We present a two-stage framework that integrates a learning-based estimator and a controller, designed to address contact-intensive tasks. The estimator leverages a Bayesian particle filter with a mixture density network (MDN) structure, effectively handling multi-modal issues arising from contact information. The controller combines a self-supervised and reinforcement learning (RL) approach, strategically dividing the low-level admittance controller's parameters into labelable and non-labelable categories, which are then trained accordingly. To further enhance accuracy and generalization performance, a transformer model is incorporated into the self-supervised learning component. The proposed framework is evaluated on the bolting task using an accurate real-time simulator and successfully transferred to an experimental environment. More visualization results are available on our project website: https://sites.google.com/view/2stagecitt

翻译：我们提出了一个两阶段框架，该框架集成了基于学习的估计器和控制器，旨在解决接触密集任务。估计器利用贝叶斯粒子滤波器与混合密度网络（MDN）结构，有效处理由接触信息引起的多模态问题。控制器结合了自监督学习和强化学习（RL）方法，将低级导纳控制器的参数策略性地划分为可标注和不可标注类别，并据此进行训练。为进一步提升精度和泛化性能，在自监督学习组件中融入了Transformer模型。所提框架通过精确的实时模拟器在螺栓拧紧任务上进行了评估，并成功迁移至实验环境。更多可视化结果可在我们的项目网站获取：https://sites.google.com/view/2stagecitt