MORPH-U: Multi-Objective Resilient Motion Planning for V2X-Enabled Autonomous Driving in High-Uncertainty Environments via Simulation
Learn how MORPH-U enables resilient motion planning for autonomous driving in high-uncertainty environments via simulation, and how to apply its principles to real-world scenarios
- Implement a closed-loop stack using CARLA to simulate and test motion planning algorithms
- Fuse LiDAR and V2X data to improve the accuracy and robustness of motion planning
- Apply multi-objective optimization techniques to balance competing goals such as safety, efficiency, and comfort in motion planning
- Test and evaluate the performance of MORPH-U in various high-uncertainty scenarios
- Integrate MORPH-U with low-level control systems to ensure seamless execution of planned motions
Autonomous driving engineers and researchers can benefit from this study to improve the robustness of their motion planning systems, while developers of V2X-enabled vehicles can apply the findings to enhance their products' safety and efficiency
💡 MORPH-U's ability to fuse LiDAR and V2X data and apply multi-objective optimization enables more robust and efficient motion planning in high-uncertainty environments
🚗💻 MORPH-U: a new approach to resilient motion planning for autonomous driving in high-uncertainty environments #autonomousdriving #V2X #motionplanning
Key Takeaways
Learn how MORPH-U enables resilient motion planning for autonomous driving in high-uncertainty environments via simulation, and how to apply its principles to real-world scenarios
Full Article
Abstract:
arXiv:2605.07370v1 Announce Type: cross Abstract: V2X can warn an autonomous vehicle about hazards beyond line-of-sight, but it also brings uncertainty: messages may be delayed, dropped, or even forged. Meanwhile, map knowledge may change during a trip, forcing the vehicle to replan under tight real-time budgets. This paper studies how to make motion planning and low-level control robust to such uncertain, event-driven updates. We present MORPH-U, a CARLA-based closed-loop stack that fuses LiDAR
DeepCamp AI