Real-World Reinforcement Learning for Autonomous Humanoid Robot Charging in a Home Environment
نویسندگان
چکیده
In this paper we investigate and develop a real-world reinforcement learning approach to autonomously recharge a humanoid Nao robot [1]. Using a supervised reinforcement learning approach, combined with a Gaussian distributed states activation, we are able to teach the robot to navigate towards a docking station, and thus extend the duration of autonomy of the Nao by recharging. The control concept is based on visual information provided by naomarks and six basic actions. It was developed and tested using a real Nao robot within a home environment scenario. No simulation was involved. This approach promises to be a robust way of implementing real-world reinforcement learning, has only few model assumptions and offers faster learning than conventional Q-learning or SARSA.
منابع مشابه
Real-world reinforcement learning for autonomous humanoid robot docking
Reinforcement learning (RL) is a biologically supported learning paradigm, which allows an agent to learn through experience acquired by interaction with its environment. Its potential to learn complex action sequences has been proven for a variety of problems, such as navigation tasks. However, the interactive randomized exploration of the state space, common in reinforcement learning, makes i...
متن کاملAccurate Ball Tracking with Extended Kalman Filters as a Prerequisite for a High-level Behavior with Reinforcement Learning
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 applie...
متن کاملA dialogue approach to learning object descriptions and semantic categories
Acquiring new knowledge through interactive learning mechanisms is a key ability for humanoid robots in a natural environment. Such learning mechanisms need to be performed autonomously, and through interaction with the environment or with other agents/humans. In this paper, we describe a dialogue approach and a dynamic object model for learning semantic categories, object descriptions, and new...
متن کاملReal World Reinforcement Learning
Self-sustenance in an unknown environment for an autonomous mobile robot with restricted sensory faculties is a challenging problem, primarily due to lack of effectiveness of existing techniques (deterministic or learning-based) in real world. Through this thesis, we try to investigate the utility of some of the existing reinforcement learning based techniques in achieving energy self-sufficien...
متن کاملAn Unsupervised Learning Method for an Attacker Agent in Robot Soccer Competitions Based on the Kohonen Neural Network
RoboCup competition as a great test-bed, has turned to a worldwide popular domains in recent years. The main object of such competitions is to deal with complex behavior of systems whichconsist of multiple autonomous agents. The rich experience of human soccer player can be used as a valuable reference for a robot soccer player. However, because of the differences between real and simulated soc...
متن کامل