Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecture
By Seonghyeon Park, Byeongdo Kim, Chang Mook Kang, Chung Choo Chung, Jun Won Choi. 2018 IEEE Intelligent Vehicles Symposium (IV), 2018
474 citations recorded by the source corpus.
In this paper, we propose a deep learning based vehicle trajectory prediction technique which can generate the future trajectory sequence of surrounding vehicles in real time. We employ the encoder-decoder architecture which analyzes the pattern underlying in the past trajectory using the long short-term memory (LSTM) based encoder and generates the future trajectory sequence using the LSTM based decoder. This structure produces the $K$ most likely trajectory candidates over occupancy grid map by employing the beam search technique which keeps the $K$ locally best candidates from the decoder output. The experiments conducted on highway traffic scenarios show that the prediction accuracy of the proposed method is significantly higher than the conventional trajectory prediction techniques.
Subfields: Building and Construction, Signal Processing
View Paper: https://www.semanticscholar.org/paper/528f6933d246ff9d0918f2e936d7bfa79aa7fea9
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Building and Construction
In Signal Processing
- Anne Verroust-Blondet
- Dariu M. Gavrila
- Kaouther Messaoud
- Fawzi Nashashibi
- Dinesh Manocha
- Itheri Yahiaoui
- Deva Ramanan
- Simon Lucey
Citations in the corpus
- A Survey on Trajectory-Prediction Methods for Autonomous Driving (2022, methodology): “Hyeon et al. [75] utilizes an encoder-decoder LSTM architecture.”
- Argoverse: 3D Tracking and Forecasting With Rich Maps (2019, methodology): “Prediction Algorithm : We implement Constant Velocity, Nearest Neighbor, and LSTM Encoder-Decoder based [46, 15, 56] models using different combinations of features.”
- Naturalistic Driver Intention and Path Prediction Using Recurrent Neural Networks (2018, background): “visual data of surrounding vehicles [12], radar data [13] or simulated Lidar returns of surround vehicles [14].”
- Attention Based Vehicle Trajectory Prediction (2020, methodology): “LSTM encoder decoder based architectures were deployed in [1], [6], [7], [31].”
- TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents (2018, methodology): “Some methods (Kim et al. 2017; Park et al. 2018; Lee et al. 2017) produce the probabilistic information about the future locations of vehicles over an occupancy grid map or samples by making use of an encoder-decoder structure.”
- Human motion trajectory prediction: a survey (2019, methodology): “2019), vehicle (Kim et al. 2017; Altché and de La Fortelle 2017; Park et al. 2018; Ding et al. 2019) and cyclist (Pool et al.”