Graph Convolution Networks for Probabilistic Modeling of Driving Acceleration

11/22/2019
by   Jianyu Su, et al.
0

The ability to model and predict ego-vehicle's surrounding traffic is crucial for autonomous pilots and intelligent driver-assistance systems. Acceleration prediction is important as one of the major components of traffic prediction. This paper proposes novel approaches to the acceleration prediction problem. By representing spatial relationships between vehicles with a graph model, we build a generalized acceleration prediction framework. This paper studies the effectiveness of proposed Graph Convolution Networks, which operate on graphs predicting the acceleration distribution for vehicles driving on highways. We further investigate prediction improvement through integrating of Recurrent Neural Networks to disentangle the temporal complexity inherent in the traffic data. Results from simulation studies using comprehensive performance metrics support the conclusion that our proposed networks outperform state-of-the-art methods in generating realistic trajectories over a prediction horizon.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/24/2022

Relation-based Motion Prediction using Traffic Scene Graphs

Representing relevant information of a traffic scene and understanding i...
research
02/25/2019

A Driving Intention Prediction Method Based on Hidden Markov Model for Autonomous Driving

In a mixed-traffic scenario where both autonomous vehicles and human-dri...
research
06/07/2017

Driver Action Prediction Using Deep (Bidirectional) Recurrent Neural Network

Advanced driver assistance systems (ADAS) can be significantly improved ...
research
06/02/2019

Longitudinal Trajectory Prediction of Human-driven Vehicles Near Traffic Lights

Predicting future trajectories of human-driven vehicles is a crucial pro...
research
02/02/2021

Vehicle trajectory prediction in top-view image sequences based on deep learning method

Annually, a large number of injuries and deaths around the world are rel...
research
09/11/2019

On-Demand Trajectory Predictions for Interaction Aware Highway Driving

Highway driving places significant demands on human drivers and autonomo...
research
03/26/2019

INFER: INtermediate representations for FuturE pRediction

In urban driving scenarios, forecasting future trajectories of surroundi...

Please sign up or login with your details

Forgot password? Click here to reset