Reliable and Real-Time Highway Trajectory Planning via Hybrid Learning-Optimization Frameworks
By: Yujia Lu, Chong Wei, Lu Ma
Potential Business Impact:
Makes self-driving cars safely avoid crashes.
Autonomous highway driving presents a high collision risk due to fast-changing environments and limited reaction time, necessitating reliable and efficient trajectory planning. This paper proposes a hybrid trajectory planning framework that integrates the adaptability of learning-based methods with the formal safety guarantees of optimization-based approaches. The framework features a two-layer architecture: an upper layer employing a graph neural network (GNN) trained on real-world highway data to predict human-like longitudinal velocity profiles, and a lower layer utilizing path optimization formulated as a mixed-integer quadratic programming (MIQP) problem. The primary contribution is the lower-layer path optimization model, which introduces a linear approximation of discretized vehicle geometry to substantially reduce computational complexity, while enforcing strict spatiotemporal non-overlapping constraints to formally guarantee collision avoidance throughout the planning horizon. Experimental results demonstrate that the planner generates highly smooth, collision-free trajectories in complex real-world emergency scenarios, achieving success rates exceeding 97% with average planning times of 54 ms, thereby confirming real-time capability.
Similar Papers
Safe Autonomous Lane Changing: Planning with Dynamic Risk Fields and Time-Varying Convex Space Generation
Robotics
Makes self-driving cars change lanes safely and quickly.
A Risk-aware Spatial-temporal Trajectory Planning Framework for Autonomous Vehicles Using QP-MPC and Dynamic Hazard Fields
Robotics
Helps self-driving cars drive safer and smoother.
HyPlan: Hybrid Learning-Assisted Planning Under Uncertainty for Safe Autonomous Driving
Robotics
Helps self-driving cars avoid crashes faster.