Simultaneously transmitting and reflecting reconfig-urable intelligent surface (STAR-RIS) capable of manifesting the wireless channel provides the capability of signal reflection and refraction. However, conventional STAR-RIS has its limitation owing to signals impinging from one side of the surface, sup-porting either uplink (UL) or downlink (DL) users. Therefore, a novel concept of double-sided STAR-RIS (DS-STAR) becomes a promising solution, enabling signals impinging from both sides of the surface. In this paper, we consider multiple DS-STARs in a full-duplex (FD) enabled multi-input-multi-output (MIMO) system. We aim for maximizing joint UL/DL data rate by configuring transmit beamforming of the base station (BS) and UL users as well as configuration of DS-STARs, while ensuring quality-of-service (QoS) for both the UL/DL users. To tackle the complex problem, a genetic algorithm (GA) enhanced multi-agent Q-learning (G-MAQ) scheme is designed. MAQ considers a QoS-aware reward with each parameters as a sub-agent, whereas GA is applied to automatically optimize the hyperparameters of MAQ. In numerical results, we observe the significant im-provement of G-MAQ compared to that without hyperparameter optimization. Moreover, the proposed architecture of DS-STARs in FD networks achieves the highest rate compared to single-sided STAR-RIS, RIS and deployment without RIS/STAR-RIS. Additionally, the proposed G-MAQ scheme of DS-STAR FD sys-tems outperforms the other existing methods in open literature.

Integrated sensing and communication (ISAC) has become a key technology in the sixth-generation (6G) wireless networks, catering to the growing need for ubiquitous sensing and communication tasks. Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) can harness both reflective and refractive signals delivered. Due to orientation limitation of STAR-RISs, the multi-dual STAR-RISs (MD-STAR) is conceived to facilitate full-plane services in ISAC systems. In this paper, we intend to solve active beamforming of dual-function radar-communication (DFRC)-enabled BSs and passive beamforming of MD-STAR in ISAC systems, aiming for maximizing the achievable sum rate constrained by the maximum position error bound (PEB) as well as hardware limitation of MD-STAR. In order to solve this complex problem, we propose a two-layered multi-agent federated Q-learning (TMFQ) scheme. The inner layer Q-learning focuses on obtaining the solution of BSs and MD-STAR, whilst the outer layer Q-learning aims for optimizing the hyperparameters, including learning rate and discount rate of the inner-layer one. Additionally, we employ federated learning to facilitate information exchange between agents in the inner Q-learning. We evaluate our proposed TMFQ in terms of different numbers of MD-STAR elements, transmit antennas, and sensing targets. Benefiting from hyperparameter optimization of the inner layer Q-learning and information exchange of federated learning, the proposed TMFQ can achieve the highest rate compared to the other benchmarks, including Q-learning without hyperparameter optimization and without federated learning, heuristic algorithm, and conventional beamforming.

Forecasting pedestrian trajectories in dynamic scenes remains a critical problem in various applications, such as autonomous driving and socially aware robots. Such forecasting is challenging due to human-human and human-object interactions and future uncertainties caused by human randomness. Generative model-based methods handle future uncertainties by sampling a latent variable. However, few studies explored the generation of the latent variable. In this work, we propose the trajectory predictor with pseudo Oracle (TPPO), which is a generative model-based trajectory predictor. The first pseudo oracle is pedestrians’ moving directions, and the second one is the latent variable estimated from ground truth trajectories. A social attention module is used to aggregate neighbors’ interactions based on the correlation between pedestrians’ moving directions and future trajectories. This correlation is inspired by the fact that pedestrians’ future trajectories are often influenced by pedestrians in front. A latent variable predictor is proposed to estimate latent variable distributions from observed and ground-truth trajectories. Moreover, the gap between these two distributions is minimized during training. Therefore, the latent variable predictor can estimate the latent variable from observed trajectories to approximate that estimated from ground-truth trajectories. We compare the performance of TPPO with related methods on several public datasets. Results demonstrate that TPPO outperforms state-of-the-art methods with low average and final displacement errors. The ablation study shows that the prediction performance will not dramatically decrease as sampling times decline during tests.

Multi-person action forecasting is an emerging topic in the computer vision field, and it is a pivotal step toward video understanding at a semantic level. This task is difficult due to the complexity of spatial and temporal dependencies. Yet, the state-of-the-art literature does not seem to be adequately responsive to this challenge. Hence, how to better foresee the forthcoming actions per actor has to be further pursued. Toward this end, we put forth a novel RElational Spatio-TEmPoral learning approach (RESTEP) for multi-person action forecasting. Our RESTEP explores the key that inherently characterizes actions from a perspective of incorporating the spatial and temporal information in a single pass (spatio-temporal dependencies) by extending relational reasoning. As a result, the RESTEP enables simultaneously predicting the actions of all actors in the scene. Our proposal significantly differs from mainstream works that heavily rely on independently processing the spatial and temporal dependencies. The proposed RESTEP first perceives a graph building upon the historical observations, then reasons the relational spatio-temporal context to extrapolate future actions. In order to augment the comprehension of individual actions that might vary over time, we further delve deeper into the essence behind this point – the evolution of spatio-temporal dependencies via optimizing the corresponding mutual information. We assess the RESTEP method on the large-scale Atomic Visual Actions (AVA) dataset, Activities in Extended Videos (ActEV/VIRAT) dataset and Joint-annotated Human Motion Data Base (J-HMDB). The experimental outcomes reveal that RESTEP can introduce considerable improvements with respect to recent leading studies.

This paper describes an energy-based learning method that predicts the activities of multiple agents simultaneously. It aims to forecast both upcoming actions and paths of all agents in a scene based on their past activities, which can be jointly formulated by a probabilistic model over time. Learning this model is challenging because: 1) it has a large number of time-dependent variables that must scale with the forecast horizon and the number of agents; 2) distribution functions have to contain multiple modes in order to capture the spatio-temporal complexities of each agent's activities. To address these challenges, we put forth a novel Energy-based Learning approach for Multi-Agent activity forecasting (ELMA) to estimate this complex model via maximum log-likelihood estimation. Specifically, by sampling from a sequence of factorized marginalized multi-model distributions, ELMA generates most possible future actions efficiently. Moreover, by graph-based representations, ELMA also explicitly resolves the spatio-temporal dependencies of all agents' activities in a single pass. Our experiments on two large-scale datasets prove that ELMA outperforms recent leading studies by an obvious margin.

The main research question of this study was how to apply the design guidelines for traditional Changeable Message Signs (CMSs) to the design of the full-color and full-matrix LED Information Display Boards (IDBs). Three categories of messages were evaluated in this study, including (1) travel-time messages, (2) transit travel-time messages, and (3) Graphic Route Information Panels (GRIPs). A driving simulation program was developed based on real-world videos and used to evaluate the designed signs in terms of understandability and helpfulness for decision-making. A total of twenty-four local commuters participated in the driving simulator experiments. Results show that: (1) the perceived easiness of five-line travel-time message is significantly lower than the baseline three-line message, (2) the perceived helpfulness of the transit logo is significantly higher than the generic symbol, and (3) there is no significant difference between the drivers’ comprehension of the three-line message and the single-link GRIPs.

The booming self-driving cars need to understand the behaviors of other road users for better performance. Recognizing pedestrians’ crossing intentions is one of the most critical capabilities of self-driving cars to guarantee safe operations in the urban environment. Some researchers try to predict the future trajectories of pedestrians to avoid a potential collision. Others extract skeleton features from pedestrians to detect specific actions related to the crossing intention. All these methods either neglect the abundant appearance information of pedestrians, or work poorly under severe conditions, e.g., pedestrians standing far away, dim light, and occlusions. In this work, a pedestrian crossing intention recognition (PCIR) framework is proposed to recognize pedestrians’ crossing intention. A module for searching targets of interest is introduced to find the pedestrians who are likely to cross the streets, and perform scene perception simultaneously. An action recognition module utilizes a 3D convolutional neural network (CNN) to automatically extract spatiotemporal features that imply early actions before crossing, like limb movements. A distance encoding module makes full use of the contextual cues, e.g., distances between pedestrians and the oncoming vehicle, local traffic scenes around pedestrians, and vehicle speeds, to improve the recognition accuracy obtained from the action recognition module only. Finally, the PCIR framework fuses these factors to predict pedestrians’ crossing intentions by minimizing a focal loss. Experimental evaluations verify the effectiveness of the proposed method in recognizing pedestrians’ crossing intentions. Comparisons with the skeleton-based methods reveal the robustness of the PCIR framework in the urban environment.

Trajectory planning is essential for self-driving vehicles and has stringent requirements for accuracy and efficiency. The existing trajectory planning methods have limitations in the feasibility of planned trajectories and computational efficiency. This paper proposes a life-long learning framework to achieve effective and high-accuracy direct trajectory planning (DTP) tasks. Based on generative adversarial networks (GANs), this study develops a lightweight GDTP model to map the initial/final states and the control action sequence. Additionally, by embedding the GDTP into the rapidly-exploring random tree (RRT), a GDTP-RRT algorithm is further designed for long-distance and multi-stage planning tasks. Taking the tractor-trailer as an application case, we test the proposed method in multiple scenarios with varying characteristics. The experimental results show that the method can plan highly feasible trajectories in a short time, compared with the most applied algorithm – the cubic curve RRT* (CCRRT*). It is found that the tracking errors of our method are 29.1% and 44.1% lower than the CCRRT* in terms of position and heading angle. This paper provides an effective and stable vehicle trajectory planning method for complex self-driving tasks.

Pedestrian trajectory prediction in dynamic scenes remains a challenging and critical problem in numerous applications, such as self-driving cars and socially aware robots. Challenges concentrate on capturing pedestrians' motion patterns and social interactions, as well as handling the future uncertainties. Recent studies focus on modeling pedestrians' motion patterns with recurrent neural networks, capturing social interactions with pooling- or graph-based methods, and handling future uncertainties by using the random Gaussian noise as the latent variable. However, they do not integrate specific obstacle avoidance experiences (OAEs) that may improve prediction performance. For example, pedestrians' future trajectories are always influenced by others in front. Here, we propose the Graph-based Trajectory Predictor with Pseudo-Oracle (GTPPO), an encoder-decoder-based method conditioned on pedestrians' future behaviors. Pedestrians' motion patterns are encoded with a long short-term memory unit, which introduces temporal attention to highlight specific time steps. Their interactions are captured by a graph-based attention mechanism, which draws OAE into the data-driven learning process of graph attention. Future uncertainties are handled by generating multimodal outputs with an informative latent variable. Such a variable is generated by a novel pseudo-oracle predictor, which minimizes the knowledge gap between historical and ground-truth trajectories. Finally, the GTPPO is evaluated on ETH, UCY, and Stanford Drone datasets, and the results demonstrate state-of-the-art performance. Besides, the qualitative evaluations show successful cases of handling sudden motion changes in the future. Such findings indicate that GTPPO can peek into the future.

Learning from demonstrations has made great progress over the past few years. However, it is generally data hungry and task specific. In other words, it requires a large amount of data to train a decent model on a particular task, and the model often fails to generalize to new tasks that have a different distribution. In practice, demonstrations from new tasks will be continuously observed and the data might be unlabeled or only partially labeled. Therefore, it is desirable for the trained model to adapt to new tasks that have limited data samples available. In this work, we build an adaptable imitation learning model based on the integration of Meta-learning and Adversarial Inverse Reinforcement Learning (Meta-AIRL). We exploit the adversarial learning and inverse reinforcement learning mechanisms to learn policies and reward functions simultaneously from available training tasks and then adapt them to new tasks with the meta-learning framework. Simulation results show that the adapted policy trained with Meta-AIRL can effectively learn from limited number of demonstrations, and quickly reach the performance comparable to that of the experts on unseen tasks.

Making decisions in complex driving environments is a challenging task for autonomous agents. Imitation learning methods have great potentials for achieving such a goal. Adversarial Inverse Reinforcement Learning (AIRL) is one of the state-of-art imitation learning methods that can learn both a behavioral policy and a reward function simultaneously, yet it is only demonstrated in simple and static environments where no interactions are introduced. In this paper, we improve and stabilize AIRL’s performance by augmenting it with semantic rewards in the learning framework. Additionally, we adapt the augmented AIRL to a more practical and challenging decision-making task in a highly interactive environment in autonomous driving. The proposed method is compared with four baselines and evaluated by four performance metrics. Simulation results show that the augmented AIRL outperforms all the baseline methods, and its performance is comparable with that of the experts on all of the four metrics.

The field of autonomous driving has seen increasing proposed use of machine learning methodologies. However, there are still challenges in applying such methods since autonomous driving involves complex and dynamic interactions with the environment. Supervised learning algorithms such as imitation learning can work in environments represented in the training data set, however, it is impractical or cost-prohibitive to collect data for all possible environments. Reinforcement learning methods can train the agent through trial and error, but it may still fail in new environments. To overcome these shortcomings, we thus propose a meta reinforcement learning (MRL) method to improve the agent's generalization capabilities to new environments. The method is applied to automated lane-changing maneuvers at different traffic congestion levels. Specifically, we train the model at light to moderate traffic conditions under a reinforcement learning framework, and then test it at heavy traffic conditions that are never encountered during training. For performance evaluation, we use both collision rate and success rate of the lane-change maneuvers to quantify the safety and effectiveness of the proposed model. A pretrained model is established as a benchmark, which uses the same network structure and training tasks as our proposed model for fair comparison. Simulation results show that the proposed method achieves an overall success rate up to 20% higher than the benchmark model when it is generalized to the new environment of heavy traffic density. The collision rate is also reduced by up to 18% compared with the benchmark model. Furthermore, the proposed model shows more stable and efficient adaptation capabilities and can achieve 100% successful rate and 0% collision rate with only a few steps of gradient update adaptation.

In this survey, we systematically summarize the current literature on studies that apply reinforcement learning (RL) to the motion planning and control of autonomous vehicles. Many existing contributions can be attributed to the pipeline approach, which consists of many hand-crafted modules, each with a functionality selected for the ease of human interpretation. However, this approach does not automatically guarantee maximal performance due to the lack of a system-level optimization. Therefore, this paper also presents a growing trend of work that falls into the end-to-end approach, which typically offers better performance and smaller system scales. However, their performance also suffers from the lack of expert data and generalization issues. Finally, the remaining challenges applying deep RL algorithms on autonomous driving are summarized, and future research directions are also presented to tackle these challenges.

Multi-person action forecasting is an emerging task and a pivotal step towards video understanding. The major challenge lies in estimating a distribution characterizing the upcoming actions of all individuals in the scene. The state-of-the-art solutions attempt to solve this problem via a step-by-step prediction procedure. However, they are not adequate to address some particular limitations, such as the compounding errors, the innate uncertainty of the future and the spatio-temporal contexts. To handle the multi-person action forecasting challenges, we put forth a novel imitative learning framework upon the basis of inverse reinforcement learning. Specifically, we aim to learn a policy to model the aforementioned distribution up to a coming horizon through an objective that naturally solves the compounding errors. Such a policy is able to explore multiple plausible futures via extrapolating a series of latent variables and taking them into account to generate predictions. The impacts of these latent variables are further investigated by optimizing the directed information. Moreover, we reason the spatial context along with the temporal cue in a single pass with the usage of graph structural data. The experimental outcomes on two large-scale datasets reveal that our approach yields considerable improvements in terms of both diversity and quality with respect to recent leading studies.

This study combines applied mathematics, visual analysis technology, information science with an approach of Scientometrics to systematically analyze the development status, research distribution and future trend of intelligent vehicles research. A total number of 3933 published paper index by SCIE and SSCI from 2000 to 2019 are researched based on Mapping Knowledge Domain (MKD) and Scientometrics approaches. Firstly, this paper analyzes the literature content in the field of intelligent vehicles by including the literature number, literature productive countries, research organization, co-authorship of main research groups and the journals from which the articles are mainly sourced. Then, co-citation analysis is used to obtain five major research directions in the field of intelligent vehicles, which include “system framework”, “internet of vehicles”, “intersection control algorithms”, “influence on traffic flow”, and “policies and barriers”, respectively. The keyword co-occurrence analysis is applied to identify four dominant clusters: “planning and control system”, “autonomous vehicle questionnaire”, “sensor and vision”, and “connected vehicles”. Finally, we divide burst keywords into three phases according to the publication date to show more clearly the change of research focus and direction over time.

Linear Parameter Varying (LPV) models can be used to describe the vehicular lateral dynamic behavior of self-driving cars. They are particularly suitable for model-based control schemes such as model predictive control (MPC) applied to real-time trajectory tracking control, since they provide a proper trade-off between accuracy in different scenarios and reduced computation cost compared to nonlinear models. The MPC control schemes use the model for a long prediction horizon of the states, therefore prediction errors for a long time horizon should be minimized in order to increase the accuracy of the tracking. For this task, this work presents a system identification procedure for the lateral dynamics of a vehicle that combines a LPV model with a learning algorithm that has been successfully applied to other dynamic systems in the past. Simulation results show the benefits of the identified model in comparison to other well-known vehicular lateral dynamic models.

Reliable representation of multi-vehicle interactions in urban traffic is pivotal but challenging for autonomous vehicles due to the volatility of the traffic environment, such as roundabouts and intersections. This paper describes a semi-stochastic potential field approach to represent multi-vehicle interactions by integrating a deterministic field approach with a stochastic one. First, we conduct a comprehensive evaluation of potential fields for representing multi-agent intersections from the deterministic and stochastic perspectives. For the former, the estimates at each location in the region of interest (ROI) are deterministic, which is usually built using a family of parameterized exponential functions directly. For the latter, the estimates are stochastic and specified by a random variable, which is usually built based on stochastic processes such as the Gaussian process. Our proposed semi-stochastic potential field, combining the best of both, is validated based on the INTERACTION dataset collected in complicated real-world urban settings, including intersections and roundabout. Results demonstrate that our approach can capture more valuable information than either the deterministic or stochastic ones alone. This work sheds light on the development of algorithms in decision-making, path/motion planning, and navigation for autonomous vehicles in the cluttered urban settings.

Lane-change maneuvers are commonly executed by drivers to follow a certain routing plan, overtake a slower vehicle, adapt to a merging lane ahead, etc. However, improper lane change behaviors can be a major cause of traffic flow disruptions and even crashes. While many rule-based methods have been proposed to solve lane change problems for autonomous driving, they tend to exhibit limited performance due to the uncertainty and complexity of the driving environment. Machine learning-based methods offer an alternative approach, as Deep reinforcement learning (DRL) has shown promising success in many application domains including robotic manipulation, navigation, and playing video games. However, applying DRL to autonomous driving still faces many practical challenges in terms of slow learning rates, sample inefficiency, and safety concerns. In this study, we propose an automated lane change strategy using proximal policy optimization-based deep reinforcement learning, which shows great advantages in learning efficiency while still maintaining stable performance. The trained agent is able to learn a smooth, safe, and efficient driving policy to make lane-change decisions (i.e. when and how) in challenging situation such as dense traffic scenarios. The effectiveness of the proposed policy is validated by using metrics of task success rate and collision rate. The simulation results demonstrate the lane change maneuvers can be efficiently learned and executed in a safe, smooth and efficient manner.

Autonomous cars have to navigate in dynamic environment which can be full of uncertainties. The uncertainties can come either from sensor limitations such as occlusions and limited sensor range, or from probabilistic prediction of other road participants, or from unknown social behavior in a new area. To safely and efficiently drive in the presence of these uncertainties, the decision-making and planning modules of autonomous cars should intelligently utilize all available information and appropriately tackle the uncertainties so that proper driving strategies can be generated. In this paper, we propose a social perception scheme which treats all road participants as distributed sensors in a sensor network. By observing the individual behaviors as well as the group behaviors, uncertainties of the three types can be updated uniformly in a belief space. The updated beliefs from the social perception are then explicitly incorporated into a probabilistic planning framework based on Model Predictive Control (MPC). The cost function of the MPC is learned via inverse reinforcement learning (IRL). Such an integrated probabilistic planning module with socially enhanced perception enables the autonomous vehicles to generate behaviors which are defensive but not overly conservative, and socially compatible. The effectiveness of the proposed framework is verified in simulation on an representative scenario with sensor occlusions.

Lane change is a challenging task which requires delicate actions to ensure safety and comfort. Some recent studies have attempted to solve the lane-change control problem with Reinforcement Learning (RL), yet the action is confined to discrete action space. To overcome this limitation, we formulate the lane change behavior with continuous action in a model-free dynamic driving environment based on Deep Deterministic Policy Gradient (DDPG). The reward function, which is critical for learning the optimal policy, is defined by control values, position deviation status, and maneuvering time to provide the RL agent informative signals. The RL agent is trained from scratch without resorting to any prior knowledge of the environment and vehicle dynamics since they are not easy to obtain. Seven models under different hyperparameter settings are compared. A video showing the learning progress of the driving behavior is available22Video is available at https://youtu.be/UvMGwqfYYY3k.. It demonstrates the RL vehicle agent initially runs out of road boundary frequently, but eventually has managed to smoothly and stably change to the target lane with a success rate of 100% under diverse driving situations in simulation.

A reliable controller is critical for execution of safe and smooth maneuvers of an autonomous vehicle. The controller must be robust to external disturbances, such as road surface, weather, wind conditions, and so on. It also needs to deal with internal variations of vehicle sub-systems, including powertrain inefficiency, measurement errors, time delay, etc. These factors introduce issues in controller performance. In this paper, a feedforward compensator is designed via a data-driven method to model and optimize the controller's performance. Principal Component Analysis (PCA) is applied for extracting influential features, after which a Time Delay Neural Network is adopted to predict control errors over a future time horizon. Based on the predicted error, a feedforward compensator is then designed to improve control performance. Simulation results in different scenarios show that, with the help of with the proposed feedforward compensator, the maximum path tracking error and the steering wheel angle oscillation are improved by 44.4% and 26.7%, respectively.

The decision-making model of merging behavior is one of the key technologies of unmanned vehicles. In order to solve the problem of unmanned vehicles' merging decision making, this paper presents a merging strategy based on Least squares Policy Iteration (LSPI) algorithm, and selects the basis function which includes reciprocal of TTC, relative distance and relative speed to represent state space and discretizes action space. This study synthetically takes consideration o safety, the success of the task, the merging efficiency and comfort in setting reward function, compares the Q-learning with LSPI algorithm, and verifies its adaptability by using NGSIM data. The algorithm can ultimately achieve a success rate of 86%. This research can provide theoretic support and technical basis for the merging decision-making of unmanned vehicles.

Lane change is a crucial vehicle maneuver which needs coordination with surrounding vehicles. Automated lane changing functions built on rule-based models may perform well under pre-defined operating conditions, but they may be prone to failure when unexpected situations are encountered. In our study, we proposed a Reinforcement Learning based approach to train the vehicle agent to learn an automated lane change behavior such that it can intelligently make a lane change under diverse and even unforeseen scenarios. Particularly, we treated both state space and action space as continuous, and designed a Q-function approximator that has a closed-form greedy policy, which contributes to the computation efficiency of our deep Q-learning algorithm. Extensive simulations are conducted for training the algorithm, and the results illustrate that the Reinforcement Learning based vehicle agent is capable of learning a smooth and efficient driving policy for lane change maneuvers.

Accurate probabilistic prediction for intention and motion of road users is a key prerequisite to achieve safe and high-quality decision-making and motion planning for autonomous driving. Typically, the performance of probabilistic predictions was only evaluated by learning metrics for approximation to the motion distribution in the dataset. However, as a module supporting decision and planning, probabilistic prediction should also be evaluated from decision and planning perspective. Moreover, the evaluation of probabilistic prediction highly relies on the problem formulation variation and motion representation simplification, which lacks a formal foundation in a comprehensive framework. To address such concerns, we provide a systematic and unified framework for the analysis of three under-explored aspects of probabilistic prediction: problem formulation, representation simplification and evaluation metric. More importantly, we address the omitted but crucial problems in the three aspects from decision and planning perspective. In addition to a review of learning metrics, metrics to be considered from planning perspective are highlighted, such as planning consequence of inaccurate and erroneous prediction, as well as violations of predicted motions to planning constraints. We address practical formulation variations of prediction problems, such as decision-maker view and blind view for viewpoint, as well as reactive prediction for interaction, so that decision and planning can be facilitated.

The rapid development of the Dedicated Short Range Communications (DSRC) has provide a good opportunity for solving the increasingly outstanding traffic safety problems. One noteworthy function enabled by DSRC is the end of queue (EOQ) collision warning system. However, the reliability of the system is easily affected by some easily ignorable factors like DSRC penetration rate, DSRC communication range and positioning accuracy. In this paper, an EOQ warning system is proposed on a highway environment. The system is established using only velocity-related information combined with real highway data, which produce a warning threshold. For the proposed warning mechanism, we also build an evaluation model considering relevant influential factors. By means of simulation validation under different road conditions, an effective EOQ warning system can be issued in time when related parameters meet corresponding requirements.

Conventional layered planning architecture temporally partitions the spatiotemporal motion planning by the path and speed, which is not suitable for lane change and overtaking scenarios with moving obstacles. In this paper, we propose to spatially partition the motion planning by longitudinal and lateral motions along the rough reference path in the Frenét Frame, which makes it possible to create linearized safety constraints for each layer in a variety of on-road driving scenarios. A generic environmental representation methodology is proposed with three topological elements and corresponding longitudinal constraints to compose all driving scenarios mentioned in this paper according to the overlap between the potential path of the autonomous vehicle and predicted path of other road users. Planners combining A* search and quadratic programming (QP) are designed to plan both rough long-term longitudinal motions and short-term trajectories to exploit the advantages of both search-based and optimization-based methods. Limits of vehicle kinematics and dynamics are considered in the planners to handle extreme cases. Simulation results show that the proposed framework can plan collision-free motions with high driving quality under complicated scenarios and emergency situations.

The smart phones and their applications add the richness of the VANET applications and increase the requirements on data dissemination support of the networks. This paper focuses on the link reliability model for data dissemination in urban VANETs. First, we extend the analytic model on 1-dimension road to the roads with orthogonal crossings. Then, we verify the link reliability model for the irregularly crossed roads using Monte Carlo simulation. Based on these analytical results, we extend the evolving graph model with reliability (EGwR) on 1-D highway to 2-D urban environment. A data dissemination scheme based on EGwR is designed to verify the model efficacy. The scheme takes into account the macroscopic mobility pattern of vehicles and the impact on the link reliability of individual vehicle movement. Through extensive simulation study, the delivery ratio, latency, and the overhead factor of relay ratio are examined. The results demonstrate that our extended EGwR can effectively improve the data dissemination performance in metropolitan VANETs.

In most developed and developing countries, the maintenance of roadway pavement consumes considerable resources and represents a major item in government budget. However, due to the lack of sustainable and systematic approaches to implement long-term road pavement monitoring and assessment, the cost-effectiveness of performing such tasks is often a concern. In this paper, a crowdsourcing framework is proposed as a solution based on a smart probe car (SPC) system that utilizes mobile sensing technologies to collect environmental roadway data. Built upon the probe-vehicle system, the proposed method not only has the potential to save a significant amount of resources but also makes it possible to acquire real-time pavement information in a large scale.

This paper focuses on the design of a model that can be used for high-level decision making and low-level maneuver control, to achieve safe, optimal and stable lane-change maneuvers of autonomous vehicles. The objective of the controller optimized for lane change maneuvers is to minimize the travel time, maintain safety distances between the target vehicle and neighboring ones, satisfy the operational constraints of the target vehicle, and comply with the speed limit. In particular, the overall control problem is formulated with three sub-controllers. The high-level decision making algorithm is constructed as a mixed logic dynamic system and solved by Cplex. Secondly, the lane tracking problem is handled by a PD-controller. Lastly, the dynamic game theory approach is adopted to deal with safety design. After the modeling of the overall system is established at the three levels, the effectiveness of the proposed methodology is demonstrated by simulated scenarios.

This paper describes the experimental design for the field tests of safety applications within the scope of Networked Traveler Project currently being conducted in California, which is part of the US Department of Transportation (USDOT) and California DOT-sponsored Safe-Trip 21 Initiative. The safety applications are designed to provide drivers with alerts of situational awareness in highway driving scenarios. The objectives of the field tests are to verify the technical approach and to collect user feedback to refine the applications for future implementation. In this paper, the functional descriptions, technical rationale and hypotheses of experimental design are given. These applications, when deployed with timely alerts to drivers, can potentially increase driver awareness of the driving environment on the road ahead and minimize risks.

In the past two decades, occupant restraint systems for automobiles have made considerable progress globally. There has been a tremendous increase in the complexity and sophistication of functional requirements. Particularly significant in the overall evolution of restraint systems is the growth in electronics content, which is concurrent with similar phenomena in the automotive world, as well as in many other technology-related fields. In conjunction with this trend, the shift to digital components and subsystems expanded, while the design of restraint systems has become more diversified with enhanced adaptability and flexibility. In addition to the airbags that are standardized for passenger vehicles, there has been a whole spectrum of emerging safety features that provide additional safety improvements. For example, rollover and occupant sensing are being added onto an integrated occupant protection system. Global positioning systems are coupled with crash sensors into emergency notification services. Increasingly, vehicles are now being equipped with active safety systems. The availability of both passive restraints and active safety functions will allow an additional layer of synergistic integration across safety systems. Research and developments in vehicular safety can be expected to remain active in the foreseeable future. This paper describes the system-level design trends that have occurred in the past and offers a perspective of future design transition in automotive restraint systems

There have been significant research and developments in recent years for intersection-safety solutions that are intended to alert drivers of hazardous situations by utilizing sensing, computing, and communication technologies. Since the effectiveness of intersection-safety systems depends strongly on driver perception and acceptance of the provided warning signal, the understanding of driver actions under the targeted scenario is a central research topic. One significant safety concern at intersections is the left-turn crossing-path scenarios, where a left-turning vehicle is confronted by oncoming traffic. This paper describes the analysis and synthesis of real-world data for such scenarios observed in field observations. Specifically, traffic interactions in left-turn across-path situations are evaluated to compare data from various intersections with different operation and traffic attributes. The analyzed data were characterized to gain insight into a time gap acceptance exhibited by a population of drivers. The knowledge of driving behaviors can provide the guidelines for future investigation as well as a knowledge basis for the selection of warning criteria to allow timely alerts to drivers in the intended safety applications.

This paper addresses the feasibility of post-impact maneuvers that aim to mitigate accident sequences. In particular, the discussions emphasize the possibility of applying steering control to stabilize the trajectories of vehicles involved in a collision. The problem of interest is defined with descriptions of accident scenarios, limitations of applicability, and performance requirements. A model of vehicle dynamics is constructed to facilitate the design of steering controllers. Various collision scenarios are simulated to demonstrate the effectiveness of a generic feedback controller. The analysis provided herein shows steering control is promising as a driver-assistance function in emergency situations.