| Learning Homotopy Prediction for Optimization-Based Trajectory Planners for Autonomous Driving |
| Abi Rahman Syamil, Dongsuk Kum |
| Cho Chun Shik Graduate School of Mobility, KAIST, Daejeon 34051, Korea |
|
|
|
Received: November 4, 2024; Revised: March 11, 2025 Accepted: March 24, 2025. Published online: May 6, 2025. |
|
|
|
| ABSTRACT |
|
Towards the real-world deployment of autonomous vehicles, it is crucial that autonomous driving systems plan safe, collision-free trajectories. However, generating a collision-free trajectory around potential obstacles requires solving a non-convex problem for conventional optimization-based planners. This is characterized by multiple local minima reflecting possible maneuvers in different homotopies that the ego vehicle can execute to avoid collision. Finding a solution among these maneuvers involves combinatorial decision-making, which incurs increasing computational costs as more obstacles are considered. In this paper, we propose a hybrid approach using learning-based decision-making for optimization planning. Our learning-based decision-maker predicts homotopic boundary constraints for the optimization planner, effectively determining a maneuver for the ego vehicle without any combinatorial decision process. In addition, the homotopic bounds enable us to reformulate the non-convex optimization problem into a more tractable quadratic programming (QP) problem. We evaluate our approach in unsignalized intersection scenarios using a simulator, demonstrating that it achieves better driving performance than existing decision-making and planning methods in non-convex driving situations. |
| Key Words:
Autonomous driving · Predictive planning · Trajectory planning · Homotopy · Deep learning · Supervised learning |
|
Corresponding Author.
Dongsuk Kum , Email. 
Preview 
Full text via DOI 
Download Citation
Print
