Latest 15 Papers - May 23, 2025

by ADMIN 32 views

Trajectory Prediction

Trajectory prediction is a crucial aspect of various applications, including autonomous driving, human-robot interaction, and infrastructure-to-everything (IoT) systems. In this section, we will explore the latest 15 papers related to trajectory prediction.

Title Date Comment
UPTor: Unified 3D Human Pose Dynamics and Trajectory Prediction for Human-Robot Interaction 2025-05-20
Proje...

Project page: https://nisarganc.github.io/UPTor-page/

Knowledge-Informed Multi-Agent Trajectory Prediction at Signalized Intersections for Infrastructure-to-Everything 2025-05-17
EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video 2025-05-16
MambaControl: Anatomy Graph-Enhanced Mamba ControlNet with Fourier Refinement for Diffusion-Based Disease Trajectory Prediction 2025-05-15
Quantum-Enhanced Parameter-Efficient Learning for Typhoon Trajectory Forecasting 2025-05-14
Open-Source LLM-Driven Federated Transformer for Predictive IoV Management 2025-05-13
Prepr...

Preprint version; submitted for academic peer review

UVTM: Universal Vehicle Trajectory Modeling with ST Feature Domain Generation 2025-05-13
SICNav-Diffusion: Safe and Interactive Crowd Navigation with Diffusion Trajectory Predictions 2025-05-12
AIS Data-Driven Maritime Monitoring Based on Transformer: A Comprehensive Review 2025-05-12
Towards Accurate State Estimation: Kalman Filter Incorporating Motion Dynamics for 3D Multi-Object Tracking 2025-05-12
Wavelet Policy: Imitation Policy Learning in Frequency Domain with Wavelet Transforms 2025-05-11
Beyond Patterns: Harnessing Causal Logic for Autonomous Driving Trajectory Prediction 2025-05-11
TPK: Trustworthy Trajectory Prediction Integrating Prior Knowledge For Interpretability and Kinematic Feasibility 2025-05-10
Accep...

Accepted in the 36th IEEE Intelligent Vehicles Symposium (IV 2025) for oral presentation

Boundary-Guided Trajectory Prediction for Road Aware and Physically Feasible Autonomous Driving 2025-05-10
Accep...

Accepted in the 36th IEEE Intelligent Vehicles Symposium (IV 2025)

Realistic Adversarial Attacks for Robustness Evaluation of Trajectory Prediction Models via Future State Perturbation 2025-05-09 20 pages, 3 figures

Motion Prediction

Motion prediction is a crucial aspect of various applications, including autonomous driving, human-robot interaction, and IoT systems. In this section, we will explore the latest 15 papers related to motion prediction.

Title Date Comment
An Empirical Bayes Analysis of Object Trajectory Representation Models 2025-05-21
UPTor: Unified 3D Human Pose Dynamics and Trajectory Prediction for Human-Robot Interaction 2025-05-20
Proje...

Project page: https://nisarganc.github.io/UPTor-page/

APEX: Empowering LLMs with Physics-Based Task Planning for Real-time Insight 2025-05-20
CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flow 2025-05-19
Multi-Resolution Haar Network: Enhancing human motion prediction via Haar transform 2025-05-19
Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions 2025-05-18
IEEE ...

IEEE International Conference on Robotics and Automation (ICRA) 2025

Patient-Specific Autoregressive Models for Organ Motion Prediction in Radiotherapy 2025-05-17
Deployable and Generalizable Motion Prediction: Taxonomy, Open Challenges and Future Directions 2025-05-14
Initi...<>Initial draft, 162 pages, 40 figures, 13 tables

Human Motion Prediction via Test-domain-aware Adaptation with Easily-available Human Motions Estimated from Videos 2025-05-13 5 pages, 4 figures
Closing the Loop: Motion Prediction Models beyond Open-Loop Benchmarks 2025-05-08
Dynamic Network Flow Optimization for Task Scheduling in PTZ Camera Surveillance Systems 2025-05-07
7 pag...

7 pages, 3 Figures, Accepted at AIRC 2025

Future-Oriented Navigation: Dynamic Obstacle Avoidance with One-Shot Energy-Based Multimodal Motion Prediction 2025-05-01
Submi...

Submitted to IEEE RA-L

BEVWorld: A Multimodal World Simulator for Autonomous Driving via Scene-Level BEV Latents 2025-04-30 10 pages
EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds 2025-04-29
Highly Accurate and Diverse Traffic Data: The DeepScenario Open 3D Dataset 2025-04-25

Conclusion

Q1: What is Trajectory Prediction?

Trajectory prediction is the process of predicting the future location and movement of an object or a person based on its past movements and other relevant factors.

Q2: What is Motion Prediction?

Motion prediction is a related concept to trajectory prediction, but it focuses on predicting the future movement of an object or a person based on its current state and other relevant factors.

Q3: What are the Applications of Trajectory Prediction and Motion Prediction?

Trajectory prediction and motion prediction have various applications in fields such as:

  • Autonomous driving
  • Human-robot interaction
  • IoT systems
  • Robotics
  • Computer vision
  • Machine learning

Q4: What are the Challenges in Trajectory Prediction and Motion Prediction?

Some of the challenges in trajectory prediction and motion prediction include:

  • Handling uncertainty and noise in data
  • Dealing with complex and dynamic environments
  • Predicting long-term behavior
  • Handling multiple objects and interactions
  • Ensuring robustness and reliability

Q5: What are the Current State-of-the-Art Methods in Trajectory Prediction and Motion Prediction?

Some of the current state-of-the-art methods in trajectory prediction and motion prediction include:

  • Deep learning-based methods
  • Graph-based methods
  • Physics-based methods
  • Hybrid methods

Q6: What are the Future Directions in Trajectory Prediction and Motion Prediction?

Some of the future directions in trajectory prediction and motion prediction include:

  • Developing more robust and reliable methods
  • Handling complex and dynamic environments
  • Predicting long-term behavior
  • Handling multiple objects and interactions
  • Integrating with other AI and machine learning techniques

Q7: What are the Open Challenges in Trajectory Prediction and Motion Prediction?

Some of the open challenges in trajectory prediction and motion prediction include:

  • Handling uncertainty and noise in data
  • Dealing with complex and dynamic environments
  • Predicting long-term behavior
  • Handling multiple objects and interactions
  • Ensuring robustness and reliability

Q8: What are the Real-World Applications of Trajectory Prediction and Motion Prediction?

Some of the real-world applications of trajectory prediction and motion prediction include:

  • Autonomous driving
  • Human-robot interaction
  • IoT systems
  • Robotics
  • Computer vision
  • Machine learning

Q9: What are the Key Players in the Field of Trajectory Prediction and Motion Prediction?

Some of the key players in the field of trajectory prediction and motion prediction include:

  • Research institutions
  • Companies
  • Academics
  • Industry experts

Q10: What are the Future Opportunities in Trajectory Prediction and Motion Prediction?

Some of the future opportunities in trajectory prediction and motion prediction include:

  • Developing more robust and reliable methods
  • Handling complex and dynamic environments
  • Predicting long-term behavior
  • Handling multiple objects and interactions
  • Integrating with other AI and machine learning techniques

Conclusion

In this article, we have provided answers to some of the frequently asked questions in the field of trajectory prediction and motion prediction. We have covered various aspects of these topics, including definitions, applications, challenges, current state-of-the-art methods, future directions, open challenges, real-world applications, key players, and future opportunities.