Dynamic path planning for autonomous driving on various roads with avoidance of static and moving obstacles
By Xuemin Hu, Long Chen, Bo Tang, Dongpu Cao, Haibo He. 2018
307 citations recorded by the source corpus.
Abstract This paper presents a real-time dynamic path planning method for autonomous driving that avoids both static and moving obstacles. The proposed path planning method determines not only an optimal path, but also the appropriate acceleration and speed for a vehicle. In this method, we first construct a center line from a set of predefined waypoints, which are usually obtained from a lane-level map. A series of path candidates are generated by the arc length and offset to the center line in the s - ρ coordinate system. Then, all of these candidates are converted into Cartesian coordinates. The optimal path is selected considering the total cost of static safety, comfortability, and dynamic safety; meanwhile, the appropriate acceleration and speed for the optimal path are also identified. Various types of roads, including single-lane roads and multi-lane roads with static and moving obstacles, are designed to test the proposed method. The simulation results demonstrate the effectiveness of the proposed method, and indicate its wide practical application to autonomous driving.
Subfields: Automotive Engineering, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/8325fc08f623d4d0e6af595208f338759c5ffe72
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 Computer Vision and Pattern Recognition
Citations in the corpus
- Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives (2023, methodology): “Typical methods include the Dubins/Reeds-Shepp curves [34], polynomials [25], and theoretical optimal control methods [35], [36].”
- A Motion Planning and Tracking Framework for Autonomous Vehicles Based on Artificial Potential Field Elaborated Resistance Network Approach (2020, background): “Generally, numerous studies, such as the geometry-based, grid-based, sampling-based, meta-heuristic-based, artificial potential field (APF)-based, and artificial intelligence (AI)-based methods are extensively used for path planning or motion planning [12].”