发表机构
School of Informatics, University of Edinburgh; Department of Mechanical and Mechatronics Engineering, University of Waterloo（爱丁堡大学信息学院; 滑铁卢大学机械与机电工程系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对富含接触操作中姿态估计难题，提出BayesContact框架，通过融合视觉与触觉信息及基于模拟的推理来维护物体姿态信念，经模拟预测与真实观测对比更新信念，提升了姿态可观测性与插入成功率。
AI 中文摘要
富含接触的操作需要比仅深度感知提供的更准确的姿态估计。现有方法依赖视觉和接触，采用成本高昂的离线训练程序，且新环境和几何形状需重新训练。我们提出BayesContact，一种用于销孔插入中视觉触觉姿态估计的基于模拟的推理框架。它通过粒子信念维护物体姿态，融合深度观测与力/扭矩衍生的接触证据。利用基于模拟的前向模型近似观测似然性，通过渲染器预测深度测量值，物理模拟器预测受保护探测动作下的接触结果，并与真实观测进行评分以更新信念。生成的多模态信念还能实现基于信息增益的探测以进行主动消歧。在模拟几何形状和真实机器人实验中，BayesContact比仅视觉推理提高了30%的姿态可观测性和插入成功率。
英文摘要
Contact-rich manipulation requires pose estimates that are often more accurate than what depth-only sensing provides. Existing methods, relying on vision and contact, employ costly offline training procedures that need to be retrained for new environments and geometries. We propose BayesContact, a Simulation-Based Inference framework for visuo-tactile pose estimation in peg-in-hole insertion. BayesContact maintains a particle belief over object pose and fuses depth observations with force/torque-derived contact evidence. We employ simulation based forward models to approximate these observation likelihoods. For each pose hypothesis, a renderer predicts depth measurements and a physics simulator predicts contact outcomes under guarded probing actions; both are scored against real observations to update the belief. The resulting multimodal belief also enables information-gain-based probing for active disambiguation. Across simulated geometries and real-robot experiments, BayesContact improves pose observability and insertion success over vision-only inference by 30%
CommentsUpdate funding sources
