运动规划论文趋势 2023–2026

主要结论

• 运动规划论文从 2023 年的 34 篇增长到 2026 年的 83 篇，三年间扩大到约 2.4 倍。
• CVPR 是发运动规划论文最多的会议，2023–2026 年共 115 篇，占四个会议总量的 51%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 16 篇。
• 在「自动驾驶」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的占用预测是 2.3 倍，运动规划是 2.4 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026Coherence-Aware Transition-Intent Fusion for LTL Planning under Uncertain Semantic Maps
• ICML 2026Trajectory-Aware Heuristic Learning for Combinatorial Search
• ICLR 2026Efficient Differentiable Contact Model with Long-range Influence
• CVPR 2026EgoPoseFormer v2 Accurate Egocentric Human Motion Estimation for ARVR
• NeurIPS 2025Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planning
• ICML 2025Goal-Space Planning with Subgoal Models
• ICLR 20253DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
• CVPR 2025A Polarization-Aided Transformer for Image Deblurring via Motion Vector Decomposition
• NeurIPS 2024Text to Blind Motion
• ICML 2024Bringing Motion Taxonomies to Continuous Domains via GPLVM on Hyperbolic manifolds
• ICLR 2024Grounding Language Plans in Demonstrations Through Counterfactual Perturbations
• CVPR 2024DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning
• NeurIPS 2023Accelerating Motion Planning via Optimal Transport
• ICML 2023Motion Question Answering via Modular Motion Programs
• ICLR 2023Integrating Symmetry into Differentiable Planning with Steerable Convolutions
• CVPR 20233D-POP - An Automated Annotation Approach to Facilitate Markerless 2D-3D Tracking of Freely Moving Birds With Marker-Based Motion Capture
• NeurIPS 2026ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
• ICML 2026Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing
• ICLR 2026NeMo-map: Neural Implicit Flow Fields for Spatio-Temporal Motion Mapping
• CVPR 2026Event-based Motion Deblurring with Unpaired Data

全部运动规划论文

共 55 篇，第 1 / 2 页

1. NeurIPS 2026Beyond Expected Values: Risk-Sensitive Planning with Distributional Monte-Carlo Tree Search
2. NeurIPS 2026Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation
3. NeurIPS 2026Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
4. NeurIPS 2026Coherence-Aware Transition-Intent Fusion for LTL Planning under Uncertain Semantic Maps
5. NeurIPS 2026ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
6. NeurIPS 2026Corrupted Plans, Clean Traces: What Planning-Execution Decoupling Reveals About CoT Monitoring
7. NeurIPS 2026CycleSpectra: Cyclic Motion Spectra for Phase-Queryable 4D Cardiac Reconstruction
8. NeurIPS 2026DAGent: Evaluate-then-Grow Planning for Deep Research Agents
9. NeurIPS 2026DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising
10. NeurIPS 2026EgoHMP: Achieving Precise Human Motion Prediction in 3D Scenes via Egocentric Cues
11. NeurIPS 2026FacEDiT: Talking Head Video Editing via Facial Motion Infilling
12. NeurIPS 2026ForceBody: Force-Paired Parametric Body Motion with Torque Uncertainty
13. NeurIPS 2026Geometric Prompt-Trajectory Planning for Test-Time Scaling
14. NeurIPS 2026Implicit-Euler Value Iteration: Long-Horizon Planning via Stable Integration of the Bellman Residual Flow
15. NeurIPS 2026Learning Motion-Appearance Coupling Priors for Solving Video Inverse Problems
16. NeurIPS 2026Locating and Repairing Domain Shift in VLM Trajectory Planning
17. NeurIPS 2026MoCAR: Motion-code Coordinate-aware AutoRegression for Continuous Trajectory Forecasting
18. NeurIPS 2026Model-Based Online Decision Making via Generative Trajectory Planning
19. NeurIPS 2026Offline Inverse Reinforcement Learning with Unified Diffusion Planning
20. NeurIPS 2026OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion Reconstruction
21. NeurIPS 2026Ordinal Geometry Complements Reconstruction: Diagnosing Planning with Compressed Value Functions
22. NeurIPS 2026Point4D: Long-range 4D Motion Reconstruction
23. NeurIPS 2026Refining Compositional Diffusion for Reliable Long-Horizon Planning
24. NeurIPS 2026REINS: A Self-Evolving Agent Harness for Real-Time Trajectory Planning
25. NeurIPS 2026Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees
26. NeurIPS 2026Sparse Planning in Visual World Models via Cost Gradients
27. NeurIPS 2026Trajectory Planning without Trajectory Data: A Manifold-Guided Approach
28. NeurIPS 2026TrajLoc: Trajectory-Attention Localization for Multi-Object Motion Control
29. NeurIPS 2025\(\varepsilon\)-Optimally Solving Two-Player Zero-Sum POSGs
30. NeurIPS 2025Flow Equivariant Recurrent Neural Networks
31. NeurIPS 2025FlowFeat: Pixel-Dense Embedding of Motion Profiles
32. NeurIPS 2025HCRMP: An LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving
33. NeurIPS 2025Learning to Plan Like the Human Brain via Visuospatial Perception and Semantic-Episodic Synergistic Decision-Making
34. NeurIPS 2025MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts
35. NeurIPS 2025Object Concepts Emerge from Motion
36. NeurIPS 2025Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planning
37. NeurIPS 2025REDOUBT: Duo Safety Validation for Autonomous Vehicle Motion Planning
38. NeurIPS 2025RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers
39. NeurIPS 2025SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models
40. NeurIPS 2025UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning
41. NeurIPS 2024ALPINE: Unveiling The Planning Capability of Autoregressive Learning in Language Models
42. NeurIPS 2024In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before an Ongoing Trajectory Terminates
43. NeurIPS 2024Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference
44. NeurIPS 2024Learning Cooperative Trajectory Representations for Motion Forecasting
45. NeurIPS 2024Model-based Diffusion for Trajectory Optimization
46. NeurIPS 2024Revisiting motion information for RGB-Event tracking with MOT philosophy
47. NeurIPS 2024Text to Blind Motion
48. NeurIPS 2024The motion planning neural circuit in goal-directed navigation as Lie group operator search
49. NeurIPS 2024What type of inference is planning?
50. NeurIPS 2023Accelerating Motion Planning via Optimal Transport

常见问题

2023–2026 年四大会议一共有多少篇运动规划论文？

共 225 篇，按年份分别是 2023 年 34 篇、2024 年 53 篇、2025 年 55 篇、2026 年 83 篇。

NeurIPS 2026 有多少篇运动规划论文？

NeurIPS 2026 有 28 篇运动规划论文，上一届是 12 篇。

ICLR 2026 有多少篇运动规划论文？

ICLR 2026 有 8 篇运动规划论文，上一届是 11 篇。

ICML 2026 有多少篇运动规划论文？

ICML 2026 有 10 篇运动规划论文，上一届是 5 篇。

CVPR 2026 有多少篇运动规划论文？

CVPR 2026 有 37 篇运动规划论文，上一届是 27 篇。

哪个会议的运动规划论文最多？

CVPR，2023–2026 年共 115 篇。