Avancerad sökning

Hittade 4 uppsatser som matchar ovanstående sökkriterier.

1. 1. Comparing Four Modelling Methods for the Simulation of a Soft Quadruped Robot

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Karin Lagrelius; [2022]
   Nyckelord :Soft Robotics; Modelling; Simulation; Lumped-parameter-method; Quadruped; Soft Actuator; Matlab Simulink; Matlab Simscape Multibody; Mjuk robotik; Modellering; Simulering; Klumpparametermetoden; Fyrfota; Mjukt ställdon; Matlab Simulink; Matlab Simscape Multibody;

   Sammanfattning : A soft quadruped robot is being developed at the Department of Machine Design and Department of Production Engineering at KTH. The legs of the robot consist of four continuum actuators that can achieve complex movements. In order to efficiently develop gaits for the robot, reinforcement learning will be used. LÄS MER

3. 2. Domain Adaptation to Meet the Reality-Gap from Simulation to Reality

   Master-uppsats, Linköpings universitet/Datorseende

   Författare :Fanny Forsberg; [2022]
   Nyckelord :domain adaptation; reality gap; domain randomization; deep learning; autonomous robot;

   Sammanfattning : Being able to train machine learning models on simulated data can be of great interest in several applications, one of them being for autonomous driving of cars. The reason is that it is easier to collect large labeled datasets as well as performing reinforcement learning in simulations. LÄS MER

4. 3. Bridging Sim-to-Real Gap in Offline Reinforcement Learning for Antenna Tilt Control in Cellular Networks

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Mayank Gulati; [2021]
   Nyckelord :reinforcement learning; transfer learning; simulation-to-reality; simulator; realworld; real-world network data; remote electrical tilt optimization; cellular networks; antenna tilt; network optimization.;

   Sammanfattning : Antenna tilt is the angle subtended by the radiation beam and horizontal plane. This angle plays a vital role in determining the coverage and the interference of the network with neighbouring cells and adjacent base stations. LÄS MER

5. 4. Bayesian Off-policy Sim-to-Real Transfer for Antenna Tilt Optimization

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Albin Larsson Forsberg; [2021]
   Nyckelord :Simulation to Reality; Coverage and Capacity Optimization; Remote Electrical Tilt; Reinforcement Learning; Bayesian Optimization; Domain Randomization; Off- policy Estimation; Simulering till Verklighet; Täckning och Kapacitetsoptimering; Fjärrstyrning av Elektrisk Lutning; Förstärkningsinlärning; Bayesiansk Optimering; Domänrandomisering; Off- policyskattning;

   Sammanfattning : Choosing the correct angle of electrical tilt in a radio base station is essential when optimizing for coverage and capacity. A reinforcement learning agent can be trained to make this choice. If the training of the agent in the real world is restricted or even impossible, alternative methods can be used. LÄS MER