Tracing Back Error Sources to Explain and Mitigate Pose Estimation Failures
Robust estimation of object poses in robotic manipulation is often addressed using foundational general estimators, that aim to handle diverse error sources naively within a single model. Still, they struggle due to environmental uncertainties, while requiring long inference times and heavy computation. In contrast, we propose a modular, uncertainty-aware framework that attributes pose estimation errors to specific error sources and applies targeted mitigation strategies only when necessary. Instantiated with Iterative Closest Point (ICP) as a simple and lightweight pose estimator, we leverage our framework for real-world robotic grasping tasks. By decomposing pose estimation into failure detection, error attribution, and targeted recovery, we significantly improve the robustness of ICP and achieve competitive performance compared to foundation models, while relying on a substantially simpler and faster pose estimator.
Code (0)
등록된 구현이 없습니다.
Tasks
Robotic GraspingPose EstimationSimilar Papers 제목 키워드 기반
Comparing the efficiency of forward and backward contact tracing
Tracing potentially infected contacts of confirmed cases is important when fighting outbreaks of many infectious diseases. The COVID-19 pandemic has motivated researchers to examine how different contact tracing strategi…
Explainable Few-shot Knowledge Tracing
Knowledge tracing (KT), aiming to mine students' mastery of knowledge by their exercise records and predict their performance on future test questions, is a critical task in educational assessment. While researchers achi…
Knowledge TracingA Survey of Explainable Knowledge Tracing
With the long term accumulation of high quality educational data, artificial intelligence has shown excellent performance in knowledge tracing. However, due to the lack of interpretability and transparency of some algori…
Explainable artificial intelligenceKnowledge TracingSurveyExplainable Link Prediction for Privacy-Preserving Contact Tracing
Contact Tracing has been used to identify people who were in close proximity to those infected with SARS-Cov2 coronavirus. A number of digital contract tracing applications have been introduced to facilitate or complemen…
Link PredictionPredictionPrivacy PreservingGradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning
Predictions made by deep learning models are prone to data perturbations, adversarial attacks, and out-of-distribution inputs. To build a trusted AI system, it is therefore critical to accurately quantify the prediction …
Deep LearningUncertainty Quantification