DRL: Deep Reinforcement Learning for Intelligent Robot Control -- Concept, Literature, and Future

Abstract

Combination of machine learning (for generating machine intelligence), computer vision (for better environment perception), and robotic systems (for controlled environment interaction) motivates this work toward proposing a vision-based learning framework for intelligent robot control as the ultimate goal (vision-based learning robot). This work specifically introduces deep reinforcement learning as the the learning framework, a General-purpose framework for AI (AGI) meaning application-independent and platform-independent. In terms of robot control, this framework is proposing specifically a high-level control architecture independent of the low-level control, meaning these two required level of control can be developed separately from each other. In this aspect, the high-level control creates the required intelligence for the control of the platform using the recorded low-level controlling data from that same platform generated by a trainer. The recorded low-level controlling data is simply indicating the successful and failed experiences or sequences of experiments conducted by a trainer using the same robotic platform. The sequences of the recorded data are composed of observation data (input sensor), generated reward (feedback value) and action data (output controller). For experimental platform and experiments, vision sensors are used for perception of the environment, different kinematic controllers create the required motion commands based on the platform application, deep learning approaches generate the required intelligence, and finally reinforcement learning techniques incrementally improve the generated intelligence until the mission is accomplished by the robot. For deep reinforcement learning, deep Q networks (DQN) 1 using Convolutional Neural Network (CNN) 2 will be used for learning the Q network. Deep Q Network approach is applied to the images acquired from our vision devices as input sensors to select the maximum rewarded action (best possible move based on our experiences) for our output controller to generate the required kinematics motion.