Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 10 of 10 for “"Robotic algorithms"”.
-
Mathematical robotic algorithms for mowing a field
Master of Science (M.S.)
-
Black-Box Worst Case Execution Time Analysis on Real-Time Robotic Algorithms
This thesis compares Genetic Algorithms (GA) and Reinforcement Learning (RL) for estimating Worst Case Execution Time (WCET) in real-time robotic systems. Unlike traditional methods needing detailed hardware and software knowledge, this research uses a black-box approach, making it adaptable across …
-
Toward Automatically Composed FPGA-Optimized Robotic Systems Using High-Level Synthesis
Robotic systems are known to be computationally intensive. To improve performance, developers tend to implement custom robotic algorithms in hardware. However, a full robotic system typically consists of many interconnected algorithmic components that can easily max-out FPGA resources, thus …
-
ROS-X-Habitat : bridging the ROS ecosystem with embodied AI
… reinforcement learning agents with other robotics resources via ROS. This interface not only offers standardized communication protocols between embodied agents and simulators, but also enables physics-based simulation. With this interface, roboticists are able to train their own Habitat …
-
A framework for the development of virtual robotic games
Multiple robotic experiments are inherently high in operating costs. As the number of agents increase, resources in time, cost, and physical space becomes a limiting factor in experimentation. This thesis presents a framework that addresses these problems by virtual reality. The computer gaming …
-
Decentralized Planning Algorithms and Hybrid Learning for Scalable and Explainable Swarm Robotic Systems
Swarm robotic system is a large number of autonomous systems working together to accomplish collective goals. Swarm systems offer remarkable operational flexibility, efficiency, and fault-tolerance, compared to sophisticated standalone systems. These characteristics make the swarm systems central …
-
Learning representations from motion trajectories
… motion is a crucial aspect of articulated robotics. Many robot manipulation tasks can be defined and solved as a motion trajectory generation problem where the robot needs to calculate and execute a task-appropriate movement. Multiple efficient methods have been developed for this problem …
-
Approaches to online reinforcement learning for miniature airships
… frontier of research in the field of mobile robotics. Based on the advancing miniaturization of electronic devices and sensors, state-of-the-art robotic systems are permanently downsized and, in this way, become useful in decreasingly constrained environments and applicable in new scenarios …
-
An Efficient Multiple-Place Foraging Algorithm for Scalable Robot Swarms
… in the least amount of time. In the foraging algorithms we study, robots act independently with little or no central control. As the swarm size and arena size increase (e.g., thousands of robots searching over the surface of Mars or ocean), the foraging performance per robot decreases. …
-
Αλγόριθμοι βελτιστοποίησης για ρομποτικές εφαρμογές
… and deep-sea exploration. Although the usage of robotics provides a solution to several problems, new problems that need to be solved are coming to the surface. One of the most important problems is the problem of finding a path that covers the entire area of interest in a predefined environment …