Avancerad sökning
Visar resultat 1 - 5 av 14 uppsatser som matchar ovanstående sökkriterier.
1. Deep Learning Model Deployment for Spaceborne Reconfigurable Hardware : A flexible acceleration approach
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Space debris and space situational awareness (SSA) have become growing concerns for national security and the sustainability of space operations, where timely detection and tracking of space objects is critical in preventing collision events. Traditional computer-vision algorithms have been used extensively to solve detection and tracking problems in flight, but recently deep learning approaches have seen widespread adoption in non-space related applications for their high accuracy. LÄS MER
2. Implementation of Bolt Detection and Visual-Inertial Localization Algorithm for Tightening Tool on SoC FPGA
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : With the emergence of Industry 4.0, there is a pronounced emphasis on the necessity for enhanced flexibility in assembly processes. In the domain of bolt-tightening, this transition is evident. Tools are now required to navigate a variety of bolts and unpredictable tightening methodologies. LÄS MER
3. Simulation and Control System Design for Autonomous Gliding to a Given Location
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The aim of this project was to design a flightcontrol system with the purpose of safely guiding a glidertoward a given GPS location over a distance of at least 50km. More specifically, the aim was to develop a control systemfor autonomous gliding and implement it on a given data hubcontaining sensors, GPS-module, microcontroller and a FieldProgrammable Gate Array (FPGA). LÄS MER
4. Automation av parametrisk CAD-modellering inom programmet Inventor
Kandidat-uppsats, Mälardalens högskola/Akademin för innovation, design och teknikSammanfattning : Companies today are constantly looking to improve the lead time of design and production processes through streamlining the process and looking for new solutions. CAD, computer-aided design, is something that has been very helpful for this. LÄS MER
5. Hardware Acceleration in the Context of Motion Control for Autonomous Systems
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : State estimation filters are computationally intensive blocks used to calculate uncertain/unknown state values from noisy/not available sensor inputs in any autonomous systems. The inputs to the actuators depend on these filter’s output and thus the scheduling of filter has to be at very small time intervals. LÄS MER