Browsing by Author "Dias , Pedro Afonso da Silva Cardoso"
Now showing 1 - 1 of 1
Results Per Page
Sort Options
- Planeamento de caminhos para um manipulador robótico com volumes de trabalho confinadosPublication . Dias , Pedro Afonso da Silva Cardoso; Silva, Manuel Fernando dos SantosIn an era where robots are becoming an integral part of human quotidian activities, understanding their inner workings is crucial. Path planning emerges as an universal aspect of robotics among the inherent building complexities, from electronics to mechanics. The first contribution of this dissertation is to provide an overview of the current discourse on robot path planning topics, serving as a valuable resource for scientists and researchers in the near future. This review aims to consolidate and elucidate the various categories of path planning methods, specifically classical or analytical methods, and computer intelligence methods. Additionally, the operational principles of these categories were explored, discussing their respective advantages and disadvantages, and reinforcing these discussions with relevant studies in the field. This work is focused on the most prevalent and recognized methods within the robotics path planning problem, either for mobile robotics or manipulator arms. The second key contribution of this work is the development of an efficient and user-friendly method for executing path planning for a robotic manipulator using a ROSAction Server. This Action Server is designed in a unique format that enhances modularity among the various metrics/heuristics employed. It provides the option to plan paths with or without perception of the surrounding environment. In the absence of environmental perception, the developed tool, also referred to as skill, generates a feasible, non-self-colliding trajectory for the manipulator. If environmental perception is required, a pipeline is initiated to process the received point cloud, which includes outlier removal and downsampling. The resultant path is then sent to the robot and executed. This skill was tested with a UR10 manipulator in various scenarios. One scenario did not involve environmental perception, while the other two did and included obstacles that made path planning to the target point challenging. The skill demonstrated its effectiveness in all tested scenarios.