Search

Accurate trajectory prediction of surrounding vehicles is vital for automated vehicles to achieve high-level driving safety in complex situations. However, most state-of-the-art approaches for multi-vehicle trajectory prediction ignore vehicle motion uncertainty caused by different driving styles. Moreover, the interrelationship between the vehicle and the environment is seldom considered. To address the above problems, this paper proposes a driving risk map-integrated deep learning (DRM-DL) method for interactive trajectory prediction of surrounding vehicles, which comprehensively considers the motion uncertainty, trajectory intention uncertainty and interactions among vehicles, lane lines and road boundaries. Specifically, we adopt a conditional variational autoencoder (CVAE) to generate the candidate trajectories, in which the motion uncertainty is considered using a conditional Gaussian distribution. Furthermore, a driving risk map is constructed to realize a unified and interpretable representation of vehicle-vehicle and vehicle-environment interactions. The probability of each candidate trajectory is assigned using a trajectory probability model and a random selection is adopted to select a guided trajectory, which simulates the driver’s trajectory intention uncertainty. Finally, a relearning module is designed to obtain the precise trajectory prediction for surrounding vehicles. The proposed method is evaluated on the HighD dataset, and the results demonstrate a more accurate and reliable trajectory prediction for surrounding vehicles compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

A timely understanding of target vehicles (TVs) lateral behavior is essential for the decision-making and control of host vehicle. Existing physical model-based methods such as motion-based method and multiple centerline-based method are generally constructed based on TV pose and longitudinal velocity, and tend to ignore TV preview driving characteristic and other useful information such as lateral velocity and yaw rate. To address these issues, a driver preview and multiple centerline model-based probabilistic behavior recognition architecture is proposed for timely and accurate TV lateral behavior prediction. Firstly, a driver preview model is used to describe vehicle preview driving characteristic, and TV preview lateral offset and preview lateral velocity are calculated with TV states and road reference information. Then, the preview lateral offset and preview lateral velocity are combined with multiple centerline model for TV lateral behavior reasoning based on the interacting multiple model-based probabilistic behavior recognition algorithm. With this method, TV preview driving characteristic and lateral motion states are combined for precise TV lateral behavior description. Furthermore, to predict short-term lateral behavior, a preview lateral velocity-dependent transition probability matrix model constructed with Gaussian cumulative distribution function is proposed. Simulation and experimental results show that the proposed method considering vehicle preview driving characteristic predicts TV lateral behavior earlier than the conventional method. [ABSTRACT FROM AUTHOR]

Coordination of the Connected and Automated Vehicles (CAVs) is a demanding task in aspects of effective incorporation of road information with the control of vehicle motion states. Formulating a platoon composed of multiple CAVs initially located in multiple lanes requires integrated consideration of both steering incurred by the curved road and merging actions. Meanwhile, additional requirement of intervehicle safety distance keeping as well as bounded actuations is also critical for practical implementation. Considering the above problems, a comprehensive framework containing a distributed controller is proposed in this paper to systematically address the combined problems. A bi-level curvilinear vehicle coordination scheme is proposed and proven to be capable of guiding CAVs to desired platoon formation with theoretical analysis. Besides, both longitudinal and lateral acceleration limitations have been taken into consideration. The limited longitudinal acceleration is included in the design of nonlinear saturated controller of which the convergence has been proven. Adaptive merging is realized with a bounded lateral controller. The condition of limiting the initial states to guarantee safe intervehicle distance maintenance is formulated. Hardware-in-the-Loop (HiL) test demonstrations in multiple road scenarios with different curvatures validate the performance of the proposed controller over existing baseline methods. [ABSTRACT FROM AUTHOR]

In this article, a new soft-switching auxiliary circuit structure for the synchronous rectification noninverting buck–boost converter (NIBBC) is proposed. This new auxiliary circuit, which contains a fully coupled inductor (or a transformer), a snubber inductor, a capacitor, and a power diode, will provide zero voltage switching (ZVS) turn-ON conditions for all power transistors of the proposed NIBBC. In addition, waveform ripples in the auxiliary circuit of the output side are reduced, and then the output current ripple is also reduced. Meanwhile, the current across the main inductor is not affected by the auxiliary circuit. In order to analyze the proposed NIBBC, operating principles, soft-switching implementation conditions, and main characteristics of the proposed NIBBC are presented in this article. Finally through building a 400-W experimental prototype, key waveforms and measuring efficiency curves are obtained. Experiment result shows that all transistors of the new NIBBC operate under ZVS conditions. The efficiency of the proposed NIBBC is improved by comparing to the triangular current mode soft-switching NIBBC. [ABSTRACT FROM AUTHOR]

Reliable trajectory prediction of preceding target vehicles (PTVs) is crucial for the planning and decision making of automated vehicles. However, the future trajectory is affected by the driver's intention and diverse driving styles, which can hardly be predicted precisely, especially when the vehicle performs a lane change maneuver. In this study, we propose a lane crossing and final points generation (CFPG) model-based trajectory prediction approach for PTVs, in which the key influence factors such as the driver's intention and the mixed driving style are included. Firstly, we build a maneuver and stage recognition model upon the long short term memory (LSTM) to infer the current maneuver of the preceding target vehicle. Furthermore, the approach predicts the lane crossing point using a physics-based model combining with a deep conditional generative model trained by a deep neural network. Moreover, a maneuver-based model is adopted to predict the final point according to the prediction interval. In order to avoid the possible cumulative error caused by iteratively generating trajectories in traditional methods, we use a curve fitting method to obtain the predicted trajectory. Lane changing data collected from naturalistic driving scenarios are used to verify the proposed approach, and the results suggest more accurate and reliable prediction trajectories compared with conventional methods. [ABSTRACT FROM AUTHOR]

Multiextended target tracking (METT) has important applications in many fields, including autonomous vehicles, traffic flow monitoring, etc. However, as an acknowledged METT algorithm, the labeled multi-Bernoulli (LMB) filter cannot handle the intertarget occlusion problem, which frequently observed among METT, leading to an estimated trajectory break and even target loss. To tackle this problem, this article proposes an improved LMB filter with intertarget occlusion handling ability for METT. First, an intertarget occlusion probability (IOP) model based on a labeled random finite set using a laser range finder is developed. The IOP model theoretically describes the probability that each tracked target being occluded, considering both partial and full occlusion. Second, a true detection probability (TDP) model is presented to describe the probability that a target will generate corresponding measurement of a sensor in the presence of occlusion. The TDPs of tracked targets provide a way to integrate their estimated occlusion probabilities into the LMB filter to improve its capability of handling occluded tracks. We carried out multiple vehicle tracking simulation and field test using a laser range finder. Both simulation and experiment results illustrate that our improved LMB filter with occlusion handling ability can successfully tackle the intertarget occlusion problem and outperform conventional algorithms. [ABSTRACT FROM AUTHOR]

Trajectory planning of an automated vehicle requires behavior knowledge of preceding target vehicles (PTVs), and lateral states, such as lateral velocity and yaw rate are key enablers for precise behavior description. However, lateral states of a PTV can hardly be measured directly by common onboard sensors. In addition, although these states can be transmitted via vehicle to vehicle (V2V), the accuracy is limited by the state holding process during the communication interval. Aiming at improved PTV lateral states, this article considers the estimation of these states using visual and V2V measurements, and proposes a three-stage fusion architecture consisting of input estimator, heterogeneous model-based local estimators, and fusion center. Specifically, to cope with the low rate of the received steering angle, the input estimator is constructed to obtain high rate control inputs. In the local estimator design, unlike the conventional modeling problems mixing control input errors with model errors in process noise, this paper separates them and develops a model adaption algorithm to compensate the time-varying covariance of the errors of the estimated control inputs. Then, to fuse the heterogeneous local estimates in the fusion center, a subfull model-based information matrix filter is designed to address this specific heterogeneous fusion problem, in which the local models are treated as submodels of a common full model. Hardware-in-the-loop experimental results show that the proposed method gives more accurate estimates in comparison with other approaches. [ABSTRACT FROM AUTHOR]

This letter proposed a new soft-switching non-inverting buck–boost converter (NIBBC) by introducing the magnetic coupling effect to an existing soft-switching dc/dc converter. The new NIBBC obtains two superiorities: one magnetic core is removed to improve the efficiency; the magnetic coupling effect can give an adjustable soft-switching range. Operating principles and converter characteristics of the new NIBBC are presented. An experimental prototype of the new NIBBC is built, and switching waveforms and the efficiency are measured. Experimental results show that the new NIBBC can obtain soft-switching conditions and has efficiency improvement comparing to hard-switching converter and another soft-switching dc/dc converter. [ABSTRACT FROM AUTHOR]

Multiple vehicle tracking (MVT) system is a prerequisite to path planning and decision making of self-driving cars as it can provide positions of surrounding vehicles. Most of the available approaches belonging to the so called tracking-by-detection approach inevitably bring detection errors into the tracking result. In this study, we proposed a laser range finder (LRF) based track-before-detect MVT algorithm without detection procedure. Moreover, different from the state of the art in track-before-detect approaches using raw data, we applied a pre-clustering procedure to segment the raw data into disjoint clusters to reduce computation demand. Specifically, a clustering algorithm named iterative nearest point search (INPS) which can even handle the partial occlusion situations that are challenging for traditional clustering algorithms was designed for the pre-clustering procedure. Furthermore, a detailed cluster-to-target measurement model was proposed to describe the difference between cluster and hypothesis vehicle. Finally, we integrated the measurement model into the labeled multi-Bernoulli filter with particle implementation. Simulations and experiments show that the proposed MVT algorithm provides more accurate estimates of vehicle number and position in comparison with conventional methods. [ABSTRACT FROM AUTHOR]

This brief summarizes soft-switching methods for the non-inverting buck-boost converter (NIBBC). Then a new zero voltage switching (ZVS) NIBBC is proposed. This new NIBBC employs a triple coupled inductor, two resonant inductors, and two auxiliary diodes. All transistors of this new NIBBC will work under ZVS conditions. Furthermore the current across the main inductor will be continuous during all the period, and therefore its ripples will be small. Benefit from low current ripples of the main inductor, ripples and harmonics of the output current are also reduced. To verify this new NIBBC, an experimental platform was built, and waveforms (voltage and current) and efficiency are measured. Measuring results show that ZVS conditions of all transistors are obtained. And the efficiency of the new NIBBC is higher than traditional continuous conduction mode and triangular current mode NIBBCs. [ABSTRACT FROM AUTHOR]

In this paper, several new coupled-inductor-based soft-switching dc–dc converters are proposed. These converters are obtained by changing the coupled branch of several existing dc–dc converters. Meanwhile they have similar characteristics to these existing converters, and provide more choices for the practical application. Then by applying an existing efficiency improvement method, which is used in the buck-type soft-switching converter, to all abovementioned converters, several new converters with efficiency improvement characteristics are obtained. This efficiency improvement method utilizes the low conduction performance of the transistor to reduce the loss. In addition, this method has the same control complexity to original topologies, because the auxiliary transistor has the same control timing to one of main transistors. The characteristic of new converters and efficiency improvement method are presented by analyzing two new topologies (boost-type converters). Finally simulation and experimental results are given and analyzed by designing a prototype. Based on these results, soft-switching conditions and efficiency improvement capability are verified. [ABSTRACT FROM AUTHOR]

Automated vehicle control requires full knowledge of motion behavior of the preceding target vehicles (PTVs), and the states such as longitudinal/lateral velocity and yaw rate are critical for the PTV behavior description. However, the PTV's lateral states estimation have seldom been addressed in the state-of-the-art literatures. Aimed at providing reliable PTV lateral states, this paper presents a novel combined model-based estimation scheme. Different from the conventional PTV models, the proposed model is constructed based on the host–target vehicle dynamics and road constraints. Specifically, steering angle of the PTV is included in the state vector. The measurements, such as heading angle, road curvature, and lateral distance to the lane center, are available from an onboard vision system. As a vision system inevitably has measurement delay, a modified Kalman filter is developed to address the sampling issue. To verify the proposed approach, hardware-in-the-loop experiments are conducted in designed testing scenarios. [ABSTRACT FROM AUTHOR]

In this paper, a soft-switching topology is proposed for the bidirectional dc–dc converter. In order to achieve soft-switching conditions, the auxiliary circuits including a small inductor and two capacitors are introduced to the bidirectional dc–dc converter. By generating and keeping a recycle current in the auxiliary circuits, the proposed topology can provide soft-switching conditions for both switches of the bidirectional dc–dc converter in fixed frequency control application. Meanwhile, no auxiliary switches are introduced. Due to the existence of the auxiliary circuits, the proposed topology can also reduce the current ripple in the main inductor. Based on this soft-switching method, a family of bidirectional soft-switching dc–dc topologies is derived. These topologies have the similar structures and the same characteristics. The topology deduction, operating principles, and design guidelines are presented in detail. Finally, an experimental prototype is built to verify the analysis and characteristics of the proposed topologies. [ABSTRACT FROM PUBLISHER]

For series–parallel hybrid electric vehicles (HEVs), problems of driveability are significant and difficult to solve due to clutch engagement during mode transitions. In this paper, a robust controller was designed for a series–parallel HEV to reduce vehicle jerk during mode transitions and improve vehicle driveability. First, a linear dynamic system model of the controlled plant was obtained for robust control design. Then, the robust controller was designed based on the mu-synthesis method and solved using the discrete $D-K$ iteration; parameter uncertainties in the system model were considered in the design process to ensure the robustness of the control system. Finally, a hardware-in-the-loop (HIL) simulation was performed to verify the proposed controller. The HIL platform was composed of a dynamometer-simulated engine, a real transmission, a virtual electric machine, and a virtual vehicle, which was constructed based on the nonlinear dynamics of tires, road, and vehicle body. The HIL simulation results showed the effectiveness of the proposed robust mode transition control. [ABSTRACT FROM AUTHOR]

This letter presents a novel topology for a buck dc–dc converter with soft-switching capability, which operates under a zero-current-switching condition at turn on and a zero-voltage-switching condition at turn off. In order to realize soft switching, based on a basic buck converter, the proposed converter added a small inductor, a diode, and an inductor coupled with the main inductor. Because of soft switching, the proposed converter can obtain a high efficiency under heavy load conditions. Moreover, a high efficiency is also achieved under light load conditions, which is significantly different from other soft-switching buck converters. The detailed theoretical analyses of steady-state operation modes are presented, and the detailed design methods and some simulation results are also given. Finally, a 600 W prototype is built to validate the theoretical principles. The switching waveforms and the efficiencies are also measured to validate the proposed topology. [ABSTRACT FROM AUTHOR]

This paper presents a novel topology for a nonisolated bidirectional dc–dc converter with soft-switching capabilities, which usually operates at a zero-voltage-switching (ZVS) condition. A nonisolated dc–dc converter combines a buck converter and a backward boost converter into one circuit, which consists of a half-bridge power switch, an inductor, and capacitors. In order to realize ZVS conditions, the proposed converter utilizes a coupled inductor, a small independent inductor, and auxiliary switches and diodes. Due to ZVS, switching stress on switch components is reduced, and the reverse recovery problem of MOSFET antiparallel body diodes is also eliminated. Moreover, the operating modes of the proposed converter can be switched between a ZVS mode and a conventional hard-switching mode on the basis of load conditions. The soft-switching mode is for heavy loads, and the hard-switching mode is for light-load conditions. Therefore, the highest efficiency can be obtained at almost all load ranges. The detailed theoretical analyses in each mode are presented, and a 1-kW prototype is also built to verify the principle of the circuit and the theoretical analysis. [ABSTRACT FROM PUBLISHER]

This paper presents the mathematical modeling and analysis of a novel multimode transmission (MMT) for a hybrid electric vehicle (HEV) using a single electric machine (EM), which implies compactness and low cost. The single-EM solution avoids losses from another EM and its power electronics, which are employed in many existing HEVs. The topology of the MMT planetary gearset is the same as that of conventional four-speed automatic transmissions (ATs). The MMT realizes five power flow modes, which are developed into 16 operation modes, including one Motor_only mode, four Engine_only modes, four Compound driving modes, six Braking modes, and one Charging while parking mode. The properly arranged clutches transmit power flow more flexibly, allow direct mechanical power transmission from the engine to the drive shaft, and avoid spin loss for the engine and energy conversion loss for the electric components. Simulation under the New European Driving Cycle (NEDC) shows that the fuel consumption of the proposed HEV is comparable to a benchmark “THS II-like” vehicle, which uses a planetary gearset, two EMs, and no clutch, which indicates the fuel economy potential of this concept. [ABSTRACT FROM PUBLISHER]