TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents

By Yuexin Ma, Xinge Zhu, Sibo Zhang, Ruigang Yang, Wenping Wang, Dinesh Manocha. AAAI Conference on Artificial Intelligence, 2018

465 citations recorded by the source corpus.

To safely and efficiently navigate in complex urban traffic, autonomous vehicles must make responsible predictions in relation to surrounding traffic-agents (vehicles, bicycles, pedestrians, etc.). A challenging and critical task is to explore the movement patterns of different traffic-agents and predict their future trajectories accurately to help the autonomous vehicle make reasonable navigation decision. To solve this problem, we propose a long short-term memory-based (LSTM-based) realtime traffic prediction algorithm, TrafficPredict. Our approach uses an instance layer to learn instances’ movements and interactions and has a category layer to learn the similarities of instances belonging to the same type to refine the prediction. In order to evaluate its performance, we collected trajectory datasets in a large city consisting of varying conditions and traffic densities. The dataset includes many challenging scenarios where vehicles, bicycles, and pedestrians move among one another. We evaluate the performance of TrafficPredict on our new dataset and highlight its higher accuracy for trajectory prediction by comparing with prior prediction methods.

Subfields: Automotive Engineering, Building and Construction, Transportation

View Paper: https://www.semanticscholar.org/paper/f13f0bb31863b4968435dc063425ec7fdc5fc5e6

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 Transportation

Citations in the corpus

GRIP: Graph-based Interaction-aware Trajectory Prediction (2019, methodology): “the Appollo dataset [16], in which data is captured not only on a highway but also from”
Adapting Object Detectors via Selective Cross-Domain Alignment (2019, background): “Whereas several public benchmarks [6, 11, 30] have already existed, they can only cover a very limited range of scenarios.”
Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting (2023, methodology): “New sensor datasets for 3D object detection [4, 39, 34, 35, 21, 28, 16, 12, 36, 31] have led to influential detection methods such as anchor-based approaches like PointPillars [23], and more recent anchor-free approaches such as (1)This count includes private submissions not posted to the public lea”
SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction (2021, methodology): “TPHT [30] represents each pedestrian by an LSTM and employs a soft-attention mechanism [42] to model interactions between pedestrians.”
Argoverse: 3D Tracking and Forecasting With Rich Maps (2019, background): “TrafficPredict [26] also uses sensor-equipped vehicles to observe driving trajectories in the wild and build a forecasting benchmark.”
Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video (2020, background): “Examples of such applications include autonomous vehicles [1], human-robotic symbiotic systems [2], and wearable assistants [3], [4].”
One Thousand and One Hours: Self-driving Motion Prediction Dataset (2020, unknown): “nuScenes [11] 6h 1000 Rasterised 3D bounding Perception, road geometry boxes, trajectories Prediction ApolloScape Trajectory 2h 103 None Trajectories Prediction [12] Argoverse Forecasting 320h 324k Lane center lines, Trajectories Prediction v1.”
Multiple Futures Prediction (2019, background): “The success of machine learning and deep learning ushered in a variety of data-driven recurrent neural network (RNN) based methods [24, 7, 13, 26, 16, 2].”
A Survey on Trajectory Data Management, Analytics, and Learning (2020, background): “uery performance. Another promising topic can be the online deep trajectory learning to meet the demand for timely decision making over dynamic trajectory data. •Self-driving trajectory: Self-driving [30, 123] will be one of the primary sources of trajectories in the near future. Different from the ”
Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction (2020, background): “8) TrafficPredict [38]: LSTM-based motion predictor for heterogeneous traffic agents.”
Deep Learning-Based Vehicle Behavior Prediction for Autonomous Driving Applications: A Review (2020, methodology): “[32] A soft attention mechanism is used to”
Empowering Things With Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things (2020, background): “car [261], estimating the intention of cars and pedestrians and predicting their trajectories [244], [245].”
One Million Scenes for Autonomous Driving: ONCE Dataset (2021, methodology): “5 15k 80k No/No 3 ApolloScape [28] 20k 2 0 475k No/No 6 KAIST [11] 8.”