Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Robotics have been published. According to news reporting originating from Beijing, People's Republic of China, by NewsRx correspondents, research stated, "In nature, when e ncountering unexpected uncertainty, animals tend to react quickly to ensure safe ty as the top priority, and gradually adapt to it based on recent valuable exper ience. We present a framework, namely EVOLutionary model-based uncertainty obser VER (EVOLVER), to mimic the bio-behavior for robotics to achieve rapid transient reaction ability and high-precision steady-state performance simultaneously." Financial support for this research came from Defense Industrial Technology Deve lopment. Our news editors obtained a quote from the research from Beihang University, "In particular, the Koopman operator is leveraged to explore the latent structure o f internal and external disturbances, which is subsequently utilized in an evolu tionary model-based disturbance observer to estimate the eventual disturbance. T he resulting observer can guarantee a provable convergence in optimal conditions . Several practical considerations, including construction of a training dataset , data noise handling, and lifting functions selection, are elaborated in pursui t of the theoretical optimality in real applications. The lightweight feature of our framework enables online computation, even on a microprocessor (STM32F7 wit h 100 Hz control frequency). The framework is thoroughly evaluated by one simula tion and three experiments. The experimental scenarios include: 1) Trajectory pr ediction of an irregular free-flying object subject to aerodynamic drag, 2) indo or and outdoor agile flights of a quadrotor subject to wind gust, and 3) high-pr ecision end-effector control of a manipulator subject to base moving disturbance ."
NETL
NSTL