Deep Reinforcement Learning based pedestrian and independent vehicle safety fortification using intelligent perception

The Light Detection and Ranging (LiDAR) sensor is utilized to track each sensed obstructions at their respective locations with their relative distance, speed, and direction; such sensitive information forwards to the cloud server to predict the vehicle-hit, traffic congestion and road damages. Learn the behaviour of the state to produce an appropriate reward as the recommendation to avoid tragedy. Deep Reinforcement Learning and Q-network predict the complexity and uncertainty of the environment to generate optimal reward to states. Consequently, it activates automatic emergency braking and safe parking assistance to the vehicles. In addition, the proposed work provides safer transport for pedestrians and independent vehicles. Compared to the newer methods, the proposed system experimental results achieved 92.15% higher prediction rate accuracy. Finally, the proposed system saves many humans, animal lives from the vehicle hit, suggests drivers for rerouting to avoid unpredictable traffic, saves fuel consumption, and avoids carbon emission.

Determination of the maximum dangerous width of a rail track on a reinforced concrete base with fasteners of the КБ type, taking into account all influencing factors

Railway track retention standards in Ukraine do not take into account theconstruction of the subrail base, but regulate one for all types maximum dangerous value of the trackwidth, which was changed from 1546 mm to 1548 mm without any justification of scientific researchor explanations of the effects of tolerances the width of the rail track and the wheel track, which ingeneral at that time were not fully investigated but taking into account the emergence anddevelopment of new scientific problems associated with the emergence of intensive lateral wear ofrails and ridges of locomotive and wagon wheels. The deterministic dependences of lateralimpressions of the P65 type rail thread head on the simultaneous influence of vertical and horizontalforces for the newly installed repair profiles of UZ rolling stock on the basis of previously performedexperimental and theoretical studies were investigated. The results allow at this stage of research todetermine and calculate the practical values of the maximum dangerous width of the track, in whichthe subrail base consists of reinforced concrete sleepers and separate rail fasteners, which are usedboth on conventional highways with mixed traffic and on high-speed lines UZ.The article establishes the need to take into account new factors influencing the dangerouswidth of the rail track with intermediate rail fasteners of separate type depending on the load stress of sections and new repair profiles of rolling stock, as well as wear processes of intermediate railfasteners type KБ and its elements on the appearance of elastic backlash in the lateral direction fromthe influence of the guide wheels of the rolling stock. The recommended value of the maximum widthof the rail track for areas where service or emergency braking is applied - 1550 mm, taking intoaccount that the contact of the wheel and the rail is not at a point, but on an ellipse. The establishednorm of the maximum width of a rail track allows to define economic efficiency of introduction in theconditions of operation of a track in curved sections of a track of small radii with limited use of themaximum admissible lateral wear (15 mm) of a head of a rail thread provided that the normal-forcedentry of rolling stock carts.

Assessment of the technical condition of lift guides using a magnetic field

The systems that monitor individual components of machines and devices are under constant development. The ability to detect damages at an early stage allows failures to be prevented, so any uncontrolled downtime can be predicted in a controlled manner. Continuous monitoring of technical condition is an activity that also helps to reduce the losses due to equipment failures. However, not all areas can be monitored continuously. Such areas include lift guides where wear and tear can occur naturally, i.e. through abrasion of the material layer due to interaction with moving guide shoes or after emergency braking. Emergency braking causes local damages to the guide through plastic deformation of its surface resulting from indentation of the knurled roller of the brake. Such places are cleaned mechanically, which results in local reduction of the cross-sectional area. In such a case, it is difficult to continuously assess the technical condition of guides due to the prevailing operating conditions. Therefore, a concept of a head enabling assessment of the technical condition of guides at every stage of their operation has been developed. This article presents the novel concept of a magnetic head used for assessing the technical condition of lift guide rails that are the running track of lifting equipment. The initial tests were performed on the original test setup. The concept of the developed measuring head was verified for correct operation on specially prepared flat bars with holes. The results obtained in the form of laboratory tests proved that the proposed measuring head concept can be applied to the measurements under real conditions.

Robust anticipation of continuous steering actions from electroencephalographic data during simulated driving

Driving a car requires high cognitive demands, from sustained attention to perception and action planning. Recent research investigated the neural processes reflecting the planning of driving actions, aiming to better understand the factors leading to driving errors and to devise methodologies to anticipate and prevent such errors by monitoring the driver’s cognitive state and intention. While such anticipation was shown for discrete driving actions, such as emergency braking, there is no evidence for robust neural signatures of continuous action planning. This study aims to fill this gap by investigating continuous steering actions during a driving task in a car simulator with multimodal recordings of behavioural and electroencephalography (EEG) signals. System identification is used to assess whether robust neurophysiological signatures emerge before steering actions. Linear decoding models are then used to determine whether such cortical signals can predict continuous steering actions with progressively longer anticipation. Results point to significant EEG signatures of continuous action planning. Such neural signals show consistent dynamics across participants for anticipations up to 1 s, while individual-subject neural activity could reliably decode steering actions and predict future actions for anticipations up to 1.8 s. Finally, we use canonical correlation analysis to attempt disentangling brain and non-brain contributors to the EEG-based decoding. Our results suggest that low-frequency cortical dynamics are involved in the planning of steering actions and that EEG is sensitive to that neural activity. As a result, we propose a framework to investigate anticipatory neural activity in realistic continuous motor tasks.

Co-simulation model coupling of flexible rope hoisting system and hydraulic braking system for a mine hoist

The hoist is an important equipment in the mine pit. Since the containers are lifted or lowered with flexible steel wire ropes, there are shocks and vibrations during operation, especially in the emergency braking stage, the shocks and vibration will be more severe. Mine hoist is a complex system; therefore, it is difficult to obtain all its dynamics information only by investigating the flexible hoisting subsystem or hydraulic brake subsystem. Therefore, it is very necessary to establish an accurate model to predict these characteristics of the hoist, this will provide useful tools for hoist design and maintenance. Therefore, a joint modeling methodology is proposed and implemented in this paper. A hoisting system model considering the non-linear factors such as contact characteristics and flexibility was established in RecurDyn. The hydraulic braking system model and control system model were established in AMESim, and the co-simulation model was constructed by the interface module. In this co-simulation model, not only the flexible hoisting subsystem and hydraulic brake subsystem are included, but also the coupling effect of subsystems is considered. Finally, taking the lifting condition as an example, execute emergency braking research on the hoisting system under experiment, mathematical model, and co-simulation model, respectively. Comparing the co-simulation model with the mathematical dynamics model, and the experimental test results, research indicates that the joint simulation model of coupled hoisting system and hydraulic braking system can effectively reflect the dynamic characteristics of the actual hoisting system. It provides an effective tool for hoist design, optimization, performance analysis, and operating condition simulation. In addition, the methods and techniques used in the co-simulation modeling procedure are portable. Therefore, the paper is of significance for the mine hoist.

Mode Switching Control Using Lane Keeping Assist and Waypoints Tracking for Autonomous Driving in a City Environment

This paper proposes a mode switching supervisory controller for autonomous vehicles. The supervisory controller selects the most appropriate controller based on safety constraints and on the vehicle location with respect to junctions. Autonomous steering, throttle and deceleration control inputs are used to perform variable speed lane keeping assist, standard or emergency braking and to manage junctions, including roundabouts. Adaptive model predictive control with lane keeping assist is performed on the main roads and a linear pure pursuit inspired controller is applied using waypoints at road junctions where lane keeping assist sensors present a safety risk. A multi-stage rule based autonomous braking algorithm performs stop, restart and emergency braking maneuvers. The controllers are implemented in MATLAB® and Simulink™ and are demonstrated using the Automatic Driving Toolbox™ environment. Numerical simulations of autonomous driving scenarios demonstrate the efficiency of the lane keeping assist mode on roads with curvature and the ability to accurately track waypoints at cross intersections and roundabouts using a simpler pure pursuit inspired mode. The ego vehicle also autonomously stops in time at signaled intersections or to avoid collision with other road users.