Search Results

The radar-based advanced driver assistance systems (ADAS) like autonomous emergency braking (AEB) and forward collision warning (FCW) can reduce accidents, so as to make vehicles, drivers and pedestrians safer. For active safety, automotive millimeter-wave radar is an indispensable role in the automotive environmental sensing system since it can work effectively regardless of the bad weather while the camera fails. One crucial task of the automotive radar is to detect and distinguish some objects close to each other precisely with the increasingly complex of the road condition. Nowadays almost all the automotive radar products work in bidimensional area where just the range and azimuth can be measured. However, sometimes in their field of view it is not easy for them to differentiate some objects, like the car, the manhole covers and the guide board, when they align with each other in vertical direction.

To promote the development of automated vehicles (AVs), large scale of field operational tests (FOTs) were carried out around the world. Applications of naturalistic driving data should base on correlative scenarios. However, most of the existing scenario typologies, aiming at advanced driving assistance system (ADAS) and extracting discontinuous fragments from driving process, are not suitable for AVs, which need to complete continuous driving tasks. In this paper, a systematic scenario-typology consisting of four layers (from top to bottom: trip, cluster, segment and process) was first proposed. A trip refers to the whole duration from starting at initial parking space to parking at final one. The basic units ‘Process’, during which the vehicle fulfils only one driving task, are classified into parking process, long-, middle- and short-time-driving-processes. A segment consists of two neighboring long-time-driving processes and a middle or/and short one between them.

Millimeter-wave automotive radars can prevent traffic accidents and save human lives as they can detect vehicles and pedestrians even in night and in bad weather. Various types of automotive radars operating at 24 and 77 GHz bands are developed for various applications, like adaptive cruise control, blind-spot detection and lane change assistance. In each year, millions of millimeter-wave radar are sold worldwide. Millimeter-wave radar is composed of radar hardware and radar signal processing software, which detects the targets among noise, measures the distance, longitudinal speed and the azimuth angle of the targets, tracks the targets continuously, and controls the ego vehicle to brake or accelerate. Performance of the radar signal processing software is closely related with the radar hardware properties and radar measurement conditions.

Due to the differences in traffic situations and traffic safety laws, standards for extraction of critical driving scenarios (CDSs) vary from different countries and areas around the world. To maintain the characteristic variables under the Chinese typical CDSs, this paper uses the three-layer detection method to extract and detect CDSs in the Natural Driving Data from China-FOT project which executing under the real traffic situation in China. The first layer of detection is mainly based on the feature distributions which deviate from normal driving situations. These distributions associated with speed and longitudinal acceleration/lateral acceleration/yaw rate also quantify the critical levels classification.

Multi-sensor information fusion framework is the eyes for unmanned driving and Advanced Driver Assistance System (ADAS) to perceive the surrounding environment. In addition to the perception of the surrounding environment, real-time vehicle localization is also the key and difficult point of unmanned driving technology. The disappearance of high-precision GPS signal suddenly and defect of the lane line will bring much more difficult and dangerous for vehicle localization when the vehicle is on unmanned driving. In this paper, a road boundary feature extraction algorithm is proposed based on multi-sensor information fusion of automotive radar and vision to realize the auxiliary localization of vehicles. Firstly, we designed a 79GHz (78-81GHz) Ultra-Wide Band (UWB) millimeter-wave radar, which can obtain the point cloud information of road boundary features such as guardrail or green belt and so on.

Cut-in scenario is common in traffic and has potential collision risk. Human driver can detect other vehicle’s cut-in intention and take appropriate maneuvers to reduce collision risk. However, autonomous driving systems don’t have as good performance as human driver. Hence a deeper understanding on driving behavior is necessary. How to make decisions like human driver is an important problem for automated vehicles. In this paper, a method is proposed to classify the dangerous cut-in situations and normal ones. Dangerous cases were extracted automatically from naturalistic driving database using specific detection criteria. Among those cases, 70 valid dangerous cut-in cases were selected manually. The largest deceleration of subject vehicle is over 4 m/s2. Besides, 249 normal cut-in cases were extracted by going through video data of 2000km traveled distance. In normal driving cases, subject vehicle may brake or keep accelerating and the largest deceleration was less than 3 m/s2.

In China there are many mixed driving roads which cause a lot of safety problems between vehicles and pedalcyclists. Research on driver behavior under risk scenarios with pedalcyclist is relatively few. In this paper driver brake parameters under naturalistic driving are studied and pedalcyclists include bicyclist, tricyclist, electric bicyclist and motorcyclist. Brake reaction time and maximum brake jerk are used to evaluate driver brake reaction speed. Average deceleration is used to evaluate the effect of driver brake operation. Maximum deceleration is used to evaluate driver braking ability. Driver behaviors collected in China are classified and risk scenarios with pedalcyclist are obtained. Driver brake parameters are extracted and statistical characteristics of driver brake parameters are obtained. Influence factors are analyzed with univariate ANOVA and regression analysis.

For sensing system, the trustworthiness of the variant sensors is the crucial point when dealing with advanced driving assistant system application. In this paper, an approach to a hybrid camera-radar application of vehicle tracking is presented, able to meet the requirement of such demand. Most of the time, different types of commercial sensors available nowadays specialize in different situations, such as the ability of offering a wealth of detailed information about the scene for the camera or the powerful resistance to the severe weather for the millimeter-wave (MMW) radar. The detection and tracking in different sensors are usually independent. Thus, the work here that combines the variant information provided by different sensors is indispensable and worthwhile. For the real-time requirement of merging the measurement of automotive MMW radar in high speed, this paper first proposes a fast vehicle tracking algorithm based on image perceptual hash encoding.

A Joint Probabilistic Data Association (JPDA) multi-objective tracking improvement algorithm based on camera-radar fusion is proposed to address the problems of poor single-sensor tracking performance, unknown target detection probability, and missing valid targets in complex traffic scenarios. First, according to the correlation rule between the target track and the measurement, the correlation probability between the target and the measurement is obtained; then the measurement collection is divided into camera-radar measurement matched target, camera-only measurement matched target, radar-only measurement matched target, and no-match target; and the correlation probability is corrected with different confidence levels to avoid the use of unknown detection probability.

The intersection is recognized as the most dangerous area because of the restricted road structures and indeterminate traffic regulations. Therefore, according to the Vehicle-to-everything (V2X) communication, Intelligent Transportation Systems (ITS), and Digital Twin data, we present a potential energy field method to establish the general characteristics of intersection traffic safety, evaluate the safety situation of intersection and assist intersection traffic participants in passing through the intersection safer and more efficient. The resulting potential energy field method is established by the contour line of traffic participants' potential energy, which is constructed as a superposition of disparate energies, such as boundary potential energy, body potential energy, and velocity potential energy. The intersection traffic safety is evaluated by the potential energy field characteristic of simultaneous intersection traffic participants.

Lane marking detection plays a crucial role in Autonomous Driving Systems or Advanced Driving Assistance System. Vision based lane marking detection technology has been well discussed and put into practical application. LiDAR is more stable for challenging environment compared to cameras, and with the development of LiDAR technology, price and lifetime are no longer an issue. We propose a lane marking detection algorithm based on solid-state LiDARs. First a series of data pre-processing operations were done for the solid-state LiDARs with small field of view, and the needed ground points are extracted by the RANSAC method. Then, based on the OTSU method, we propose an approach for extracting lane marking points using intensity information.

Automotive radar is the most important component in the autonomous driving system, which detects the obstacles, vehicles and pedestrians around with acceptable cost. The target tracking is one of the key functions in the automotive radar which estimates the position and speed of the targets having regarding to the measurement inaccuracy and interferences. Modern automotive radar requires a multi-target tracking algorithm, as in the radar field of view hundreds of targets can present. In practice, the automotive radar faces very complicated and fast-changing road conditions, for example tunnels and curved roads. The targets’ unpredictable movements and the reflections of the electromagnetic wave from the tunnel walls and the roads will make the multi-target tracking a difficult task. Such situation may last several seconds so that the continuous tracks of the targets cannot be maintained and the tracks are dropped mistakenly.

Cut-in scenarios are common and of potential risk in China but Advanced Driver Assistant System (ADAS) doesn’t work well under such scenarios. In order to improve the acceptance of ADAS, its reactions to Cut-in scenarios should meet driver’s driving habits and expectancy. Brake is considered as an express of risk and brake tendency in normal Cut-in situations needs more investigation. Under critical Cut-in scenarios, driver tends to brake hard to eliminate collision risk when cutting in vehicle right crossing lane. However, under less critical Cut-in scenarios, namely normal Cut-in scenarios, driver brakes in some cases and takes no brake maneuver in others. The time when driver initiated to brake was defined as key time. If driver had no brake maneuver, the time when cutting-in vehicle right crossed lane was defined as key time. This paper focuses on driver’s brake tendency at key time under normal Cut-in situations.

In this paper, a potential risk assessment algorithm is proposed. The obvious risk assessment measure is defined as time to collision (TTC), whereas the potential risk measure is defined as the time before the host vehicle has to decelerate to avoid a rear-end collision assuming that the target vehicle brakes, i.e. time margin (TM). The driving behavior of the human driver in the dangerous car following scenario is studied by using the naturalistic driving data collected by video drive record (VDR), which include 78 real dangerous car following dangerous scenarios. A potential risk assessment algorithm was constructed using TM and the dangerous car following scenarios. Firstly, the braking starting time during dangerous car following is identified. Next, the TM at brake starting time of the 78 dangerous car following scenarios is analyzed. In the last, the thresholds of the potential risk levels are achieved.

The camera-based advanced driver assistance systems (ADAS) like lane departure warning system (LDWS) and lane keeping assist (LKA) can make vehicles safer and driving easier. Lane detection is indispensable for these lane-based systems for achieving vehicle local localization and behavior prediction. Since the vision is vulnerable to the variable environment conditions such as bad weather, occlusions and illumination, the robustness is important. In this paper, a robust algorithm for detecting and tracking multiple lanes with arbitrary shape is proposed. We extend the previously lane detection and tracking process from the space domain to the temporal-spatial domain by using a more robust and general multi-lane model. First, new slice images containing temporal information are generated from image sequences. Instead of binarization process, we use a more general detector for extracting the lane marker candidates with prior knowledge to generate the binary slice image.

The functional elements of decision making system are fuzzy, adaptive and self-learning for intelligent ground vehicles. As is well-known, operating environment of unmanned ground vehicles (UGVs) is complex, unknown and time-changing. And on the other hand, exact dynamic model of the vehicle is relatively difficult to gain. However, the changing of special dynamic parameters and the man-made driving laws of velocities and running direction are easily available. Therefore, this paper attempts to provide an approach based on fuzzy Q-learning algorithm for studying autonomous navigation and control system’s design, which aims to make unmanned vehicles adaptive and robust under complex and time-changing environment. The presented approach utilizes the drivers’ empirical knowledge for.

Estimating the motion state of peripheral targets is a very important part in the environment perception of intelligent vehicles. The accurate estimation of the motion state of the peripheral targets can provide more information for the intelligent vehicle planning module which means the intelligent vehicle is able to anticipate hazards ahead of time. To get the motion state of the target accurately, the target’s range, velocity, orientation angle and yaw rate need to be estimated. Three-dimensional high-resolution automotive millimeter wave radar can measure radial range, radial velocity, azimuth angle and elevation angle about multiple reflections of an extended target. Thus, the three-dimensional range information and three-dimensional velocity information can be obtained. With multiple three-dimensional high-resolution automotive millimeter-wave radar, it is possible to measure information in various directions of a target.

In the autonomous driving perception task, the accuracy of target detection is an essential evaluation, especially for small targets. In this work, we propose a multi-sensor fusion neural network that combines radar and image data to improve the confidence level of the camera when detecting targets and the accuracy of the prediction box regression. The fusion network is based on the basic structure of single-shot multi-box detection (SSD). Inspired by the attention mechanism in image processing, our work incorporates the a priori knowledge of radar detection in the convolutional block attention module (CBAM), which forms a new attention mechanism module called radar convolutional block attention module (RCBAM). We add the RCBAM into the SSD target detection network to build a deep neural network fusing millimeter-wave radar and camera.