Review on Vehicle Detection Technology for Unmanned Ground Vehicles

Liu, Qi; Li, Zirui; Yuan, Shuai; Zhu, Yuzheng; Li, Xueyuan

doi:10.3390/s21041354

Cited by 22 publications

(6 citation statements)

References 231 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the point cloud data is very sparse and uneven compared with image data and the data volume is large, which makes the data application and storage calculation face new problems. The 3D target recognition algorithm focuses on the design of algorithms for the above two problems, including various forms of reprocessing of the point cloud and clever design of the network structure to understand the geometric information in the point cloud [15]. The prediction-tracking relationship between the front and back frames of lane line detection is then established to further improve the accuracy and efficiency of lane line detection.…”

Section: Application Of Three-dimensional Targetmentioning

confidence: 99%

Multiview Fusion 3D Target Information Perception Model in Nighttime Unmanned Intelligent Vehicles

Zhen

2022

Journal of Function Spaces

View full text Add to dashboard Cite

Unmanned technology is an important development project of today’s cutting-edge science and technology, which has a significant impact on social and economic development, national defense construction, and scientific and technological development. The rapid development of industrial information technology has driven the unmanned intelligent vehicle system to innovate and gradually enter the public’s view, and at the same time, the driving safety of unmanned intelligent vehicles is also widely concerned. Target information perception system is the foundation of unmanned system and the fundamental guarantee of safety and intelligence of unmanned vehicles. There are three key problems of target recognition in unmanned driving, namely, target classification, localization, and attitude determination. In the implementation of a networked virtual environment system, a flexible and complete perception model is needed as the guiding model of the system. Since 3D point cloud data can provide more spatial information than 2D RGB image data, it is more beneficial to determine the target category, position, and pose in 3D. In this paper, based on the existing research of unmanned intelligent vehicle perception system, we combine the application of fusion of 3D target information perception model and develop a nighttime unmanned system based on multiview fusion of 3D target information perception model. This system can simultaneously perform the detection of multiple categories of objects and predict the center point, length, width, height, and orientation of the objects, so that the unmanned car can sense the location of the surrounding objects when driving in the actual scene.

show abstract

Section: Application Of Three-dimensional Targetmentioning

confidence: 99%

Multiview Fusion 3D Target Information Perception Model in Nighttime Unmanned Intelligent Vehicles

Zhen

2022

Journal of Function Spaces

View full text Add to dashboard Cite

show abstract

“…de Godoy et al [121] introduced the PAWS wearable acoustic system for monitoring pedestrian safety around car noises using pedestrians' own smart phones. More sophisticated audio sensing is routinely used for vehicles along high streets [122], to assess potential collisions between cars and people and objects, using vehicle-mounted ultrasound as a form of radar [123]. Lateral ultrasound sensing [124], in particular, has applicability to sensing of high street sidewalks, where pedestrians can often be rendered detectable from the roadway [125].…”

Section: Sensorsmentioning

confidence: 99%

Smart and Sentient Retail High Streets

Torrens

2022

Smart Cities

View full text Add to dashboard Cite

Here, we examine the extension of smart retailing from the indoor confines of stores, outward to high streets. We explore how several technologies at the union of retail intelligence and smart city monitoring could coalesce into retail high streets that are both smart and sentient. We examine the new vantages that smart and sentient retail high streets provide on the customer journey, and how they could transform retailers’ sway over customer experience with new reach to the public spaces around shops. In doing so, we pursue a three-way consideration of these issues, examining the technology that underpins smart retailing, new advances in artificial intelligence and machine learning that beget a level of street-side sentience, and opportunities for retailers to map the knowledge that those technologies provide to individual customer journeys in outdoor settings. Our exploration of these issues takes form as a review of the literature and the introduction of our own research to prototype smart and sentient retail systems for high streets. The topic of enhancing retailers’ acuity on high streets has significant currency, as many high street stores have recently been struggling to sustain custom. However, the production and application of smart and sentient technologies at hyper-local resolution of the streetscape conjures some sobering considerations about shoppers’ and pedestrians’ rights to privacy in public.

show abstract

“…Moreover, it sends the determined control strategy to the motion-controlling module, including high-level behavior and low-level control requirements [7,8]. It is crucial to complete autonomous driving tasks safely and efficiently by making reasonable decisions based on other modules [9].…”

Section: Introductionmentioning

confidence: 99%

Multi-Agent Decision-Making Modes in Uncertain Interactive Traffic Scenarios via Graph Convolution-Based Deep Reinforcement Learning

Gao

Liu

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

As one of the main elements of reinforcement learning, the design of the reward function is often not given enough attention when reinforcement learning is used in concrete applications, which leads to unsatisfactory performances. In this study, a reward function matrix is proposed for training various decision-making modes with emphasis on decision-making styles and further emphasis on incentives and punishments. Additionally, we model a traffic scene via graph model to better represent the interaction between vehicles, and adopt the graph convolutional network (GCN) to extract the features of the graph structure to help the connected autonomous vehicles perform decision-making directly. Furthermore, we combine GCN with deep Q-learning and multi-step double deep Q-learning to train four decision-making modes, which are named the graph convolutional deep Q-network (GQN) and the multi-step double graph convolutional deep Q-network (MDGQN). In the simulation, the superiority of the reward function matrix is proved by comparing it with the baseline, and evaluation metrics are proposed to verify the performance differences among decision-making modes. Results show that the trained decision-making modes can satisfy various driving requirements, including task completion rate, safety requirements, comfort level, and completion efficiency, by adjusting the weight values in the reward function matrix. Finally, the decision-making modes trained by MDGQN had better performance in an uncertain highway exit scene than those trained by GQN.

show abstract

Review on Vehicle Detection Technology for Unmanned Ground Vehicles

Cited by 22 publications

References 231 publications

Multiview Fusion 3D Target Information Perception Model in Nighttime Unmanned Intelligent Vehicles

Multiview Fusion 3D Target Information Perception Model in Nighttime Unmanned Intelligent Vehicles

Smart and Sentient Retail High Streets

Multi-Agent Decision-Making Modes in Uncertain Interactive Traffic Scenarios via Graph Convolution-Based Deep Reinforcement Learning

Contact Info

Product

Resources

About