Accurately assessing uncertainty and prediction of a regression model is essential for making informed decisions, especially in high-risk tasks. Conformal Prediction (CP) is a powerful distribution-free uncertainty quantification framework for building such models as it is capable to transform a single-point prediction of any machine learning model into a Prediction Interval (PI) with a guarantee of encompassing the true value for specified levels of confidence. On the other hand, to generate high-quality PIs, the PIs should be as narrow as possible while enveloping a certain amount of uncertainty (i.e. confidence level). The generated width of the PIs mainly depends on the nonconformity measure used within the CP. In this study, we propose two novel Fuzzy c-Means Clustering (FCM) based nonconformity measures for CP with nearest neighbors to learn distribution-free and high-quality PIs for regression. The proposed approach generates tight PIs by evaluating the degree of nonconformity of a new data point compared to the so-called calibration points via Fuzzy Sets (FSs). From the calibration dataset, we extract representative FSs via FCM and assign every test point alongside the nearest neighbors within the calibration dataset with membership grades to adapt the nonconformity measure. To evaluate the performance, we present statistical comparisons and demonstrate that the proposed FCM-based nonconformity measures result in high-quality PIs.

In micromobility applications, maintaining satisfactory motor drive performance in the full torque-speed envelope of an outer rotor non-salient permanent magnet synchronous machine is a challenge due to the drastic performance degradation with the increasing non-linearity above the nominal ratings of the motor. In this article, we tackle this challenge via fuzzy gain scheduling proportional–integral speed controllers that have been designed by taking into account practical considerations. On the basis of experimental voltage ripple analyses conducted on the speed control loop with different system characteristics, we develop a single-input fuzzy gain scheduling proportional–integral speed controller and a double-input fuzzy gain scheduling proportional–integral speed controller to reduce the voltage ripples while providing satisfactory dynamical performance. The proposed structures continuously adjust the characteristics of the speed control loop within a specified region to exhibit different dynamical system characteristics against varying conditions. It is verified by the experimental test results that the proposed structures successfully reduced the increasing voltage ripples as the disturbances increase while providing satisfactory dynamical performance. Finally, we provided a discussion on the trade-off between the proposed structures and suggested deploying single-input fuzzy gain scheduling proportional–integral controller for micromobility speed control applications as it is agnostic to noise to a certain degree hence offering better reliability.

This article presents a novel autonomous navigation approach that is capable of increasing map exploration and accuracy while minimizing the distance traveled for autonomous drone landings. For terrain mapping, a probabilistic sparse elevation map is proposed to represent measurement accuracy and enable the increasing of map quality by continuously applying new measurements with Bayes inference. For exploration, the Quality-Aware Best View (QABV) planner is proposed for autonomous navigation with a dual focus: map exploration and quality. Generated paths allow for visiting viewpoints that provide new measurements for exploring the proposed map and increasing its quality. To reduce the distance traveled, we handle the path-cost information in the framework of control theory to dynamically adjust the path cost of visiting a viewpoint. The proposed methods handle the QABV planner as a system to be controlled and regulate the information contribution of the generated paths. As a result, the path cost is increased to reduce the distance traveled or decreased to escape from a low-information area and avoid getting stuck. The usefulness of the proposed mapping and exploration approach is evaluated in detailed simulation studies including a real-world scenario for a packet delivery drone.

In the last two decades, the use of quadrotors has become widespread among the aerospace, control, and robotics community. Although many researchers have mentioned the problem of achieving high accuracy in trajectory-tracking while obtaining low oscillations for quadrotors, it is still an area open to research and development. In this paper, we introduce a differential flatness-based sliding mode controller designed specifically for moment and force controllers to enhance trajectory and rotation tracking performances. The primary novelty is the combination of a sliding mode controller with an adjustable sliding surface which allows the designer to tune the controllers' aggressiveness and differential flatness property of the quadrotor which provides ease in controller design, as well as trajectory generation by compactly expressing control inputs and the trajectory of the system as a function of the system's differentially flat outputs. The proposed controller is tested with various tightly constrained trajectories. The resulting performance analyses and compared with the differential flatness-based Mellinger controller. The presented results attest to the superiority of the proposed controller.