An LSTM network for highway trajectory prediction

By Florent Altch'e, Arnaud de La Fortelle. 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 2017

609 citations recorded by the source corpus.

In order to drive safely and efficiently on public roads, autonomous vehicles will have to understand the intentions of surrounding vehicles, and adapt their own behavior accordingly. If experienced human drivers are generally good at inferring other vehicles' motion up to a few seconds in the future, most current Advanced Driving Assistance Systems (ADAS) are unable to perform such medium-term forecasts, and are usually limited to high-likelihood situations such as emergency braking. In this article, we present a first step towards consistent trajectory prediction by introducing a long short-term memory (LSTM) neural network, which is capable of accurately predicting future longitudinal and lateral trajectories for vehicles on highway. Unlike previous work focusing on a low number of trajectories collected from a few drivers, our network was trained and validated on the NGSIM US-101 dataset, which contains a total of 800 hours of recorded trajectories in various traffic densities, representing more than 6000 individual drivers.

Subfields: Automotive Engineering, Building and Construction, Signal Processing

View Paper: https://www.semanticscholar.org/paper/08054cb1e57948b3f113ad2a3158cbcb2b5c0f37

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Building and Construction

In Signal Processing

Citations in the corpus

A Survey on Trajectory-Prediction Methods for Autonomous Driving (2022, methodology): “[72] use a single-layer LSTM to accomplish trajectory prediction of the target vehicle.”
Attention Based Vehicle Trajectory Prediction (2020, methodology): “In [5], [8], the exact future positions are predicted.”
A Survey of State-Action Representations for Autonomous Driving (2018, methodology): “This representation is used in (Abbeel and Ng, 2004; Wei et al., 2010; Levine et al., 2011; Ulbrich and Maurer, 2013; Wang and Chan, 2017; Altché and Fortelle, 2017; Bhattacharyya et al., 2018), and is studied in (Chen et al.”
Multimodal Motion Prediction with Stacked Transformers (2021, methodology): “Recently deep learning-based meth-ods have been widely used for motion prediction [1, 15, 8, 2, 11].”
Deep Learning-Based Vehicle Behavior Prediction for Autonomous Driving Applications: A Review (2020, methodology): “The authors in [28] consider nine vehicles in three lanes surrounding the target vehicle including two vehicles in front of the TV.”
INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps (2019, methodology): “NGSIM dataset [13] is the most popular one used in the aforementioned areas, such as prediction [14]–[16], behavior modeling [5], social behavior generation and planning [10], and represen-”
GOHOME: Graph-Oriented Heatmap Output for future Motion Estimation (2021, background): “The sequential nature of temporal trajectories makes them a straightforward application of recurrent neural networks [9].”