mlsanityData to 14 Oct 2026

DTPP: Differentiable Joint Conditional Prediction and Cost Evaluation for Tree Policy Planning in Autonomous Driving

arXiv 2310.05885 ↗First posted 9 Oct 2023cs.ROcited by 46

On the map: End-to-end autonomous driving → Imitation-learning end-to-end planners

Abstract (arXiv)

Motion prediction and cost evaluation are vital components in the decision-making system of autonomous vehicles. However, existing methods often ignore the importance of cost learning and treat them as separate modules. In this study, we employ a tree-structured policy planner and propose a differentiable joint training framework for both ego-conditioned prediction and cost models, resulting in a direct improvement of the final planning performance. For conditional prediction, we introduce a query-centric Transformer model that performs efficient ego-conditioned motion prediction. For planning cost, we propose a learnable context-aware cost function with latent interaction features, facilitating differentiable joint learning. We validate our proposed approach using the real-world nuPlan dataset and its associated planning test platform. Our framework not only matches state-of-the-art planning methods but outperforms other learning-based methods in planning quality, while operating more efficiently in terms of runtime. We show that joint training delivers significantly better performance than separate training of the two modules. Additionally, we find that tree-structured policy planning outperforms the conventional single-stage planning approach.

Key facts. Cited by 46 papers in the map (data through 14 Oct 2026). Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving. Builds on 30 of its 38 references that are in the map. First posted on arXiv 9 Oct 2023.

Builds on

30 of 38 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving10 Mar
  2. 2023Learning Interaction-aware Motion Prediction Model for Decision-making in Autonomous Driving8 Feb
  3. 2022Conditional Predictive Behavior Planning with Inverse Reinforcement Learning for Human-like Autonomous Driving17 Dec
  4. 2022Differentiable Integrated Motion Prediction and Planning with Learnable Cost Function for Autonomous Driving21 Jul
  5. 2021Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients27 Sep

Other references · 25

  1. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 493
  2. 2020Learning Lane Graph Representations for Motion Forecastingcited by 382
  3. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 331
  4. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 298
  5. 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 280
  6. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 270
  7. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 242
  8. 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 213
  9. 2023MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Queryingcited by 140
  10. 2021LookOut: Diverse Multi-Future Prediction and Planning for Self-Drivingcited by 96
  11. 2020PiP: Planning-informed Trajectory Prediction for Autonomous Drivingcited by 80
  12. 2021Multi-modal Motion Prediction with Transformer-based Neural Network for Autonomous Drivingcited by 73
13 more
  1. 2021SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policiescited by 69
  2. 2021Identifying Driver Interactions via Conditional Behavior Predictioncited by 48
  3. 2020Driving Behavior Modeling using Naturalistic Human Driving Data with Inverse Reinforcement Learningcited by 46
  4. 2022DiffStack: A Differentiable and Modular Control Stack for Autonomous Vehiclescited by 37
  5. 2020Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning with Application to Autonomous Drivingcited by 34
  6. 2020MATS: An Interpretable Trajectory Forecasting Representation for Planning and Controlcited by 30
  7. 2023The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Reviewcited by 29
  8. 2023Tree-structured Policy Planning with Learned Behavior Modelscited by 24
  9. 2021Limitations and Improvements of the Intelligent Driver Model (IDM)cited by 17
  10. 2022Efficient Game-Theoretic Planning with Prediction Heuristic for Socially-Compliant Autonomous Drivingcited by 14
  11. 2022Interventional Behavior Prediction: Avoiding Overly Confident Anticipation in Interactive Predictioncited by 8
  12. 2020Planning on the fast lane: Learning to interact using attention mechanisms in path integral inverse reinforcement learningcited by 4
  13. 2020Expressing Diverse Human Driving Behavior with Probabilistic Rewards and Online Inferencecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 11; 2025: 23; 2026: 9.

46 papers.

Sort:

By area:

  1. 2024DRAMA: An Efficient End-to-end Motion Planner for Autonomous Driving with Mambacited by 87
  2. 2024Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-tuningcited by 42
  3. 2024Solving Motion Planning Tasks with a Scalable Generative Modelcited by 40
  4. 2024Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios?cited by 38
  5. 2024SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Predictioncited by 25
  6. 2024Generalizing Motion Planners with Mixture of Experts for Autonomous Drivingcited by 22
  7. 2025Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Drivingcited by 19
  8. 2023End-To-End Planning of Autonomous Driving in Industry and Academia: 2022-2023cited by 11
  9. 2024Planning with Adaptive World Models for Autonomous Drivingcited by 11
  10. 2023Categorical Traffic Transformer: Interpretable and Diverse Behavior Prediction with Tokenized Latentcited by 10
  11. 2025LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarioscited by 7
  12. 2025CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refinecited by 7
34 more
  1. 2025When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarkscited by 7
  2. 2025Fully Unified Motion Planning for End-to-End Autonomous Drivingcited by 6
  3. 2025VLMPlanner: Integrating Visual Language Models with Motion Planningcited by 6
  4. 2024Learning Online Belief Prediction for Efficient POMDP Planning in Autonomous Drivingcited by 5
  5. 2025Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and Perspectivescited by 5
  6. 2025Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planningcited by 5
  7. 2025AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Frameworkcited by 5
  8. 2026Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Drivingcited by 5
  9. 2023Predictive Control for Autonomous Driving with Uncertain, Multi-modal Predictionscited by 4
  10. 2024LoRD: Adapting Differentiable Driving Policies to Distribution Shiftscited by 4
  11. 2025CoPlanner: An Interactive Motion Planner with Contingency-Aware Diffusion for Autonomous Drivingcited by 4
  12. 2025Perfect Prediction or Plenty of Proposals? What Matters Most in Planning for Autonomous Drivingcited by 4
  13. 2025DAP: A Discrete-token Autoregressive Planner for Autonomous Drivingcited by 4
  14. 2025Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planningcited by 3
  15. 2025HYPE: Hybrid Planning with Ego Proposal-Conditioned Predictionscited by 3
  16. 2025MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous drivingcited by 3
  17. 2026ParkDiffusion++: Ego Intention Conditioned Joint Multi-Agent Trajectory Prediction for Automated Parking using Diffusion Modelscited by 3
  18. 2024Integrating Decision-Making Into Differentiable Optimization Guided Learning for End-to-End Planning of Autonomous Vehiclescited by 2
  19. 2025SafeCast: Risk-Responsive Motion Forecasting for Autonomous Vehiclescited by 2
  20. 2025From Static to Dynamic: a Survey of Topology-Aware Perception in Autonomous Drivingcited by 2
  21. 2026AutoWorld: Learning Multi-Agent Traffic Simulation with Self-Supervised World Modelscited by 2
  22. 2024LHPF: Look back the History and Plan for the Future in Autonomous Drivingcited by 1
  23. 2025CAFE-AD: Cross-Scenario Adaptive Feature Enhancement for Trajectory Planning in Autonomous Drivingcited by 1
  24. 2025VLM as Strategist: Adaptive Generation of Safety-critical Testing Scenarios via Guided Diffusioncited by 1
  25. 2025Driving is a Game: Combining Planning and Prediction with Bayesian Iterative Best Responsecited by 1
  26. 2026RAPiD: Reward-Guided Consistency Distillation of Diffusion Planners for Real-Time Autonomous Drivingcited by 1
  27. 2026TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scalecited by 1
  28. 2025Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictionscited by 0
  29. 2025Trajectory Entropy: Modeling Game State Stability from Multimodality Trajectory Predictioncited by 0
  30. 2025UniPlanner: A Unified Motion Planning Framework for Autonomous Vehicle Decision-Making Systems via Multi-Dataset Integrationcited by 0
  31. 2026Gradient-Based Data Valuation Improves Curriculum Learning for Game-Theoretic Motion Planningcited by 0
  32. 2026Hope for the Best, Prepare for the Worst: Occlusion-Aware Contingency Planning for Autonomous Vehiclescited by 0
  33. 2026Learning Reliable Parking Policies via Offline Reinforcement Learning with Quantized Action Representationscited by 0
  34. 2026INTERACT: Interactive Planning for Autonomous Driving via Anchor-Conditioned Prediction and Trust-Region Refinementcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Bridging Predictive Uncertainty and Safe Action: Sample-Conditioned Differentiable Planning for Autonomous Driving
  2. 2024PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Driving
  3. 2024Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving
  4. 2022Learning Interpretable, High-Performing Policies for Autonomous Driving
  5. 2024Hybrid-Prediction Integrated Planning for Autonomous Driving
  6. 2021Closing the Planning-Learning Loop with Application to Autonomous Driving
  7. 2026Beyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End Driving
  8. 2025TreeIRL: Safe Urban Driving with Tree Search and Inverse Reinforcement Learning