Boundary-Guided Trajectory Prediction for Road Aware and Physically Feasible Autonomous Driving
This work addresses the challenge of ensuring safe and robust trajectory predictions for autonomous vehicles, though it is incremental as it builds on existing methods with specific improvements in feasibility and generalization.
The paper tackles the problem of generating physically feasible and road-aware trajectory predictions for autonomous driving by proposing a constrained regression framework guided by permissible driving directions and boundaries, which reduces the off-road rate under adversarial attacks from 66% to 1% and improves final displacement error.
Accurate prediction of surrounding road users' trajectories is essential for safe and efficient autonomous driving. While deep learning models have improved performance, challenges remain in preventing off-road predictions and ensuring kinematic feasibility. Existing methods incorporate road-awareness modules and enforce kinematic constraints but lack plausibility guarantees and often introduce trade-offs in complexity and flexibility. This paper proposes a novel framework that formulates trajectory prediction as a constrained regression guided by permissible driving directions and their boundaries. Using the agent's current state and an HD map, our approach defines the valid boundaries and ensures on-road predictions by training the network to learn superimposed paths between left and right boundary polylines. To guarantee feasibility, the model predicts acceleration profiles that determine the vehicle's travel distance along these paths while adhering to kinematic constraints. We evaluate our approach on the Argoverse-2 dataset against the HPTR baseline. Our approach shows a slight decrease in benchmark metrics compared to HPTR but notably improves final displacement error and eliminates infeasible trajectories. Moreover, the proposed approach has superior generalization to less prevalent maneuvers and unseen out-of-distribution scenarios, reducing the off-road rate under adversarial attacks from 66% to just 1%. These results highlight the effectiveness of our approach in generating feasible and robust predictions.