Posnemanje elementov človekove hoje na humanoidnem robotu

REZAR, ROK (avtor), Mihelj, Matjaž (mentor), Ude, Aleš (komentor)

Cilj naloge je bil razviti sistem, ki robotu omogoča posnemanje elementov človekove hoje (poglavje štiri), ki jo zajamemo z globinsko kamero Microsoft Kinect. Obravnavali smo tudi problem preprečevanja trkov med udi humanoidnega robota. V drugem poglavju smo obravnavali glavni komponenti, ki smo ju uporabili v našem delu. To sta humanoidni robot HOAP-3 in Microsoft Kinect. Humanoidni robot je robot, katerega zgradba je podobna človekovemu telesu. Humanoidni roboti praviloma zajemajo trup z glavo, dve roki in dve nogi. Med najpomembnejše elemente, ki opredeljujejo zmogljivost humanoidnih robotov, spadajo 1) uporabljeni senzorji in aktuatorji, 2) sposobnost zagotavljanja energije za delovanje, 3) samostojno učenje kompleksnih nalog brez ali z zunanjim posredovanjem ter s prilagajanjem strategij učenja glede na okolico in 4) sposobnost varnega delovanja v človekovem okolju brez ogrožanja varnosti ljudi v okolici. Fujitsu HOAP-3 je humanoidni robot, ki ga odlikuje kompaktnost, nizka teža ter enostavno upravljanje. Ima 28 sklepov z električnimi servomotorji, dve kameri, ki služita za vid, mikrofon, triosni žiroskop, pospeškomer, senzorji sile na podplatih in v zapestjih, merilnik razdalje, vgrajen pa ima tudi modul za razpoznavanje in sintezo govora. Microsoft Kinect je barvno-globinska kamera, s katero lahko zaznamo in izračunamo gibanje ljudi v prostoru. Kinect omogoča sledenje do šestim ljudem in do 25 sklepom na osebo. V našem delu smo Kinect uporabili za zajem gibanja demonstratorja. V tretjem poglavju sledi posnemanje gibanja rok človeka, preprečevanje trkov med segmenti robota ter opis kontrole stabilnosti. Demonstratorjeva gibanja, ki jih zaznamo s Kinectom, lahko prenesemo na humanoidne robote, saj se ti lahko gibljejo na podoben način kot ljudje. Za uspešno posnemanje pa pogosto ni dovolj, da demonstratorjeve gibe direktno prenesemo s človeka na robota, temveč moramo poskrbeti, da ne prihaja do samotrkov in da robot ostane stabilen. V tej nalogi smo razvili metodo izogibanja samotrkom s pomočjo metode prioritete nalog. Primarna naloga je preprečevanje trkov, sekundarna naloga pa je gibanje demonstratorja posneto s Kinectom. Če želimo, da robot uspešno posnema gibanje človeka, mora med posnemanjem demonstratorjevega gibanja ostati stabilen. Robot je najbolj stabilen, ko je točka ničelnega navora (angl. zero moment point, ZMP) v centru podpornega poligona, ki obkroža nogi robota. Pri posnemanju elementov človekove hoje mora primarna naloga skrbeti za nadzor stabilnosti, medtem ko se sekundarna naloga nanaša na posnemanje gibanja. ZMP je odvisen od gibanja centra težišča robota. Vse to pa je pomembno za načrtovanje trajektorij hoje, ki jih v našem delu uporabljamo v poglavju štiri.

• Jezik: Slovenski jezik
• Ključne besede: humanoidna robotika, zaznavanje gibanja človeka, posnemanje elementov hoje, preprečevanje trkov
• Vrsta gradiva: Magistrsko delo/naloga
• Organizacija: FE - Fakulteta za elektrotehniko
• Leto izida: 2015
• PID: 20.500.12556/RUL-76597
• Datum objave v RUL: 24.12.2015

Sekundarni jezik

• Jezik: Angleški jezik
• Naslov: Imitation of elements of human walking in a humanoid robot

Izvleček

The main goal of this thesis was to create a system that enables a humanoid robot to imitate human walking (chapter four), which is captured by an RGB-D camera like for example Microsoft Kinect. We also considered how to prevent collisions between the limbs of a humanoid robot during imitation. In the second chapter we discuss the main components that are used in our work. These are humanoid robot HOAP-3 and Microsoft Kinect. Humanoid robot is a robot whose structure is similar to the structure of a human body. Humanoid robots are typically comprised of the torso and the head, two arms, and two legs. Among the most important elements that define the capabilities of humanoid robots are: 1) sensors and actuators used to build the robot, 2) ability to provide energy for autonomous operation, 3) ability to effectively learn complex tasks with or without external teacher intervention, including movement adaptation to the enviroment, 4) ability to securely operate in human environments, without compromising safety of people in the area. Fujitsu HOAP-3 is a humanoid robot distinguished by its compactness, low weight, and easy operation. It has 28 joints with electric servomotors, two cameras to provide visual information, microphone, three axis gyroscope, accelerometer, force sensors on the soles of the feet, distance meter, and a built-in module for recognition and speech synthesis. Microsoft Kinect is an RGB-D camera that can be applied to detect and follow human motion in 3-D space. Range images are essential to enable Kinect to track up to six people and up to 25 joints per person. In our work we used Kinect to capture the motion of a human demonstrator. In the third chapter follows the human hands movement imitation, preventing collisions between robot segments and descritption of stability control. Due to its similarity to people, a humanoid robot can imitate human motion captured by Kinect. For a more effective movement imitation, two additional problems need to be solved: collision avoidance and stability of the robot. In this thesis collision avoidance was implemented using the task priority approach. In this context, the primary task is to prevent collisions between the robot body parts, The secondary task is to imitate the movement acquired by Kinect. For effective imitation of human walking, the robot must remain stable while imitating the demonstrator's motion. The robot is most stable when the zero moment point (ZMP) is in the center of the support polygon that surrounds the legs of the robot. Thus when imitating human body motion while walking, the primary task must ensure the stability of the robot, while the secondary task refers to the imitation of the demonstrator's movement. ZMP depends on the center of gravity of the robot. All this is important for planning walking trajectories that are used in our work in chapter four.

• Ključne besede: Humanoid robot, Human motion detection, Walking elements imitation, Collision avoidance