Arbitrary shape object trajectory planning method and system based on space-time joint A star
By combining the spatiotemporal A-Star algorithm and Hermite curve interpolation, the inefficiency of traditional path planning in complex shapes and dynamic environments is solved, achieving efficient and continuous trajectory planning, which is suitable for robot navigation in complex shapes and dynamic environments.
Patent Information
- Application Number
- CN202610450157.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-08
- Publication Date
- 2026-05-12
- Estimated Expiration
- 2046-04-08
AI Technical Summary
Traditional path planning algorithms are inefficient in handling complex shapes and dynamic environments. They cannot effectively handle non-convex polygonal contours or internal holes, and ignoring the time dimension leads to infeasible or overly conservative planning results. Collision detection computation is computationally expensive, making it difficult to process complex shapes in real time.
A trajectory planning method based on spatiotemporal joint A-satellite is adopted. A polygonal model of the robot is generated through parametric modeling, a four-dimensional state space is introduced, mask information is used for efficient collision detection, and Hermite curve interpolation is used to smooth the path and generate a continuous executable trajectory.
It improves the flexibility and efficiency of robot trajectory planning in complex environments, reduces sharp turns, improves tracking accuracy and energy efficiency, and is suitable for dynamic environments and multi-robot collaboration.