Sökning: "robot skill"
Visar resultat 1 - 5 av 9 uppsatser innehållade orden robot skill.
1. Furhat på museet : Hur påverkar felhantering och användarinitativ upplevd intelligens och människolikhet?
Kandidat-uppsats, Linköpings universitet/Institutionen för datavetenskapSammanfattning : I detta arbete genomfördes en enkätundersökning för att se hur upplevelsen av en furhatrobot ändrades efter att ha implementerat felhantering och mer användarinitiativ. Genom enkätformatet Godspeed undersöktes kategorierna människolikhet och upplevd intelligens. LÄS MER
2. Heuristic control of a small line-following robot : A comparison of different methods
Magister-uppsats, KTH/Skolan för industriell teknik och management (ITM)Sammanfattning : A line-follower is a robot that follows a line. Line-followers can be used in industry, mostly for material transportation, but are also raced against each other in competitions. While line-followers used in industry prioritize smooth motion and accuracy, competition-style line-followers prioritize speed around the track. LÄS MER
3. Faster Environment Modelling and Integration into Virtual Reality Simulations
Magister-uppsats, Högskolan i Skövde/Institutionen för ingenjörsvetenskapSammanfattning : The use of virtual reality in engineering tasks, such as in virtual commissioning, has increased steadily in recent years, where a robot, machine or object of interest can be simulated and visualized. Yet, for a more immerse experience, an environment for the object in question needs to be constructed. LÄS MER
4. Skill Imitation Learning on Dual-arm Robotic Systems
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : A control system used to control two Panda Franka Emika robots online and simultaneously with two HTC Vive controllers is presented, with the primary purpose of demonstrating tasks for robots. The system is validated by learning from demonstration/imitation learning task via Principle Component Analysis (PCA). LÄS MER
5. Transfer of reinforcement learning for a robotic skill
Master-uppsats, Luleå tekniska universitet/Institutionen för system- och rymdteknikSammanfattning : In this work, we develop the transfer learning (TL) of reinforcement learning (RL) for the robotic skill of throwing a ball into a basket, from a computer simulated environment to a real-world implementation. Whereas learning of the same skill has been previously explored by using a Programming by Demonstration approach directly on the real-world robot, for our work, the model-based RL algorithm PILCO was employed as an alternative as it provides the robot with no previous knowledge or hints, i. LÄS MER
