# Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning

arXiv: https://arxiv.org/abs/2607.07844 · HTML: https://mlsanity.com/paper/2607.07844/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving.
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 8 Jul 2026.

## Placed in

- End-to-end autonomous driving / [End-to-end system architecture](https://mlsanity.com/driving/end-to-end-system-architecture/)

## Builds on (most cited first, 30 of 31)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021)
- [A Survey of Deep Learning Techniques for Autonomous Driving](https://mlsanity.com/paper/1910.07738/) (2019)
- [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://mlsanity.com/paper/1904.08980/) (2019)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems](https://mlsanity.com/paper/1810.05642/) (2018)
- [Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving](https://mlsanity.com/paper/2406.03877/) (2024)
- [Parting with Misconceptions about Learning-based Vehicle Motion Planning](https://mlsanity.com/paper/2306.07962/) (2023)
- [INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps](https://mlsanity.com/paper/1910.03088/) (2019)
- [Pseudo-Simulation for Autonomous Driving](https://mlsanity.com/paper/2506.04218/) (2025)
- [Self-Driving Cars: A Survey](https://mlsanity.com/paper/1901.04407/) (2019)
- [Diffusion-Based Planning for Autonomous Driving with Flexible Guidance](https://mlsanity.com/paper/2501.15564/) (2025)
- [AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles](https://mlsanity.com/paper/2101.06549/) (2021)
- [PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Driving](https://mlsanity.com/paper/2404.14327/) (2024)
- [TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions](https://mlsanity.com/paper/1812.04767/) (2018)
- [SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles](https://mlsanity.com/paper/2206.09682/) (2022)
- [A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook](https://mlsanity.com/paper/2401.01454/) (2024)
- [WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios](https://mlsanity.com/paper/2510.26125/) (2025)
- [A Survey of Deep RL and IL for Autonomous Driving Policy Learning](https://mlsanity.com/paper/2101.01993/) (2021)
- [ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling](https://mlsanity.com/paper/2306.12241/) (2023)
- [CitySim: A Drone-Based Vehicle Trajectory Dataset for Safety Oriented Research and Digital Twins](https://mlsanity.com/paper/2208.11036/) (2022)
- [Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios?](https://mlsanity.com/paper/2404.07569/) (2024)
- [CaRL: Learning Scalable Planning Policies with Simple Rewards](https://mlsanity.com/paper/2504.17838/) (2025)
- [openDD: A Large-Scale Roundabout Drone Dataset](https://mlsanity.com/paper/2007.08463/) (2020)
- [Rethinking Imitation-based Planner for Autonomous Driving](https://mlsanity.com/paper/2309.10443/) (2023)
- [Highly Accurate and Diverse Traffic Data: The DeepScenario Open 3D Dataset](https://mlsanity.com/paper/2504.17371/) (2025)
- [When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks](https://mlsanity.com/paper/2510.14677/) (2025)
- [nuPlan-R: A Closed-Loop Planning Benchmark for Autonomous Driving via Reactive Multi-Agent Simulation](https://mlsanity.com/paper/2511.10403/) (2025)

## Abstract (arXiv)

While closed-loop motion planners trained on large-scale, object-level datasets, e.g., nuPlan, demonstrate strong in-distribution (ID) performance, their generalization to novel urban topologies and recovery mechanisms following execution perturbations remain under-explored. To address this, we present Shift & Drift, a novel dual-track benchmark designed to rigorously stress-test motion planners across two critical axes of distribution shift: (1) The Semantic Shift Track leverages a novel conversion pipeline that transforms the aerial, DeepScenario Open 3D dataset into the nuPlan simulation framework. This enables zero-shot evaluation of planners trained on North American and Singaporean data against 1,182 scenarios spanning four German cities and the US city of San Francisco featuring dense pedestrian-cyclist interactions. (2) The State-Distribution Drift Track injects stochastic perturbations into the ego vehicle's dynamics to quantify robustness against compounding execution errors. Based on this, we systematically evaluate the failure modes of diverse planning paradigms under semantic and state-distribution shifts. While imitation learning methods achieve high scores in ID benchmarks, they exhibit significant failures under semantic shift, particularly in pedestrian-dense environments, and suffer from persistent drift when subjected to temporally correlated actuation noise. In contrast, the evaluated reinforcement-learning-based planner demonstrates more graceful degradation, maintaining higher safety and progress metrics across both tracks. Our findings reveal an empirical trade-off between imitation fidelity and closed-loop resilience, providing the community with a rigorous benchmark to evaluate progress toward reliable deployment.