ML p(r)ior | Combining Vision, Machine Learning and Automatic Control to Play the Labyrinth Game

Combining Vision, Machine Learning and Automatic Control to Play the Labyrinth Game

2016-02-01
The labyrinth game is a simple yet challenging platform, not only for humans but also for control algorithms and systems. The game is easy to understand but still very hard to master. From a system point of view, the ball behaviour is in general easy to model but close to the obstacles there are severe non-linearities. Additionally, the far from flat surface on which the ball rolls provides for changing dynamics depending on the ball position. The general dynamics of the system can easliy be handled by traditional automatic control methods. Taking the obstacles and uneaven surface into accout would require very detailed models of the system. A simple deterministic control algorithm is combined with a learning control method. The simple control method provides initial training data. As the learning method is trained, the system can learn from the results of its own actions and the performance improves well beyond the performance of the initial controller. A vision system and image analysis is used to estimate the ball position while a combination of a PID controller and a learning controller based on LWPR is used to learn to navigate the ball through the maze.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2018-09-24

We consider the task of controlling a quadrotor to hover in front of a freely moving user, using inp… show more
PDF

Highlights - Most important sentences from the article

2018-10-03

Designing optimal controllers continues to be challenging as systems are becoming complex and are in… show more
PDF

Highlights - Most important sentences from the article

2018-09-13

Event-triggered control (ETC) methods can achieve high-performance control with a significantly lowe… show more
PDF

Highlights - Most important sentences from the article

2019-01-24

Legged robots pose one of the greatest challenges in robotics. Dynamic and agile maneuvers of animal… show more
PDF

Highlights - Most important sentences from the article

2019-04-17
1904.08353 | stat.ML

Reinforcement learning (RL) constitutes a promising solution for alleviating the problem of traffic … show more
PDF

Highlights - Most important sentences from the article

2019-05-15

In this paper we develop a computational offloading strategy with graceful degradation for executing… show more
PDF

Highlights - Most important sentences from the article

2019-03-31
1904.00378 | cs.RO

The main motivation of this work is to propose a simulation approach for a specific task within the … show more
PDF

Highlights - Most important sentences from the article

2019-05-24

The control of complex systems is of critical importance in many branches of science, engineering, a… show more
PDF

Highlights - Most important sentences from the article

2019-03-09

Modelling of contact-rich tasks is challenging and cannot be entirely solved using classical control… show more
PDF

Highlights - Most important sentences from the article

2019-02-19

For complex real-world systems, designing controllers are a difficult task. With the advent of neura… show more
PDF

Highlights - Most important sentences from the article

2019-03-09

Power system emergency control is generally regarded as the last safety net for grid security and re… show more
PDF

Highlights - Most important sentences from the article

2018-12-15

Bayesian optimization is proposed for automatic learning of optimal controller parameters from exper… show more
PDF

Highlights - Most important sentences from the article

2018-12-24

Delayed feedback control is an easy realizable control method which generates control force by compa… show more
PDF

Highlights - Most important sentences from the article

2019-03-15
1903.06842 | cs.SY

In a paper by Willems and coworkers it was shown that sufficiently excited data could be used to rep… show more
PDF

Highlights - Most important sentences from the article

2019-01-10

We present a new method for the automated synthesis of digital controllers with formal safety guaran… show more
PDF

Highlights - Most important sentences from the article

2019-03-07

Nonlinear optimal control problems are often solved with numerical methods that require knowledge of… show more
PDF