trajectory distribution evaluation

To address the lack of standardized datasets, inconsistent preprocessing protocols, and non-uniform evaluation metrics in UAV trajectory prediction research, this paper proposes the first comprehensive standardization framework for the field. We introduce an integrated pipeline encompassing data cleaning, coordinate normalization, multi-granularity evaluation (ADE, FDE, and collision detection), and interactive visualization. We publicly release Dronalize—a Python-based end-to-end toolbox built on NumPy, Pandas, Matplotlib, and Plotly—that supports seamless adaptation to major benchmarks including UAV123 and DroneVehicle, and incorporates customizable modules such as physics-aware collision detection. Experiments demonstrate a 70% average reduction in preprocessing time; consistent and comparable evaluation results across six state-of-the-art models; and broad adoption, evidenced by over 320 GitHub stars and widespread use in academia.

该论文提出一种不确定性感知的轨迹预测方法，通过利用跟踪器提供的可靠性线索，改进了在不完美多目标跟踪下的轨迹预测准确性。

This work addresses the challenge in trajectory prediction where existing methods often tailor training objectives to specific evaluation metrics, leading to optimization conflicts and suboptimal performance across multiple metrics. To overcome this limitation, the authors propose a metric-agnostic prediction paradigm: first, a probabilistic prediction model based on the DONUT architecture—termed DONUT-NLL—is trained using negative log-likelihood (NLL) to learn a unified trajectory distribution; then, during inference, a newly introduced TraDiE strategy adaptively maps this distribution to generate K optimal trajectories along with their confidence scores, tailored to any given evaluation metric. By decoupling training from evaluation, the method achieves state-of-the-art performance across all metrics on the Waymo Motion Prediction Benchmark, significantly enhancing both generalizability and practical utility.

This work addresses mobile trajectory prediction under state-dependent, set-valued measurement uncertainty. Method: We propose an estimation-aware trajectory optimization framework that integrates set-valued analysis, local linearization modeling, and a machine learning (ML)-driven visual estimation module. Its core innovation is the first formulation of a concave observability metric based on output-regular set-valued mappings—capable of characterizing non-Gaussian, state-dependent set uncertainties—and embedding this metric directly into nonlinear trajectory optimization. Results: Evaluated on cooperative-free satellite tracking, the optimized trajectories significantly improve both localization accuracy and robustness of the ML-based estimator, thereby enabling reliable perception–control closed-loop operation in realistic scenarios.

Existing trajectory prediction methods for autonomous driving inadequately model uncertainty, particularly lacking interpretable decomposition into aleatoric (environmental stochasticity) and epistemic (model uncertainty) components. Method: We propose the first information-theoretic unified framework that quantifies total uncertainty via entropy and mutual information, and decouples aleatoric and epistemic uncertainties through Bayesian approximate inference. The framework is plug-and-play compatible with mainstream predictors, balancing theoretical rigor and engineering practicality. Contribution/Results: Extensive empirical analysis across multiple architectures on nuScenes reveals critical impacts of model architecture on uncertainty estimation bias and planning robustness. Experiments demonstrate significant improvements in high-risk scenario identification, enabling safety-critical decision-making with reliable, uncertainty-aware predictions.

This work addresses a critical limitation in existing methods for evaluating uncertainty in language agents, which conflate ranking utility with probabilistic fidelity and fail to accurately capture the trajectory of success probabilities under prefix conditions. Drawing on preordered proper scoring theory, the paper introduces Trajectory Proper Scoring (TPS)—the first family of strictly proper scoring rules applicable to both complete and truncated trajectories—that rigorously incentivizes language models to emit stepwise uncertainty estimates aligned with their true success probabilities. By integrating preordered proper scoring, trajectory-level rule design, truncation handling, and projection-based approximation, TPS demonstrates markedly higher sensitivity to calibration shifts than conventional metrics across StrategyQA, Tau2-Bench, HotpotQA, and WebShop. Notably, truncation-aware approximations can substantially alter evaluation outcomes, revealing that current approaches capture only weak proxies of true calibration.

本文综述了时间序列和时空数据的概率预测方法，通过统一视角组织不同引入不确定性的预测手段，对比分析了多种模型的有效性和效率。

This work addresses the issue in trajectory prediction where Winner-Take-All (WTA) training yields uninformative posterior probabilities over modes, hindering effective mode pruning. The study identifies hard assignment in WTA as the root cause of mode oversplitting and instability, and unifies existing approaches under a Gaussian Mixture Model (GMM) framework. To rectify mode probabilities without retraining, the authors propose two lightweight post-processing strategies: test-time posterior-weighted fusion and a single-step EM-based soft responsibility update. Evaluated across multiple WTA-based architectures, these methods significantly enhance the informativeness of posterior probabilities, improve mode ranking accuracy, and boost overall prediction performance.

Existing influence estimation methods for trajectory-based data attribution lack systematic error analysis, limiting their reliability in data selection, valuation, and model diagnostics. This work identifies optimizer mismatch—specifically with AdamW—as a critical source of error and introduces AdamW-influence to address it. We derive a closed-form proxy for influence that avoids costly retraining and propose a K-step lookahead framework that unifies offline and online data selection strategies. Experiments across MLPs, CNNs, GPT-2, and Llama 3.2-1B demonstrate that our approach improves attribution accuracy by 10% to 300%, with online short-horizon selection matching or even surpassing the performance of offline methods.

为了解决现有规划器在决策边界附近监督信息有限的问题，本文设计了一种新的训练数据集，并使用基于Transformer的评分器进行训练，提高了驾驶策略性能。