用近似贝叶斯推断捕捉数据关联的多解分布，避免模糊场景下的错误匹配。
Distribution Estimation for Global Data Association via Approximate Bayesian Inference
- 将可能解表示为粒子，通过确定或随机更新规则覆盖多解模式。
- 在高度模糊的点云与物体地图配准中，准确估计变换分布。
- 支持优化约束并利用GPU并行加速，适合复杂多机器人环境应用。
全局数据关联是机器人在不同时刻或不同传感器环境下运行的基础。重复或对称的数据给现有方法带来挑战，这些方法通常依赖最大似然或最大共识来生成单一关联结果。但在模糊场景中，全局数据关联的解空间往往高度多模态，单解方法常失效。本文提出一种基于近似贝叶斯推断的数据关联框架，能捕捉解空间中的多个模式，避免在模糊情况下过早锁定单一解。方法将假设解表示为粒子，依据确定性或随机更新规则演化以覆盖解分布的各模式。此外，该方法可融入数据关联中的优化约束，并直接利用GPU并行优化加速。大量仿真与真实世界实验表明，该方法在高度模糊的数据下能正确估计点云或物体地图配准时的变换分布。
原文摘要 · Abstract (English)
Global data association is an essential prerequisite for robot operation in environments seen at different times or by different robots. Repetitive or symmetric data creates significant challenges for existing methods, which typically rely on maximum likelihood estimation or maximum consensus to produce a single set of associations. However, in ambiguous scenarios, the distribution of solutions to global data association problems is often highly multimodal, and such single-solution approaches frequently fail. In this work, we introduce a data association framework that leverages approximate Bayesian inference to capture multiple solution modes to the data association problem, thereby avoiding premature commitment to a single solution under ambiguity. Our approach represents hypothetical solutions as particles that evolve according to a deterministic or randomized update rule to cover the modes of the underlying solution distribution. Furthermore, we show that our method can incorporate optimization constraints imposed by the data association formulation and directly benefit from GPU-parallelized optimization. Extensive simulated and real-world experiments with highly ambiguous data show that our method correctly estimates the distribution over transformations when registering point clouds or object maps.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。