Motion Planning for Autonomous Driving with Real Traffic Data Validation

• Published in: Chinese journal of mechanical engineering Vol. 37; no. 1; pp. 6 - 13
• Main Authors: Chu, Wenbo, Yang, Kai, Li, Shen, Tang, Xiaolin
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 10.01.2024; Springer Nature B.V; SpringerOpen
• Edition: English ed.
• Subjects: Advanced Transportation Equipment; Algorithms; Autonomous vehicles; Civil engineering; Datasets; Deep learning; Electrical Machines and Networks; Electronics and Microelectronics; Engineering; Engineering Thermodynamics; Graph neural network; Graph neural networks; Heat and Mass Transfer; Instrumentation; INTERACTION dataset; Machine learning; Machines; Manufacturing; Mechanical Engineering; Motion planning; Neural networks; Optimization; Original Article; Pedestrians; Performance evaluation; Planning; Power Electronics; Prediction models; Predictive control; Processes; Roads; Roads & highways; Theoretical and Applied Mechanics; Traffic information; Trajectory prediction; Vehicle safety; Motion planning; Trajectory prediction; INTERACTION dataset; Graph neural network
• ISSN: 2192-8258; 1000-9345; 2192-8258
• DOI: 10.1186/s10033-023-00968-5

Accurate trajectory prediction of surrounding road users is the fundamental input for motion planning, which enables safe autonomous driving on public roads. In this paper, a safe motion planning approach is proposed based on the deep learning-based trajectory prediction method. To begin with, a trajectory prediction model is established based on the graph neural network (GNN) that is trained utilizing the INTERACTION dataset. Then, the validated trajectory prediction model is used to predict the future trajectories of surrounding road users, including pedestrians and vehicles. In addition, a GNN prediction model-enabled motion planner is developed based on the model predictive control technique. Furthermore, two driving scenarios are extracted from the INTERACTION dataset to validate and evaluate the effectiveness of the proposed motion planning approach, i.e . , merging and roundabout scenarios. The results demonstrate that the proposed method can lower the risk and improve driving safety compared with the baseline method.