistema je pomembna tudi zaradi poenostavitve dela s sistemom (npr. v industriji), saj lahko z možnostjo avtomatičnega umerjanja odstranimo potrebo po ekspertnem znanju in zmanjšamo strošek vgradnje.

• Jezik: Slovenski jezik
• Ključne besede: avtonomni mobilni sistemi, strojni vid, stereo kamera, Pioneer 3-AT, Intel RealSense D435i, segmentacija okolja, preprečevanje trkov, detekcija ovir, merjenje globine, senzorji za zaznavanje ovir
• Vrsta gradiva: Magistrsko delo/naloga
• Organizacija: FE - Fakulteta za elektrotehniko
• Leto izida: 2019
• PID: 20.500.12556/RUL-110084
• Datum objave v RUL: 12.09.2019

Sekundarni jezik

• Jezik: Angleški jezik
• Naslov: An Implementation of Collision Prevention System for a Mobile Robot based-on Obstacle Detection with a Stereo Camera

Izvleček

In the thesis we investigated the problem of environmental sensing with a stereo camera, which is commonly used in the field of mobile systems for three-dimensional sensing of the environment in the form of a point cloud. The problem of reconstruction is usually solved by stereo vision based on epipolar geometry. We use three-dimensional information to build a local robot map based on which we implemented collision avoidance algorithms. With the D435i depth camera, we obtain a depth image, which was used for reconstruction of a three-dimensional representation of the environment through triangulation. With the segmentation of the environment we built a local map of the robot, where we improved the representation of the obtained map of the robot by means of a morphological dilation operation and a hole filter. On the map, segmentation achieved the division of space into floors, obstacles and unoccupied areas, i.e. areas where we were unable to retrieve information from the current scene. Based on this information, we implemented a system for preventing collisions when driving straight and when cornering. Collision prevention is based on a proportional reduction of speed with respect to the distance to the closest obstacle or minimum time to impact. In situations that may result in a collision with an obstacle, the control system shall intervene and, if necessary, bring the mobile system to a standstill. In the master's thesis we tested obstacle detection with a stereo camera and the operation of control algorithms on a Pioneer 3-AT robot, which is commonly used for research purposes. Obstacle detection and collision avoidance systems meet the requirements for real-time operation. The algorithms are implemented in the Matlab software tool, which communicate with robot via a wireless connection. A meta-operating system ROS is running on the robot. In this thesis, we introduced the calibration of an obstacle detection system that allows the robot to determine automatically the ground plane and pose of the stereo camera in the plane. This kind of calibration is also important in order to simplify the work with the mobile system (e.g. in the industry), since the possibility of automatic calibration can eliminate the need for expert knowledge and reduce the cost of system integration.

• Ključne besede: autonomous mobile systems, machine vision, stereo camera, Pioneer 3-AT, Intel RealSense D435i, environment segmentation, collision prevention, obstacle detection, depth measurement, proximity sensors