Kim, Dong Hwan Hwang, Soonwook Lim, Myotaeg Oh, Yong hwan Lee, Yisoo 2024-01-12T06:32:17Z 2024-01-12T06:32:17Z 2023-11-27 2023-11 2169-3536 https://pubs.kist.re.kr/handle/201004/79741 Joint velocity estimation is one of the essential properties that implement for accurate robot motion control. Although conventional approaches such as numerical differentiation of position measurements and model-based observers exhibit feasible performance for velocity estimation, instability can be occurred because of phase lag or model inaccuracy. This study proposes a model-free approach that can estimate the velocity with less phase lag by batch training of a neural network with pre-collected encoder measurements. By learning a weighted moving average, the proposed method successfully estimates the velocity with less latency imposed by the noise attenuation compared to the conventional methods. Practical experiments with two robot platforms with high degrees of freedom are conducted to validate the effectiveness of the proposed method. English Institute of Electrical and Electronics Engineers Inc. Neural Network-Based Joint Velocity Estimation Method for Improving Robot Control Performance Article 10.1109/ACCESS.2023.3333388 1 IEEE Access, v.11, pp.130517 - 130526 IEEE Access 11 130517 130526 Y scie scopus 001120897000001 Computer Science, Information Systems Engineering, Electrical & Electronic Telecommunications Computer Science Engineering Telecommunications Article TRACKING CONTROL FORCE CONTROL MANIPULATORS POSITION OBSERVER TORQUE IDENTIFICATION BANDWIDTH Robots Actuators Observers Computational modeling Mathematical models Low-pass filters Robot control Neural networks Machine learning State estimation Velocity control Robotics robot control neural network machine learning state estimation