Trajectory Prediction
Overview
Trajectory prediction estimates future paths from past motion and cues such as maps, goals, other agents, and environmental conditions. Common methods include Transformers, graph neural networks, and state-space models, alongside probabilistic approaches such as variational autoencoders, diffusion, and flow matching that represent multiple possible futures. Physics-based models, retrieval, and language or vision-language models are also used, especially when forecasts must support planning or work across domains. A central challenge is balancing accuracy and efficient inference with calibrated uncertainty, realistic and safe behavior, and reliable performance under distribution shifts; displacement benchmarks alone may not capture success in closed-loop settings.
Latest papers
191 papers10 papers in the last four weeks, down 50% on the four weeks before. 0.1% of all new papers.
LLaTSA: Large Language Model-Aligned General-Purpose Transient Stability Analysis
Enhancing Human Mobility Prediction with Spatially Aware LLM-based Multi-Agent Systems
Uncertainty-Aware Conflict Detection Against Operator-Conditioned Weather Hazards
What Next-Event Accuracy Cannot See: Closed-Loop Evaluation of Emergency Department Trajectory Simulators
Hi-FLoop: Hierarchical State-Feedback Loops for Multi-Timescale World Modeling
MamMA: A Mamba-Based Pedestrian Trajectory Prediction Algorithm Considering Occupancy Map and Pedestrian Awareness States
Residual Kalman Dynamics for Event-Based UAV Forecasting
Uncertainty-Aware Trajectory Forecasting from Imperfect Tracking
Safety-oriented pedestrian trajectory prediction at urban intersections using time-to-collision and crossing-zone context
Active Client Selection in Federated Trajectory Prediction with Uncertainty-Awareness and Heterogeneous Complexity
TRACE-CRC: Trajectory-Adaptive Conformal Risk Control for Multi-Step Channel State Information Prediction
DESCENT: Directed Edge Scene Encoding for Airport Surface Movement Prediction
SIREN-Bench: Behavior-Driven Generation and Evaluation of Emergency-Vehicle Interactions
Velocity-coupled Representation Refinement for Satellite Orbit Prediction
Fine-tuning LLMs for Tourist Trajectory Prediction using Field Experiment Data
Towards Surgical World-Action Modeling: A Preliminary Joint Visual-Trajectory Forecasting for Surgical Motion Planning
ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting
LE4Mob: Towards Inductive, Distance-Aware and General-Purpose Location Embedding for Human Mobility Modelling
DyGT: Modeling Object Dynamics with 3D Gaussian Temporal-Spatial Particle Graph Transformer
ControlledShifts: Towards Standardizing Robustness Evaluation in Trajectory Prediction Under Distribution Shifts
Unified Pedestrian Path Prediction Using Inverse Reinforcement Learning
Non-Parametric Spatiotemporal Trajectory Prediction via State-Conditioned Transition Sampling
AirForesight: Current-to-Future Spatial Map Imagination with Cross-Space Planning Consistency for UAV-VLN
Capturing Uncertainty in Human Motion for Representation Learning in Soccer
Towards Collaborative Joint Perception and Prediction: Framework, Baseline Evaluation, and Deployment Perspectives
SurgWMBench: A Vision-Based Benchmark for World-Modeling Surgical Instrument Motion Planning
A Unified Framework for Trajectory Prediction with Explicit Planning and Reaction Decomposition
Pivot-Centric Trajectory Prediction: Bridging Long Horizons via Dynamical Guidance
pivots'' and focusing on predicting pivot points along extended trajectories, we divide the long-term prediction task into short-term sub-tasks at various scales. Specifically, PCTP decouples the long-term trajectory predicting process into two processes: pivot prediction and pivot-based trajectory refinement. The pivot prediction process aims to utilize global map context and agent-to-agent interactions to identify these pivot points'', while the pivot-based trajectory refinement process focuses on local map details and refines the short-term trajectory based on predicted ``pivot points''. Compared with existing methods, PCTP provides more intermediate guidance while reducing compounding errors. Moreover, PCTP is a flexible approach that can be integrated into most state-of-the-art trajectory prediction models. Experimental results show that PCTP improves the prediction accuracy of leading models on both Argoverse I and Argoverse II datasets with minimal impact on model size. Specifically, PCTP combined with QCNet outperforms all published ensemble-free methods on the Argoverse II leaderboard at submission.