MORPH-U: Multi-Objective Resilient Motion Planning for V2X-Enabled Autonomous Driving in High-Uncertainty Environments via Simulation
For autonomous driving researchers and engineers, this work addresses the practical challenge of making motion planning robust to V2X communication uncertainties and map changes, but the approach is incremental—combining existing techniques (Hybrid-A*, LDM, Pareto optimization) with a simple Byzantine gate.
MORPH-U introduces a motion planning stack for V2X-enabled autonomous vehicles that handles uncertain V2X messages and dynamic map changes by fusing sensor data into a Local Dynamic Map, using Hybrid-A* replanning with multi-objective Pareto tuning, and adding a Byzantine-inspired gate to reject false hazard messages. Experiments show improved safety with V2X, controllable trade-offs via Pareto tuning, and full rejection of false DENM attacks at p_attack=1.0.
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/radar/camera with V2X (CAM/DENM) into a Local Dynamic Map (LDM) and triggers Hybrid-A* replanning when validated hazards or map changes affect the planned route. We expose the planning/control trade-offs via a multi-objective formulation over tracking error, safety margin (minimum TTC), responsiveness, and smoothness, and select operating points using Pareto-frontier analysis. To avoid unsafe replanning from faulty V2X triggers, MORPH-U adds a lightweight Byzantine-inspired acceptance gate that combines a quorum rule with an on-board sensor veto. Experiments in dynamic CARLA scenarios show that V2X-augmented LDM improves downstream safety, Pareto tuning provides controllable accuracy-comfort trade-offs, and the gate prevents replanning under saturated false-DENM injection ($p_{\text{attack}}=1.0$).