CAFE-AD: Cross-Scenario Adaptive Feature Enhancement for Trajectory Planning in Autonomous Driving

2025-04-09

AI Summary

To address causal confounding and long-tailed scene distribution in imitation learning–based trajectory planning on the nuPlan dataset, this paper proposes a cross-scene adaptive feature enhancement framework. Methodologically, it introduces two novel components: (i) adaptive feature pruning, which dynamically selects discriminative representations via differentiable pruning guided by feature importance ranking; and (ii) cross-scene semantic interpolation, which injects semantic priors weighted by scene rarity to mitigate overfitting to dominant scenes and bias toward tail classes. Evaluated on the nuPlan Test14-Hard closed-loop benchmark, the framework significantly outperforms both rule-based and hybrid planners. Real-world vehicle validation further demonstrates substantial improvements in planning robustness and safety—particularly in complex, rare scenarios—validating its effectiveness in mitigating long-tail degradation and causal misalignment.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

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: Attacks and countermeasures in recommendation systems

Abstract

Imitation learning based planning tasks on the nuPlan dataset have gained great interest due to their potential to generate human-like driving behaviors. However, open-loop training on the nuPlan dataset tends to cause causal confusion during closed-loop testing, and the dataset also presents a long-tail distribution of scenarios. These issues introduce challenges for imitation learning. To tackle these problems, we introduce CAFE-AD, a Cross-Scenario Adaptive Feature Enhancement for Trajectory Planning in Autonomous Driving method, designed to enhance feature representation across various scenario types. We develop an adaptive feature pruning module that ranks feature importance to capture the most relevant information while reducing the interference of noisy information during training. Moreover, we propose a cross-scenario feature interpolation module that enhances scenario information to introduce diversity, enabling the network to alleviate over-fitting in dominant scenarios. We evaluate our method CAFE-AD on the challenging public nuPlan Test14-Hard closed-loop simulation benchmark. The results demonstrate that CAFE-AD outperforms state-of-the-art methods including rule-based and hybrid planners, and exhibits the potential in mitigating the impact of long-tail distribution within the dataset. Additionally, we further validate its effectiveness in real-world environments. The code and models will be made available at https://github.com/AlniyatRui/CAFE-AD.

Problem

• Address causal confusion in imitation learning for autonomous driving
• Mitigate long-tail scenario distribution challenges in trajectory planning
• Enhance cross-scenario feature representation for diverse driving conditions

Innovation

• Adaptive feature pruning for noise reduction
• Cross-scenario feature interpolation for diversity
• Enhanced feature representation across scenarios