Multi-Domain Enhanced Map-Free Trajectory Prediction with Selective Attention
By: Wenyi Xiong, Jian Chen
Potential Business Impact:
Helps self-driving cars predict where others will go.
Trajectory prediction is crucial for the reliability and safety of autonomous driving systems, yet it remains a challenging task in complex interactive scenarios. Existing methods often struggle to efficiently extract valuable scene information from redundant data, thereby reducing computational efficiency and prediction accuracy, especially when dealing with intricate agent interactions. To address these challenges, we propose a novel map-free trajectory prediction algorithm that achieves trajectory prediction across the temporal, spatial, and frequency domains. Specifically, in temporal information processing, We utilize a Mixture of Experts (MoE) mechanism to adaptively select critical frequency components. Concurrently, we extract these components and integrate multi-scale temporal features. Subsequently, a selective attention module is proposed to filter out redundant information in both temporal sequences and spatial interactions. Finally, we design a multimodal decoder. Under the supervision of patch-level and point-level losses, we obtain reasonable trajectory results. Experiments on Nuscences datasets demonstrate the superiority of our algorithm, validating its effectiveness in handling complex interactive scenarios.
Similar Papers
Prediction-Driven Motion Planning: Route Integration Strategies in Attention-Based Prediction Models
Robotics
Helps self-driving cars plan safer routes.
Beyond Patterns: Harnessing Causal Logic for Autonomous Driving Trajectory Prediction
Artificial Intelligence
Helps self-driving cars predict where others go.
A Parameter-Efficient Mixture-of-Experts Framework for Cross-Modal Geo-Localization
CV and Pattern Recognition
Drones find places using words and pictures.