# SafeShift: Safety-Informed Distribution Shifts for Robust Trajectory Prediction in Autonomous Driving

arXiv: https://arxiv.org/abs/2309.08889 · HTML: https://mlsanity.com/paper/2309.08889/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2023.

## Built on by (most cited first, 9 of 9)

- [CaDRE: Controllable and Diverse Generation of Safety-Critical Driving Scenarios using Real-World Trajectories](https://mlsanity.com/paper/2403.13208/) (2024)
- [SEAL: Towards Safe Autonomous Driving via Skill-Enabled Adversary Learning for Closed-Loop Scenario Generation](https://mlsanity.com/paper/2409.10320/) (2024)
- [Generating Out-Of-Distribution Scenarios Using Language Models](https://mlsanity.com/paper/2411.16554/) (2024)
- [Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen](https://mlsanity.com/paper/2505.21743/) (2025)
- [The Case for Negative Data: From Crash Reports to Counterfactuals for Reasonable Driving](https://mlsanity.com/paper/2509.18626/) (2025)
- [Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies](https://mlsanity.com/paper/2505.22829/) (2025)
- [Amelia: A Large Dataset and Benchmark for Airport Surface Movement Forecasting](https://mlsanity.com/paper/2407.21185/) (2024)
- [Forecasting the Past: Gradient-Based Distribution Shift Detection in Trajectory Prediction](https://mlsanity.com/paper/2604.12425/) (2026)
- [Collision Snapshot Guided Time-Reversed Safety-Critical Scenario Generation](https://mlsanity.com/paper/2609.06433/) (2026)

## Abstract (arXiv)

As autonomous driving technology matures, safety and robustness of its key components, including trajectory prediction, is vital. Though real-world datasets, such as Waymo Open Motion, provide realistic recorded scenarios for model development, they often lack truly safety-critical situations. Rather than utilizing unrealistic simulation or dangerous real-world testing, we instead propose a framework to characterize such datasets and find hidden safety-relevant scenarios within. Our approach expands the spectrum of safety-relevance, allowing us to study trajectory prediction models under a safety-informed, distribution shift setting. We contribute a generalized scenario characterization method, a novel scoring scheme to find subtly-avoided risky scenarios, and an evaluation of trajectory prediction models in this setting. We further contribute a remediation strategy, achieving a 10% average reduction in prediction collision rates. To facilitate future research, we release our code to the public: github.com/cmubig/SafeShift