Robotic force-based compliance control is a preferred approach to achieve high-precision assembly tasks. When the geometric features of assembly objects are asymmetric or irregular, reinforcement learning (RL) agents are gradually incorporated into the compliance controller to adapt to complex force-pose mapping which is hard to model analytically. Since force-pose mapping is strongly dependent on geometric features, a compliance controller is only optimal for current geometric features. To reduce the learning cost of assembly objects with different geometric features, this paper is devoted to answering how to reconfigure existing controllers for new assembly objects with different geometric features. In this paper, model-based parameters are first reconfigured based on the proposed Equivalent Theory of Compliance Law (ETCL). Then the RL agent is transferred based on the proposed Weighted Dimensional Policy Distillation (WDPD) method. The experiment results demonstrate that the control reconfiguration method costs less time and achieves better control performance, which confirms the validity of proposed methods.

Businesses and organizations worldwide spend a large amount of time scrutinizing their legal, IT, and data handling services on their efficacy to be data compliant. Data compliance in this tech-driven world is critical and any lapses in adhering to regulations cost companies their reputation and could lead to substantial fines. Conversational systems that collect data and AI automation require that businesses train their staff to manage and deal with data compliance laws in addition to the other services they offer. The General Data Protection Regulations (GDPR) by the European Union in 2018 has imposed every organization in any part of the world that handles personal data to ensure data compliance. Even if businesses are not directly affected by the GDPR, many countries and states have their own data compliance laws that come into force with regards to AI technologies and the information they collect.