Boundary-Guided Trajectory Prediction for Road Aware and Physically Feasible Autonomous Driving

TL;DR

This paper introduces a boundary-guided trajectory prediction framework for autonomous driving that ensures on-road, physically feasible predictions by leveraging map boundaries and kinematic constraints, improving robustness and reducing infeasible trajectories.

Contribution

The paper presents a novel constrained regression approach that incorporates boundary guidance and acceleration profiles to produce feasible, on-road trajectories in autonomous driving scenarios.

Findings

Reduces off-road prediction rate from 66% to 1% under adversarial attacks.

Improves final displacement error compared to baseline methods.

Ensures trajectory feasibility and better generalization to unseen scenarios.

Abstract

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.