Studies from California Institute of Technology (Caltech) Add New Findings in th e Area of Robotics and Automation (Learning-based Minimally-sensed Fault-toleran t Adaptive Flight Control)
Studies from California Institute of Technology (Caltech) Add New Findings in th e Area of Robotics and Automation (Learning-based Minimally-sensed Fault-toleran t Adaptive Flight Control)
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on Robotics - Ro botics and Automation have been published. According to news originating from Pa sadena, California, by NewsRx correspondents, research stated, “Many multirotor aircraft use redundant configurations to maintain control in the event of an act uator failure. Due to the redundancy of the system, fault isolation is inherentl y difficult and further compounded by complex interacting aerodynamics of the pr opellers, wings, and body.” Financial support for this research came from Supernal, LLC. Our news journalists obtained a quote from the research from the California Inst itute of Technology (Caltech), “This letter presents a novel sparse failure iden tification and control correction method that does not require direct fault sens ing, and instead utilizes only the vehicle’s dynamic response. The method couple s an l(1)-regularized representation of the failure with a deep neural network t o effectively isolate faults and improve tracking control in highly dynamic envi ronments with unmodeled aerodynamic effects and unknown actuator failures. The m ethod also includes a control re-allocation scheme which corrects for the identi fied faults while maximizing control authority and maintaining nominal performan ce characteristics. Experimental results demonstrate the method’s ability to mai ntain control of a multirotor aircraft by isolating motor failures and reallocat ing control, improving position tracking by 48 % over the baseline .”
Key words
Pasadena/California/United States/Nor th and Central America/Robotics and Automation/Robotics/California Institute of Technology (Caltech)
NETL
NSTL