Driver Intention Recognition: State-of-the-Art Review

Vellenga, Koen; Steinhauer, H. Joe; Karlsson, Alexander; Falkman, Göran; Rhodin, Asli; Koppisetty, Ashok Chaitanya

doi:10.1109/ojits.2022.3197296

Cited by 12 publications

(4 citation statements)

References 93 publications

(120 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is because predicting the categories of edge data is not an easy task. But many tasks, such as vehicle trajectory prediction [13], [14], [39], [46] and behavior prediction [16], [43], [47]- [49], benefit from graph-based data representation, since it provides an easy way to learn from a given scene without using image representation data.…”

Section: A Graph-based Methods Applied In Intelligent Vehiclementioning

confidence: 99%

RSG-GCN: Predicting Semantic Relationships in Urban Traffic Scene With Map Geometric Prior

Tian

Carballo

et al. 2023

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

Automated identification of the relationships between traffic actors and surrounding objects, in order to describe their behavior and predict their intentions, has become the focus of increasing attention in the field of autonomous driving. Therefore, in this work, we propose a Road Scene Graphs-Graph Convolutional Network (RSG-GCN) as a novel, graphbased model for predicting the topological graph structure of a given traffic scene. The status of the actors and HD map information are integrated as prior knowledge, allowing the edges linking the actor nodes to capture potential semantic relationships, such as "vehicle approaching pedestrian" and "pedestrian waiting at intersection". To train this model, we created our own RSG dataset, as well as a relational dataset and benchmark derived from nuScenes. Our extensive range of experiments demonstrate that our model can more accurately predict semantic relationships and behavior in a given traffic scene than other popular traffic scene prediction models. In particular, regarding the use of HD map prior knowledge, we found that the resulting increase in accuracy significantly outweighs performance loss caused by the increase in graph size. The downstream applications of RSG include traffic scene retrieval and synthetic traffic scene generation, which are briefly described.

show abstract

Section: A Graph-based Methods Applied In Intelligent Vehiclementioning

confidence: 99%

RSG-GCN: Predicting Semantic Relationships in Urban Traffic Scene With Map Geometric Prior

Tian

Carballo

et al. 2023

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

show abstract

“…The current methods of driving intention recognition can be broadly categorized into three main groups [1] : fuzzy control, Hidden Markov Models (HMM) and Neural Networks (NNs). Among them, fuzzy control [2][3][4] recognition method is easy to implement, but the rule formulation of fuzzy logic table is done by experience or manually, which has strong human subjectivity.…”

Section: Introductionmentioning

confidence: 99%

Driving intention recognition based on COA-LSTM network

Xu,

Xi,

Qin

et al. 2024

Fourth International Conference on Mechanical Engineering, Intelligent Manufacturing, and Automation Technology (MEMAT 2023)

View full text Add to dashboard Cite

Driving intention recognition is one of the key technologies in the development of advanced assisted driving systems (ADAS), which can greatly reduce the occurrence of traffic accidents and thus improve driving safety and comfort. In order to recognize driving intention more effectively and accurately, this paper proposes a method to improve the recognition rate of driving intention based on Long Short-term Memory (LSTM) network optimized by Coati Optimization Algorithm (COA). First, the training dataset and test set based on the road information dataset are established by considering the degree of influence of feature factors on driving intention. Second, the COA-LSTM driving intention recognition model is constructed. Finally, the training and validation evaluation metrics are performed based on the dataset, and the results show that the COA-LSTM-based driving intention recognition model proposed in this paper is better than the LSTM and BP models as a whole, and the accuracy rate and the 𝐹 score are both above 0.95.

show abstract

“…For example, methods 28 for solving multi-depot vehicle routing frame the problem via deterministic optimization, using binary decision variables. On the other hand, the use of stochastic frameworks has been gaining traction in the literature on advanced and intelligent transportation systems, for example in the context of differential privacy (privacy is indeed a key requirement for these applications 29 ) where privacy is achieved by injecting noise in the system 30 , 31 , or in driver 32 or pedestrian 33 intent prediction. Probabilistic methods/models 34 have a long history 35 in mobility estimation/prediction.…”

Section: Introductionmentioning

confidence: 99%

CRAWLING: a crowdsourcing algorithm on wheels for smart parking

Garrabé,

Russo

2023

Sci Rep

View full text Add to dashboard Cite

We present the principled design of CRAWLING: a CRowdsourcing Algorithm on WheeLs for smart parkING. CRAWLING is an in-car service for the routing of connected cars. Specifically, cars equipped with our service are able to crowdsource data from third-parties, including other cars, pedestrians, smart sensors and social media, in order to fulfill a given routing task. CRAWLING relies on a solid control-theoretical formulation and the routes it computes are the solution of an optimal data-driven control problem where cars maximize a reward capturing environmental conditions while tracking some desired behavior. A key feature of our service is that it allows to consider stochastic behaviors, while taking into account streams of heterogeneous data. We propose a stand-alone, general-purpose, architecture of CRAWLING and we show its effectiveness on a set of scenarios aimed at illustrating all the key features of our service. Simulations show that, when cars are equipped with CRAWLING, the service effectively orchestrates the vehicles, making them able to react online to road conditions, minimizing their cost functions. The architecture implementing our service is openly available and modular with the supporting code enabling researchers to build on CRAWLING and to replicate the numerical results.

show abstract

Driver Intention Recognition: State-of-the-Art Review

Cited by 12 publications

References 93 publications

RSG-GCN: Predicting Semantic Relationships in Urban Traffic Scene With Map Geometric Prior

RSG-GCN: Predicting Semantic Relationships in Urban Traffic Scene With Map Geometric Prior

Driving intention recognition based on COA-LSTM network

CRAWLING: a crowdsourcing algorithm on wheels for smart parking

Contact Info

Product

Resources

About