首页|New Robotics Study Results from Federal University of Goias (UFG) Described (Dee p-q-network Hybridization With Extended Kalman Filter for Accelerate Learning In Autonomous Navigation With Auxiliary Security Module)
New Robotics Study Results from Federal University of Goias (UFG) Described (Dee p-q-network Hybridization With Extended Kalman Filter for Accelerate Learning In Autonomous Navigation With Auxiliary Security Module)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Current study results on Robotics have been publi shed. According to news originating from Goiania, Brazil, by NewsRx corresponden ts, research stated, "This article proposes an algorithm for autonomous navigati on of mobile robots that mixes reinforcement learning with extended Kalman filte r (EKF) as a localization technique, namely EKF-DQN, aiming to accelerate the ma ximization of the learning curve and improve the reward values obtained in the l earning process. More specifically, Deep-Q-Networks (DQN) are used to control th e trajectory of an autonomous robot in an environment with many obstacles." Our news journalists obtained a quote from the research from the Federal Univers ity of Goias (UFG), "To improve navigation capability in this environment, we al so propose a fusion of visual and nonvisual sensors. Due to the ability of EKF t o predict states, this algorithm is used as a learning accelerator for the DQN n etwork, predicting future states and inserting this information into the memory replay. Aiming to increase the safety of the navigation process, a visual safety system is also proposed to avoid collisions between the mobile robot and people circulating in the environment. The efficiency of the proposed control system i s verified through computational simulations using the CoppeliaSIM simulator wit h code insertion in Python. The simulation results show that the EKF-DQN algorit hm accelerates the maximization of rewards obtained and provides a higher succes s rate in fulfilling the mission assigned to the robot when compared to other va lue-based and policy-based algorithms. A demo video of the navigation system can be seen at:. This article proposes an algorithm for autonomous navigation of mo bile robots that merges reinforcement learning with extended Kalman filter (EKF) as a localization technique, namely, EKF-DQN, aiming to accelerate learning and improve the reward values obtained in the process of apprenticeship. More speci fically, deep neural networks (DQN-Deep-Q-Networks) are used to control the traj ectory of an autonomous vehicle in an indoor environment. Due to the ability of EKF to predict states, this algorithm is proposed to be used as a learning accel erator of the DQN network, predicting states ahead and inserting this informatio n in the memory replay."
GoianiaBrazilSouth AmericaAlgorith msCybersecurityEmerging TechnologiesMachine LearningNano-robotReinforc ement LearningRobotRoboticsFederal University of Goias (UFG)
NETL
NSTL
