Negotiating Control: Neurosymbolic Variable Autonomy
Georgios Bakirtzis, Manolis Chiou, Andreas Theodorou
TL;DR
The paper addresses the challenge of dynamically balancing autonomy and human intervention for robust robotic planning under uncertainty. It introduces neurosymbolic variable autonomy, pairing a fast DRL optimizer with a slow rule-based metacontroller and a negotiation module to adapt level of autonomy in real time. Dynamic reward structure adjustment uses human data through CIRL, human preference learning, reward shaping, safe exploration, and transfer learning to calibrate autonomous behavior. Rule-based symbolic reasoning via modal and deontic logic interprets normative concepts and enforces socio-ethical norms, providing feedback to the learning controller. The framework aims to improve safety, transparency, and adaptability of autonomous systems operating in complex, real-world environments.
Abstract
Variable autonomy equips a system, such as a robot, with mixed initiatives such that it can adjust its independence level based on the task's complexity and the surrounding environment. Variable autonomy solves two main problems in robotic planning: the first is the problem of humans being unable to keep focus in monitoring and intervening during robotic tasks without appropriate human factor indicators, and the second is achieving mission success in unforeseen and uncertain environments in the face of static reward structures. An open problem in variable autonomy is developing robust methods to dynamically balance autonomy and human intervention in real-time, ensuring optimal performance and safety in unpredictable and evolving environments. We posit that addressing unpredictable and evolving environments through an addition of rule-based symbolic logic has the potential to make autonomy adjustments more contextually reliable and adding feedback to reinforcement learning through data from mixed-initiative control further increases efficacy and safety of autonomous behaviour.