Gaussian Processes (GPs) are powerful non-parametric Bayesian models for regression of scalar fields, formulated under the assumption that measurement locations are perfectly known and the corresponding field measurements have Gaussian noise. However, many real-world scalar field mapping applications rely on sensor-equipped mobile robots to collect field measurements, where imperfect localization introduces state uncertainty. Such discrepancies between the estimated and true measurement locations degrade GP mean and covariance estimates. To address this challenge, we propose a method for updating the GP models when improved estimates become available. Leveraging the differentiability of the kernel function, a second-order correction algorithm is developed using the precomputed Jacobians and Hessians of the GP mean and covariance functions for real-time refinement based on measurement location discrepancy data. Simulation results demonstrate improved prediction accuracy and computational efficiency compared to full model retraining.
Dual-Mode Synchronization Predictive Control of Robotic Manipulator
School of Mechanical and Electrical Engineering, Guangzhou University(广州大学机械与电气工程学院);School of Automation, Guangdong University of Technology(广东工业大学自动化学院)
GaussTwin: Unified Simulation and Correction with Gaussian Splatting for Robotic Digital Twins
Intelligent Autonomous Systems Lab, Technical University of Darmstadt(德累斯顿技术大学智能自主系统实验室);German Research Center for AI (DFKI), SAIROL(德国人工智能研究中心(DFKI)SAIROL);Robotics Institute Germany (RIG)(德国机器人研究所);NAVER LABS Europe(NAVER LABS欧洲)
FLARE: A Failure-Aware Framework for Autonomous Correction and Recovery in Visual-Language Robotic Manipulation
The Chinese University of Hong Kong(香港中文大学);Centre for Perceptual and Interactive Intelligence(感知与交互智能中心);Duke University(杜克大学);Sun Yat-sen University(中山大学);TengenX(天工科技);Tencent Robotics X(腾讯Robotics X实验室);Shenzhen Loop Area Institute(深圳河套学院);Guangdong Key Laboratory of Big Data Analysis and Processing(广东省大数据分析与处理重点实验室)
Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols
Beihang University(北京航空航天大学);Shanghai Innovation Institute(上海创新研究院);Southern University of Science and Technology(南方科技大学);Shanghai Jiao Tong University(上海交通大学)