|
|
Reinforcement Learning for RoboCup
Bočán, Hynek ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
Goal of this thesis is creation of artificial intelligence capable of controlling robotic soccer player simulated in SimSpark environment. Agent created is expanding capabilities of existing third party agent which provides set of basic skills such as localization on the field, dribbling with the ball and omnidirectional walk. Responsibility of the created agent is to pick the best action based current state of the game. This decision making was implemented using reinforcement learning and its method Q-learning. State of the game is transformed into 2D picture with several planes. This picture is then analyzed using deep convolution neural network implemented using C++ and DeepCL library.
|
|
|
Planning expert system for mobile robot
Dvořáková, Ivona ; Sáblík, Václav (referee) ; Valenta, Jan (advisor)
The thesis connects on knowledge from semestral project. The first part of thesis represents primary parts, sorts, problems and principles for planning expert systems. The second part of thesis interprets possibilities and principles usage planning expert systems in mobile robotic. The thesis includes an example of mobile robotic, too. Characterization of robotic football is presented in the third part. The part of thesis interprets system´s scales and their specifications. In the last part detailed conception for robotic football is designed(group of MIROSOT).
|
|
|
Robotic Soccer in RDS
Kuparowitz, Tomáš ; Florián, Tomáš (referee) ; Honzík, Petr (advisor)
The aim of this thesis is to create a list of robotic simulators suitable for simulating robotic soccer. Simulation environment included in Microsoft Robotic Developer Studio is also used to implement the vector field path planning algorithm for robotic soccer.
|
|
|
PDA software for robot soccer
Uhlíř, Luděk ; Honzík, Petr (referee) ; Hrabec, Jakub (advisor)
Robotic soccer is a game like a real soccer but here the game is played by robots. The rules are the same, only there are few exceptions (foul, penalty kick, stalemate situation). Game is running without the human intervention. Just a human referee is supervising the game. Two teams are attending the game. Each of them has a control computer. The control computer is the brain of the game. It has a camera, it is making decisions for the next step of robots and sending them configuration data. The thesis deals with testing of communication interface and designs the new communication protocol for the next generation of the robots. The testing is provided by pocket pc Palm TX. It will send data over the Bluetooth interface to the control pc and will configure particular constants, like constants of PID regulator and an address of a robot. This will be provided by the IrDA interface.
|
|
|
Robotic Soccer
Suchý, Václav ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
This work describes a design of an agent model for robotic soccer based on the DEVS formalism. There is also presented a design of own DEVS simulator (based on classic DEVS simulator) for parallel realtime simulations. Functionality of the simulator and the model is shown on an example of a soccer client for RoboCup Soccer Server. Based on this client, there is also presented a design of a library for easier creation of soccer clients for RoboCup.
|
|
|
Reinforcement Learning for RoboCup
Bočán, Hynek ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
Goal of this thesis is creation of artificial intelligence capable of controlling robotic soccer player simulated in SimSpark environment. Agent created is expanding capabilities of existing third party agent which provides set of basic skills such as localization on the field, dribbling with the ball and omnidirectional walk. Responsibility of the created agent is to pick the best action based current state of the game. This decision making was implemented using reinforcement learning and its method Q-learning. State of the game is transformed into 2D picture with several planes. This picture is then analyzed using deep convolution neural network implemented using C++ and DeepCL library.
|
|
|
Robotic Soccer in RDS
Kuparowitz, Tomáš ; Florián, Tomáš (referee) ; Honzík, Petr (advisor)
The aim of this thesis is to create a list of robotic simulators suitable for simulating robotic soccer. Simulation environment included in Microsoft Robotic Developer Studio is also used to implement the vector field path planning algorithm for robotic soccer.
|
|
|
Robotic Soccer
Suchý, Václav ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
This work describes a design of an agent model for robotic soccer based on the DEVS formalism. There is also presented a design of own DEVS simulator (based on classic DEVS simulator) for parallel realtime simulations. Functionality of the simulator and the model is shown on an example of a soccer client for RoboCup Soccer Server. Based on this client, there is also presented a design of a library for easier creation of soccer clients for RoboCup.
|
|
|
Planning expert system for mobile robot
Dvořáková, Ivona ; Sáblík, Václav (referee) ; Valenta, Jan (advisor)
The thesis connects on knowledge from semestral project. The first part of thesis represents primary parts, sorts, problems and principles for planning expert systems. The second part of thesis interprets possibilities and principles usage planning expert systems in mobile robotic. The thesis includes an example of mobile robotic, too. Characterization of robotic football is presented in the third part. The part of thesis interprets system´s scales and their specifications. In the last part detailed conception for robotic football is designed(group of MIROSOT).
|
|
|
PDA software for robot soccer
Uhlíř, Luděk ; Honzík, Petr (referee) ; Hrabec, Jakub (advisor)
Robotic soccer is a game like a real soccer but here the game is played by robots. The rules are the same, only there are few exceptions (foul, penalty kick, stalemate situation). Game is running without the human intervention. Just a human referee is supervising the game. Two teams are attending the game. Each of them has a control computer. The control computer is the brain of the game. It has a camera, it is making decisions for the next step of robots and sending them configuration data. The thesis deals with testing of communication interface and designs the new communication protocol for the next generation of the robots. The testing is provided by pocket pc Palm TX. It will send data over the Bluetooth interface to the control pc and will configure particular constants, like constants of PID regulator and an address of a robot. This will be provided by the IrDA interface.
|
guest ::
