mlsanityData to 7 Oct 2026

Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios?

arXiv 2404.07569 ↗First posted 11 Apr 2024cs.RO cs.AI cs.LGcited by 38

Not on the map. Why?

Cited by 26 in End-to-end autonomous driving, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Real-world autonomous driving systems must make safe decisions in the face of rare and diverse traffic scenarios. Current state-of-the-art planners are mostly evaluated on real-world datasets like nuScenes (open-loop) or nuPlan (closed-loop). In particular, nuPlan seems to be an expressive evaluation method since it is based on real-world data and closed-loop, yet it mostly covers basic driving scenarios. This makes it difficult to judge a planner's capabilities to generalize to rarely-seen situations. Therefore, we propose a novel closed-loop benchmark interPlan containing several edge cases and challenging driving scenarios. We assess existing state-of-the-art planners on our benchmark and show that neither rule-based nor learning-based planners can safely navigate the interPlan scenarios. A recently evolving direction is the usage of foundation models like large language models (LLM) to handle generalization. We evaluate an LLM-only planner and introduce a novel hybrid planner that combines an LLM-based behavior planner with a rule-based motion planner that achieves state-of-the-art performance on our benchmark.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 48 of its 58 references that are in the map. First posted on arXiv 11 Apr 2024.

Builds on

48 of 58 references.

References · 48

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  4. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  5. 2022Planning-oriented Autonomous Drivingcited by 1,068
  6. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 527
  7. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 485
  8. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  9. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 477
  10. 2023GPT-Driver: Learning to Drive with GPTcited by 344
  11. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  12. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baselinecited by 247
36 more
  1. 2021End-to-end Interpretable Neural Motion Plannercited by 240
  2. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 238
  3. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Drivingcited by 233
  4. 2023Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Drivingcited by 231
  5. 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 229
  6. 2022Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformercited by 211
  7. 2023LanguageMPC: Large Language Models as Decision Makers for Autonomous Drivingcited by 188
  8. 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 178
  9. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  10. 2023A Language Agent for Autonomous Drivingcited by 161
  11. 2023Drive Like a Human: Rethinking Autonomous Driving with Large Language Modelscited by 158
  12. 2023GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Drivingcited by 141
  13. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Priorcited by 136
  14. 2022Learning from All Vehiclescited by 135
  15. 2021AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehiclescited by 132
  16. 2021Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradientscited by 122
  17. 2022PlanT: Explainable Planning Transformers via Object-Level Representationscited by 105
  18. 2018Baidu Apollo EM Motion Plannercited by 99
  19. 2022KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradientscited by 95
  20. 2023Hidden Biases of End-to-End Driving Modelscited by 95
  21. 2023ReasonNet: End-to-End Driving with Temporal and Global Reasoningcited by 92
  22. 2023ADAPT: Action-aware Driving Caption Transformercited by 78
  23. 2020Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Methodcited by 74
  24. 2018Conditional Affordance Learning for Driving in Urban Environmentscited by 70
  25. 2018On Offline Evaluation of Vision-based Driving Modelscited by 62
  26. 2020Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluationcited by 54
  27. 2023DTPP: Differentiable Joint Conditional Prediction and Cost Evaluation for Tree Policy Planning in Autonomous Drivingcited by 46
  28. 2018Scenarios for Development, Test and Validation of Automated Vehiclescited by 45
  29. 2023From Prediction to Planning With Goal Conditioned Lane Graph Traversalscited by 45
  30. 2017Ontology based Scene Creation for the Development of Automated Vehiclescited by 40
  31. 2023Empowering Autonomous Driving with Large Language Models: A Safety Perspectivecited by 34
  32. 2023The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Reviewcited by 29
  33. 2023Rethinking Imitation-based Planner for Autonomous Drivingcited by 25
  34. 2021CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoningcited by 23
  35. 2023Large Trajectory Models are Scalable Motion Predictors and Plannerscited by 23
  36. 2021Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Modelscited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 13; 2026: 20.

38 papers.

Sort:

By area:

  1. 2024Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Drivingcited by 55
  2. 2025Centaur: Robust End-to-End Autonomous Driving with Test-Time Trainingcited by 41
  3. 2025BEVDriver: Leveraging BEV Maps in LLMs for Robust Closed-Loop Drivingcited by 26
  4. 2024CoMAL: Collaborative Multi-Agent Large Language Models for Mixed-Autonomy Trafficcited by 22
  5. 2024Generalizing Motion Planners with Mixture of Experts for Autonomous Drivingcited by 22
  6. 2025Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modelingcited by 22
  7. 2025Plan-R1: Safe and Feasible Trajectory Planning as Language Modelingcited by 19
  8. 2026Fail2Drive: Benchmarking Closed-Loop Driving Generalizationcited by 15
  9. 2025CoCMT: Communication-Efficient Cross-Modal Transformer for Collaborative Perceptioncited by 13
  10. 2025LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarioscited by 7
  11. 2025When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarkscited by 7
  12. 2025AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Frameworkcited by 5
26 more
  1. 2026Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Drivingcited by 5
  2. 2024LoRD: Adapting Differentiable Driving Policies to Distribution Shiftscited by 4
  3. 2025Perfect Prediction or Plenty of Proposals? What Matters Most in Planning for Autonomous Drivingcited by 4
  4. 2024A-BDD: Leveraging Data Augmentations for Safe Autonomous Driving in Adverse Weather and Lightingcited by 3
  5. 2025Generative AI for Autonomous Driving: A Reviewcited by 3
  6. 2025FlowDrive: moderated flow matching with data balancing for trajectory planningcited by 3
  7. 2026Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open Challengescited by 3
  8. 2026RAD-LAD: Rule and Language Grounded Autonomous Driving in Real-Timecited by 3
  9. 2026ChainFlow-VLA: Causal Flow Planning with Vision-Language Modelscited by 3
  10. 2025Pedestrian-Aware Motion Planning for Autonomous Driving in Complex Urban Scenarioscited by 2
  11. 2025Driving is a Game: Combining Planning and Prediction with Bayesian Iterative Best Responsecited by 1
  12. 2026ReflexDiffusion: Reflection-Enhanced Trajectory Planning for High-lateral-acceleration Scenarios in Autonomous Drivingcited by 1
  13. 2026RAPiD: Reward-Guided Consistency Distillation of Diffusion Planners for Real-Time Autonomous Drivingcited by 1
  14. 2026TaCarla: A comprehensive benchmarking dataset for end-to-end autonomous drivingcited by 1
  15. 2026Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAscited by 1
  16. 2026World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planningcited by 1
  17. 2026TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scalecited by 1
  18. 2026DiffuSearch: How Hybrid Trajectory Planning Benefits from Aligned Objectives in Diffusion and Action Spacecited by 1
  19. 2026Dash2Sim: Closed-Loop Driving Simulation from in-the-wild Dashcam Videoscited by 0
  20. 2026Is Your Trajectory Displacement Safe in Long-tail?cited by 0
  21. 2026SENSE-VAD: Sentient and Semantic Video Anomaly Detection for Autonomous Drivingcited by 0
  22. 2026Agent-driven Long-tail Simulation for Autonomous Drivingcited by 0
  23. 2026Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planningcited by 0
  24. 2026CoLT-Drive: Counterfactual Long-Tail Benchmarking and Knowledge-Preserving Adaptation for Driving Affordance Predictioncited by 0
  25. 2026INTERACT: Interactive Planning for Autonomous Driving via Anchor-Conditioned Prediction and Trust-Region Refinementcited by 0
  26. 2026A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platformcited by 0