2021
DOI: 10.1177/0361198121993471
|View full text |Cite
|
Sign up to set email alerts
|

Long Short-Term Memory-Based Human-Driven Vehicle Longitudinal Trajectory Prediction in a Connected and Autonomous Vehicle Environment

Abstract: The advent of connected and autonomous vehicles (CAVs) will change driving behavior and travel environment, and provide opportunities for safer, smoother, and smarter road transportation. During the transition from the current human-driven vehicles (HDVs) to a fully CAV traffic environment, the road traffic will consist of a “mixed” traffic flow of HDVs and CAVs. Equipped with multiple sensors and vehicle-to-vehicle communications, a CAV can track surrounding HDVs and receive trajectory data of other CAVs in c… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
12
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 22 publications
(12 citation statements)
references
References 39 publications
0
12
0
Order By: Relevance
“…Many existing autonomous vehicles have implemented machine learning-based car-following models [16], [17]. These models utilize human-driven car-following data to capture the pattern of human driving maneuvers.…”
Section: B Motivationmentioning
confidence: 99%
See 1 more Smart Citation
“…Many existing autonomous vehicles have implemented machine learning-based car-following models [16], [17]. These models utilize human-driven car-following data to capture the pattern of human driving maneuvers.…”
Section: B Motivationmentioning
confidence: 99%
“…As shown (17b), 𝑏 𝑐𝑜𝑚 (𝑡) =0 holds if the speed of a subject AV, 𝑣 𝐴𝑉 (𝑡) equals to speed of its immediate upstream vehicle,𝑣 𝑓 (𝑡) and 𝑠 𝑓𝑔𝑎𝑝 (𝑡) = 𝑠 𝑠𝑎𝑓𝑒 (𝑡). As shown in (17), 𝑏 𝑐𝑜𝑚 (𝑡)=0 holds only if the speed of a subject AV, 𝑣 𝐴𝑉 (𝑡) = 0, and speed of its immediate upstream vehicle,𝑣 𝑓 (𝑡) = 0. Thus, 𝑣 𝑓 (𝑡) = 𝑣 𝐴𝑉 (𝑡) = 0 and 𝑠 𝑛𝑒𝑡 (𝑡) = 0.…”
Section: ) Static Equilibriummentioning
confidence: 99%
“…While this method is simple in design and easy to implement, the computational cost of it is also significant. In a commonly used setting of spatial grids ( 10 , 16 ), one dedicated spatial grid of 3 × 13 cells is constructed for each vehicle, and constructing each grid needs to traverse the dataset once. Consequently, this method is not applicable in dense traffic scenarios.…”
Section: Related Workmentioning
confidence: 99%
“…Intra-vehicle level interpretability, which is inspired by motion-based models, reveals the true intentions of vehicles by predicting their longitudinal and lateral maneuvers. The next generation simulation (NGSIM) dataset ( 22 ), which has been widely used in previous studies ( 10 , 12 , 14 , 16 , 18 , 2325 ), is used to test the prediction performance of the proposed IIT model. Since NGSIM dataset only covers a limited area and thus cannot resemble large-scale traffic scenarios which ITS faces, a synthesized large-scale (SLS) dataset with up to 2,500 vehicles in a single scenario is developed to validate the scalability of the proposed IIT model.…”
mentioning
confidence: 99%
“…Similar to the encoder, we use an LSTM network as the primary decoder to achieve multistep trajectory prediction. The attentional mechanism is widely used in series forecasting for its good performance, such as machine translation [31], image annotation [32], speech recognition [33], text summarization [34], and trajectory prediction [35]. For efficiently solving the high-dimensional encoding representation C and dynamically paying attention to surrounding vehicles' motion, we also apply the attention mechanism to the decoder so that our decoder can adaptively select the most noteworthy surrounding vehicles at each time-step.…”
Section: Attentional Decodermentioning
confidence: 99%