Accurate Ball Tracking with Extended Kalman Filters as a Prerequisite for a High-level Behavior with Reinforcement Learning
نویسندگان
چکیده
Controlling autonomous, humanoid robots in a dynamic, continuous, and real-time environment is a complex task. We have used an Extended Kalman Filter to track the position and velocity of the soccer ball in the RoboCup 3D soccer simulation scenario. The influence of reducing the error in the ball estimate on a high-level behavior is then demonstrated using the keep-away behavior. We have applied Sarsa(λ) with tile-coding as a linear function approximator. The keep-away task has been successfully learned in the 2D Soccer Simulation League a few years ago; in this paper, we apply similar ideas on a humanoid robot and describe new problems that arise with both the different robot model and the environment. The learned behavior depends highly on the underlying skills, which is shown using different ball localizations. The results are promising, yet reveal a new level of complexity. Keywords-Extended Kalman Filter, Reinforcement Learning, Sarsa(λ)
منابع مشابه
Estimation of LOS Rates for Target Tracking Problems using EKF and UKF Algorithms- a Comparative Study
One of the most important problem in target tracking is Line Of Sight (LOS) rate estimation for using from PN (proportional navigation) guidance law. This paper deals on estimation of position and LOS rates of target with respect to the pursuer from available noisy RF seeker and tracker measurements. Due to many important for exact estimation on tracking problems must target position and Line O...
متن کاملFixed-point FPGA Implementation of a Kalman Filter for Range and Velocity Estimation of Moving Targets
Tracking filters are extensively used within object tracking systems in order to provide consecutive smooth estimations of position and velocity of the object with minimum error. Namely, Kalman filter and its numerous variants are widely known as simple yet effective linear tracking filters in many diverse applications. In this paper, an effective method is proposed for designing and implementa...
متن کاملPractical Evaluation of EKF1 and UKF2 Filters for Terrain Aided Navigation
This article would study batch and recursive methods that used in terrain navigation systems. Terrain navigation has a lot ofdisadvantages and so researchers have been studied on different method of aided navigation for many years. Therefore, more types of aided navigation systems were introduced with advantages and disadvantages in terms of practical and theoretical. One of the main ideas for ...
متن کاملIMPLEMENTATION OF EXTENDED KALMAN FILTER TO REDUCE NON CYCLO-STATIONARY NOISE IN AERIAL GAMMA RAY SURVEY
Gamma-ray detection has an important role in the enhancement the nuclear safety and provides a proper environment for applications of nuclear radiation. To reduce the risk of exposure, aerial gamma survey is commonly used as an advantage of the distance between the detection system and the radiation sources. One of the most important issues in aerial gamma survey is the detection noise. Various...
متن کاملDoppler and bearing tracking using fuzzy adaptive unscented Kalman filter
The topic of Doppler and Bearing Tracking (DBT) problem is to achieve a target trajectory using the Doppler and Bearing measurements. The difficulty of DBT problem comes from the nonlinearity terms exposed in the measurement equations. Several techniques were studied to deal with this topic, such as the unscented Kalman filter. Nevertheless, the performance of the filter depends directly on the...
متن کامل