SceneSelect: Selective Learning for Trajectory Scene Classification and Expert Scheduling

2026-04-27

AI Summary

This work addresses the challenges of poor generalization, low prediction accuracy, and computational redundancy in trajectory forecasting caused by the high heterogeneity of real-world scenes. To this end, the authors propose a scene-aware selective learning paradigm that leverages unsupervised clustering on geometric and kinematic features to construct a lightweight scene classification module. This module dynamically routes input data to the most suitable expert model, enabling decoupled, plug-and-play expert scheduling without requiring joint retraining for cross-dataset transfer. Evaluated on three major benchmarks—ETH-UCY, SDD, and NBA—the approach achieves an average performance gain of 10.5% over strong single-model and ensemble baselines, demonstrating its effectiveness and scalability.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Search and Optimization: Learning to Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Accurate trajectory prediction is fundamentally challenging due to high scene heterogeneity - the severe variance in motion velocity, spatial density, and interaction patterns across different real-world environments. However, most existing approaches typically train a single unified model, expecting a fixed-capacity architecture to generalize universally across all possible scenarios. This conventional model-centric paradigm is fundamentally flawed when confronting such extreme heterogeneity, inevitably leading to a severe generalization gap, degraded accuracy, and massive computational waste. To overcome this bottleneck, rather than refining restricted model-centric architectures, we propose selective learning, a novel scene-centric paradigm. It explicitly analyzes the characteristics of the underlying scene to dynamically route inputs to the most appropriate expert models. As a concrete implementation of this paradigm, we introduce SceneSelect. Specifically, SceneSelect utilizes unsupervised clustering on interpretable geometric and kinematic features to discover a latent scene taxonomy. A highly decoupled classification module is then trained to assign real-time inputs to these scene categories, and a highly extensible, plug-and-play scheduling policy automatically dispatches the trajectory sequence to the optimal expert predictor. Crucially, this decoupled design ensures excellent generalization capabilities, allowing seamless integration with different off-the-shelf models and robust adaptation across new datasets without requiring computationally expensive joint retraining. Extensive experiments on three public benchmarks (ETH-UCY, SDD, and NBA) demonstrate that our method consistently outperforms strong single-model and ensemble baselines, achieving an average improvement of 10.5%, showcasing the effectiveness of scene-aware selective learning.

Problem

• trajectory prediction
• scene heterogeneity
• model generalization
• computational efficiency
• scene classification

Innovation

• selective learning
• scene-centric paradigm
• expert scheduling
• unsupervised scene clustering
• decoupled classification