English

Differentiable Semantic Meta-Learning Framework for Long-Tail Motion Forecasting in Autonomous Driving

Computational Engineering, Finance, and Science 2025-11-11 v1

Abstract

Long-tail motion forecasting is a core challenge for autonomous driving, where rare yet safety-critical events-such as abrupt maneuvers and dense multi-agent interactions-dominate real-world risk. Existing approaches struggle in these scenarios because they rely on either non-interpretable clustering or model-dependent error heuristics, providing neither a differentiable notion of "tailness" nor a mechanism for rapid adaptation. We propose SAML, a Semantic-Aware Meta-Learning framework that introduces the first differentiable definition of tailness for motion forecasting. SAML quantifies motion rarity via semantically meaningful intrinsic (kinematic, geometric, temporal) and interactive (local and global risk) properties, which are fused by a Bayesian Tail Perceiver into a continuous, uncertainty-aware Tail Index. This Tail Index drives a meta-memory adaptation module that couples a dynamic prototype memory with an MAML-based cognitive set mechanism, enabling fast adaptation to rare or evolving patterns. Experiments on nuScenes, NGSIM, and HighD show that SAML achieves state-of-the-art overall accuracy and substantial gains on top 1-5% worst-case events, while maintaining high efficiency. Our findings highlight semantic meta-learning as a pathway toward robust and safety-critical motion forecasting.

Keywords

Cite

@article{arxiv.2511.06649,
  title  = {Differentiable Semantic Meta-Learning Framework for Long-Tail Motion Forecasting in Autonomous Driving},
  author = {Bin Rao and Chengyue Wang and Haicheng Liao and Qianfang Wang and Yanchen Guan and Jiaxun Zhang and Xingcheng Liu and Meixin Zhu and Kanye Ye Wang and Zhenning Li},
  journal= {arXiv preprint arXiv:2511.06649},
  year   = {2025}
}

Comments

Accepted at AAAI-26 (AAAI 2026), Main Track

R2 v1 2026-07-01T07:28:49.965Z