Pre-programming a robot may be efficient to some extent, but since a human has code the robot it will only be as efficient as the programming. The problem can solved by using machine learning, which lets the robot learn the most efficient way by itself. This thesis is continuation of a previous work that covered the development of the framework Safe-To-Explore-State-Spaces (STESS) for safe robot manipulation. This thesis evaluates the efficiency of the Q-Learning with normalized advantage function (NAF), a deep reinforcement learning algorithm, when integrated with the safety framework STESS. It does this by performing a 2D task where the robot moves the tooltip on a plane from point A to point B in a set workspace. To test the viabili...
I denne avhandlingen ble det utviklet et sim-til-real rammeverk for å løse visjonsbasert robot plukk...
Sammen med dyp læring har Reinforcement Learning (forsterkningslæring) hatt flere gjennombrudd de si...
This thesis presents a safety-aware learning framework that employs an adaptivemodel learning method...
Pre-programming a robot may be efficient to some extent, but since a human has code the robot it wil...
Deep reinforcement learning algorithms typically require large amounts of data to solve a specific p...
Det å forbedre roboters autonomi har lenge vært et mål for forskere. Ulike verktøy har blitt brukt f...
Autonom navigering i stadig mer komplekse domener byr på nye utfordringer og stiller spørsmål ved ef...
Reinforcement learning was recently successfully used for real-world robotic manipulation tasks, wit...
Robot programming can be an expensive and tedious task and companies may have to employ dedicated st...
In this paper a real-time collision avoidance approach using machine learning is presented for safe ...
Reinforcement Learning (RL) is popular to solve complex tasks in robotics, but using it in scenarios...
Deep reinforcement learning has been shown to be a potential alternative to a traditional controller...
Innen klinisk medisin ansees det som utfordrende å benytte autonome robotsystemer. Håndtering av bev...
Traditionally robots have been preprogrammed to execute specific tasks. Thisapproach works well in i...
I denne avhandlingen ble det utviklet et sim-til-real rammeverk for å løse visjonsbasert robot plukk...
Sammen med dyp læring har Reinforcement Learning (forsterkningslæring) hatt flere gjennombrudd de si...
This thesis presents a safety-aware learning framework that employs an adaptivemodel learning method...
Pre-programming a robot may be efficient to some extent, but since a human has code the robot it wil...
Deep reinforcement learning algorithms typically require large amounts of data to solve a specific p...
Det å forbedre roboters autonomi har lenge vært et mål for forskere. Ulike verktøy har blitt brukt f...
Autonom navigering i stadig mer komplekse domener byr på nye utfordringer og stiller spørsmål ved ef...
Reinforcement learning was recently successfully used for real-world robotic manipulation tasks, wit...
Robot programming can be an expensive and tedious task and companies may have to employ dedicated st...
In this paper a real-time collision avoidance approach using machine learning is presented for safe ...
Reinforcement Learning (RL) is popular to solve complex tasks in robotics, but using it in scenarios...
Deep reinforcement learning has been shown to be a potential alternative to a traditional controller...
Innen klinisk medisin ansees det som utfordrende å benytte autonome robotsystemer. Håndtering av bev...
Traditionally robots have been preprogrammed to execute specific tasks. Thisapproach works well in i...
I denne avhandlingen ble det utviklet et sim-til-real rammeverk for å løse visjonsbasert robot plukk...
Sammen med dyp læring har Reinforcement Learning (forsterkningslæring) hatt flere gjennombrudd de si...
This thesis presents a safety-aware learning framework that employs an adaptivemodel learning method...