Visual SLAM and human recognition system of a legged robot | |
| Author | Ipiales, Jose Carlos Perez |
| Call Number | AIT Thesis no.ISE-19-38 |
| Subject(s) | Robots SLAM (Computer program language) Computer vision |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Mechatronics, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | |
| Abstract | The purpose of this project was to design a 3D printed 4-legged indoors robot which incorporates a Visual SLAM system and that is able to manage the intrinsic movement of the depth camera when the locomotion and the perturbations associated are happening. At the same time this robot runs a tiny YOLOv2 deep neural network which can recognize persons with an acceptable level of accuracy and in real time operation. This robot uses ROS (Robotic Operational System) and is remotely connected to a PC that performs the computational processes required by the Visual SLAM using RTabMap while YOLO and the high-level control is being managed by a Jetson Nano board which has a serial connection with an Arduino Due whose function is to perform the low-level control necessary to perform the motion. |
| Year | 2019 |
| Corresponding Series Added Entry | |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Industrial Systems Engineering (DISE) |
| Academic Program/FoS | Industrial Systems Engineering (ISE) |
| Chairperson(s) | Manukid Parnichkun; |
| Examination Committee(s) | Mongkol Ekpanyapongl;Pisut Koomsap; |
| Scholarship Donor(s) | Secretariat of Higher Education, Science, Technology and Innovation (SENESCYT), Ecuador; |
| Degree | Thesis (M. Eng.) --Asian Institute of Technology, 2019 |