paper-with-me

Papers

Uncertainty-Aware Data Aggregation for Deep Imitation Learning

2019-05-07 · Yuchen Cui, David Isele, Scott Niekum, Kikuo Fujimura

Estimating statistical uncertainties allows autonomous agents to communicate their confidence during task execution and is important for applications in safety-critical domains such as autonomous driving. In this work, we present the uncertainty-aware imitation learning (UAIL) algorithm for improving end-to-end control systems via data aggregation. UAIL applies Monte Carlo Dropout to estimate uncertainty in the control output of end-to-end systems, using states where it is uncertain to selectively acquire new training data. In contrast to prior data aggregation algorithms that force human experts to visit sub-optimal states at random, UAIL can anticipate its own mistakes and switch control to the expert in order to prevent visiting a series of sub-optimal states. Our experimental results from simulated driving tasks demonstrate that our proposed uncertainty estimation method can be leveraged to reliably predict infractions. Our analysis shows that UAIL outperforms existing data aggregation algorithms on a series of benchmark tasks.

📄 PDF Abstract BibTeX arXiv:1905.02780

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingImitation Learning

Methods 이 논문이 사용한 방법론

Monte Carlo Dropout 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Uncertainty-Based Methods for Automated Process Reward Data Construction and Output Aggregation in Mathematical Reasoning

2025-08-03 · Jiuzhou Han, Wray Buntine, Ehsan Shareghi arxiv

Large language models have demonstrated remarkable capabilities in complex mathematical reasoning tasks, but they inevitably generate errors throughout multi-step solutions. Process-level Reward Models (PRMs) have shown …

Mathematical Reasoning

Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models

2025-08-11 · Tianyi Zhou, Johanne Medina, Sanjay Chawla arxiv

Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation, which poses increasing risks in multi-turn or agentic applications where outputs may be reused as context. In thi…

GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting

2026-07-01 · Siwoo Lim, Sunjae Yoon, Gwanhyeong Koo, Chang D. Yoo arxiv

Gaussian Splatting has achieved significant improvements by incorporating warping-based techniques. However, such methods suffer from pixel-level inaccuracies due to uncertain geometry. This uncertainty leads to spatial …

Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance

2026-03-31 · Vanessa Emanuela Guarino, Claudia Winklmayr, Jannik Franzen, Josef Lorenz Rumberger 외 arxiv

Uncertainty Quantification (UQ) is crucial for ensuring the reliability of automated image segmentations in safety-critical domains like biomedical image analysis or autonomous driving. In segmentation, UQ generates pixe…

Autonomous Driving

Probabilistic Feature Imputation and Uncertainty-Aware Multimodal Federated Aggregation

2026-04-14 · Nafis Fuad Shahid, Maroof Ahmed, Md Akib Haider, Saidur Rahman Sagor 외 arxiv

Multimodal federated learning enables privacy-preserving collaborative model training across healthcare institutions. However, a fundamental challenge arises from modality heterogeneity: many clinical sites possess only …

Federated Learning