Self-Optimizing Path Tracking Controller for Intelligent Vehicles Based on Reinforcement Learning

The path tracking control system is a crucial component for autonomous vehicles; it is challenging to realize accurate tracking control when approaching a wide range of uncertain situations and dynamic environments, particularly when such control must perform as well as, or better than, human drivers. While many methods provide state-of-the-art tracking performance, they tend to emphasize constant PID control parameters, calibrated by human experience, to improve tracking accuracy. A detailed analysis shows that PID controllers inefficiently reduce the lateral error under various conditions, such as complex trajectories and variable speed. In addition, intelligent driving vehicles are highly non-linear objects, and high-fidelity models are unavailable in most autonomous systems. As for the model-based controller (MPC or LQR), the complex modeling process may increase the computational burden. With that in mind, a self-optimizing, path tracking controller structure, based on reinforcement learning, is proposed. For the lateral control of the vehicle, a steering method based on the fusion of the reinforcement learning and traditional PID controllers is designed to adapt to various tracking scenarios. According to the pre-defined path geometry and the real-time status of the vehicle, the interactive learning mechanism, based on an RL framework (actor–critic—a symmetric network structure), can realize the online optimization of PID control parameters in order to better deal with the tracking error under complex trajectories and dynamic changes of vehicle model parameters. The adaptive performance of velocity changes was also considered in the tracking process. The proposed controlling approach was tested in different path tracking scenarios, both the driving simulator platforms and on-site vehicle experiments have verified the effects of our proposed self-optimizing controller. The results show that the approach can adaptively change the weights of PID to maintain a tracking error (simulation: within ±0.071 m; realistic vehicle: within ±0.272 m) and steering wheel vibration standard deviations (simulation: within ±0.04°; realistic vehicle: within ±80.69°); additionally, it can adapt to high-speed simulation scenarios (the maximum speed is above 100 km/h and the average speed through curves is 63–76 km/h).

3D-Printed Miniature Robots with Piezoelectric Actuation for Locomotion and Steering Maneuverability Applications

The miniaturization of robots with locomotion abilities is a challenge of significant technological impact in many applications where large-scale robots have physical or cost restrictions. Access to hostile environments, improving microfabrication processes, or advanced instrumentation are examples of their potential use. Here, we propose a miniature 20 mm long sub-gram robot with piezoelectric actuation whose direction of motion can be controlled. A differential drive approach was implemented in an H-shaped 3D-printed motor platform featuring two plate resonators linked at their center, with built-in legs. The locomotion was driven by the generation of standing waves on each plate by means of piezoelectric patches excited with burst signals. The control of the motion trajectory of the robot, either translation or rotation, was attained by adjusting the parameters of the actuation signals such as the applied voltage, the number of applied cycles, or the driving frequency. The robot demonstrated locomotion in bidirectional straight paths as long as 65 mm at 2 mm/s speed with a voltage amplitude of only 10 V, and forward and backward precise steps as low as 1 µm. The spinning of the robot could be controlled with turns as low as 0.013 deg. and angular speeds as high as 3 deg./s under the same conditions. The proposed device was able to describe complex trajectories of more than 160 mm, while carrying 70 times its own weight.

Monitoring Weeder Robots and Anticipating Their Functioning by Using Advanced Topological Data Analysis

The present paper aims at analyzing the topological content of the complex trajectories that weeder-autonomous robots follow in operation. We will prove that the topological descriptors of these trajectories are affected by the robot environment as well as by the robot state, with respect to maintenance operations. Most of existing methodologies enabling efficient diagnosis are based on the data analysis, and in particular on some statistical quantities derived from the data. The present work explores the use of an original approach that instead of analyzing quantities derived from the data, analyzes the “shape” of the data, that is, the time series topology based on the homology persistence. We will prove that this procedure is able to extract valuable patterns able to discriminate the trajectories that the robot follows depending on the particular patch in which it operates, as well as to differentiate the robot behavior before and after undergoing a maintenance operation. Even if it is a preliminary work, and it does not pretend to compare its performances with respect to other existing technologies, this work opens new perspectives in considering quite natural and simple descriptors based on the intrinsic information that data contains, with the aim of performing efficient diagnosis and prognosis.

Late Holocene Hydro-Climate Variability in the Eastern Mediterranean: A Spatial Multi-Proxy Approach

A total of thirteen (13) paleoclimatic coastal and hinterland archives of the broader eastern Mediterranean region were collected and examined statistically in search of underlying trends for the period 2800 to 200 BP. For each archive, a proxy record representative of hydro-climatic changes was selected, normalized using z-factors to facilitate intercomparison, and analyzed statistically. Multivariate statistical analysis was performed using a clustering analysis (HCA) and dimension reduction (PCA), which led to groupings of similar records temporally, and allowed the identification of spatially underlying modes of variability. Two main modes of variability were identified, further supporting complex trajectories of paleoclimatic evolution in the region. The first mode was identified for sites presenting a trend from a wetter to an overall drier phase, with respective changes at major phase shifts at 1400 BP and 1100 BP. All sites were from the southern and northern Balkan region, as well as southwestern Turkey. A contrasting dry to wet trend was identified for a site in the Peloponnese (Greece) and the Levant, with a major phase shift at around 750 BP. The inclusion of different proxies from very different environmental settings and the 200-year window has complicated the connection of established short-term climatic events to the study’s findings.

“God’s Absence During Trauma Took Its Toll”: Dialogic Tracing of Literate Activity and Lifespan Trajectories of Semiotic (Un)becoming

Scholarship on trajectories of becoming with literate activities is of growing interest in Writing Studies, particularly in accounts of writing grounded in cultural-historical and dialogic approaches, and in lifespan accounts of writing. The research reported here contributes to those conversations by tracing trajectories of becoming that are dynamically nonlinear, necessarily messy, and predicated on exceptionally complex streams of times, places, life experiences, artifacts, and literate activities. I draw from one case study with Alex, once a deeply faithful Christian who, over complex trajectories of semiotic becoming, lost her faith and was left to make sense of drastic perspectival shifts, in large part, through literate activity. Weaving analyses of talk across 2 years, 15 interviews, and multiple texts and textual interactions, I trace a narrative of Alex’s trajectories of unbecoming/becoming. I argue that Writing Studies needs flexible, theoretically grounded methods to trace becoming across lifespan trajectories and I address this imperative by showcasing one approach— dialogic animation protocols coupled with dialogic analyses.

PT -symmetric classical mechanics

This paper reports the results of an ongoing in-depth analysis of the classical trajectories of the class of non-Hermitian PT -symmetric Hamiltonians H = p2 + x2 (ix) ε (ε ⩾ 0). A variety of phenomena, heretofore overlooked, have been discovered such as the existence of infinitely many separatrix trajectories, sequences of critical initial values associated with limiting classical orbits, regions of broken PT -symmetric classical trajectories, and a remarkable topological transition at ε = 2. This investigation is a work in progress and it is not complete; many features of complex trajectories are still under study.

CALCULATION OF FLOWS IN AN ACCELERATOR OF ELEMENTARY PARTICLES

The Schrödinger and Klein-Gordon equations have a finite velocity solution using the Navier-Stokes equation. But the Dirac equation did not lend itself to solving with the help of a finite formula for an arbitrary vector and scalar potential. Finally, the transition from the derivative of the function to the derivative of the logarithm of the function worked. Then we managed to solve a linear equation with respect to the derivative of the logarithm of the function, which can be integrated. Moreover, it turned out that it is possible to describe many particles. At accelerators, the trajectories of particles with an error are described, i.e. complex trajectories. In this article, the task is to calculate the accelerator in the complex plane, where the imaginary part is the error of the mean — the real part.

Experimental verification of the isotropy postulate at deformation of steel 45 along orthogonal curvilinear trajectories of constant curvature

Представлены результаты экспериментальных исследований по проверке достоверности одного из основных законов пластичности - постулата изотропии А.А. Ильюшина в условиях ортогональных сложных нагружений по криволинейным окружным траекториям постоянной кривизны. Экспериментальные исследования выполнены на тонкостенных трубчатых образцах из материала сталь 45 на автоматизированном расчетно-экспериментальном комплексе СН-ЭВМ. Программы нагружения трубчатых образцов задавались в девиаторном пространстве деформаций А.А. Ильюшина при одновременном комбинированном действии на образец растяжения-сжатия и кручения. В экспериментах реализовано четыре траектории деформирования, представляющие собой окружности, начинающиеся из начала координат. Установлено, что для реализованных сложных траекторий постоянной кривизны постулат изотропии выполняется как по скалярным, так и векторным свойствам. The results of experimental studies on validation Ilyushin’s isotropy postulate under the conditions of orthogonal complex loads along curvilinear trajectories of constant curvature. Experimental studies were carried out on thin-walled tubular specimens made of steel 45 on SN-EVM testing machine. Loading programs for tubular specimens were set in the deviatorial strain space of A.A. Ilyushin under the combined action of tension-compression and torsion on the specimens. Experimental data are obtained for four strain trajectories, which are circles starting from the origin. It is found that for the realized complex trajectories of constant curvature the isotropy postulate is fulfilled in terms of scalar and vector properties.

Tracking by Deblatting

Objects moving at high speed along complex trajectories often appear in videos, especially videos of sports. Such objects travel a considerable distance during exposure time of a single frame, and therefore, their position in the frame is not well defined. They appear as semi-transparent streaks due to the motion blur and cannot be reliably tracked by general trackers. We propose a novel approach called Tracking by Deblatting based on the observation that motion blur is directly related to the intra-frame trajectory of an object. Blur is estimated by solving two intertwined inverse problems, blind deblurring and image matting, which we call deblatting. By postprocessing, non-causal Tracking by Deblatting estimates continuous, complete, and accurate object trajectories for the whole sequence. Tracked objects are precisely localized with higher temporal resolution than by conventional trackers. Energy minimization by dynamic programming is used to detect abrupt changes of motion, called bounces. High-order polynomials are then fitted to smooth trajectory segments between bounces. The output is a continuous trajectory function that assigns location for every real-valued time stamp from zero to the number of frames. The proposed algorithm was evaluated on a newly created dataset of videos from a high-speed camera using a novel Trajectory-IoU metric that generalizes the traditional Intersection over Union and measures the accuracy of the intra-frame trajectory. The proposed method outperforms the baselines both in recall and trajectory accuracy. Additionally, we show that from the trajectory function precise physical calculations are possible, such as radius, gravity, and sub-frame object velocity. Velocity estimation is compared to the high-speed camera measurements and radars. Results show high performance of the proposed method in terms of Trajectory-IoU, recall, and velocity estimation.

Afterword: The value of children in the Global South: Current contributions and future directions

This Afterword to the Current Sociology Monograph on ‘The Value Turn in Childhood Sociology’ reflects on how this issue adds fundamental insights to our understanding not only of children’s social positions, the roles they play and their life experiences from the perspectives of various stakeholders in a variety of Southern societies, but also of the heterogeneous, hybrid and complex trajectories of modernization in these societies. The articles contribute to existing scholarship in at least three ways. First, they illustrate the productivity of the value turn in childhood sociology by linking children’s social roles, experiences and positions in society with multi-level social mechanisms (inclusive of family, educational institutions, social groups and organizations, and the state) in culturally and socially contextualized analyses. Second, the value turn proposed in this monograph attempts a critical intervention to de-center the previous Western-centric knowledge production in childhood sociology. The articles have contributed towards this objective by foregrounding Southern empirical realities and spearheading grounded theorization based on Southern experiences. Finally, the articles showcase a plethora of research methods and techniques in a variety of research paradigms, including critical discourse analysis, in-depth interviews, ethnographic research, historical analysis and mixed-methods research, which yield rich, profound and nuanced findings about the valuation of children in different contexts. I conclude this closing article by deliberating on future directions for the research agenda on the value of children in sociology.