Abstract
Decision-making in autonomous agents requires consideration of physical constraints, safety, uncertainty, learned experience, and mission objectives. Inspired by quantum cognition, this paper presents a hybrid quantum–classical architecture that organizes these aspects into four functions: physical reality, experience, machine conscience, and attention. Physical reality constrains the available actions, experience proposes suitable alternatives, machine conscience evaluates them against predefined safety and operational criteria, and attention selects the final action.
Classical checks enforce hard constraints and score soft preferences, while Grover circuits search for actions meeting rule-based thresholds. A conditional Quantum Circuit Born Machine (QCBM) provides learned action preferences. A classical hierarchy gives priority to emergencies, feasibility, risk, and uncertainty, then selects an eligible action using the integration score.
The QCBM is trained offline on 2147 examples from a 3060-example teacher-labelled dataset, with the remaining examples reserved for validation and testing.
On 466 held-out examples, the QCBM reproduced the teacher-defined preferred action with 83.26% accuracy. In repeated fixed-state replays, all constraint-aware policies had zero hard-constraint violations and full emergency-STOP compliance. The full hierarchy selected STOP less often than the hard-masked QCBM, with the same observed compliance. Finite-sampling experiments showed that higher shot counts reduced probability error and generally brought decisions closer to those obtained from the exact simulated probability distribution.
Overall, the results demonstrate that quantum generative learning and Grover-based quantum search can be integrated into a constraint-preserving decision architecture. The results establish functional integration under simulation rather than quantum advantage or physical robot performance. They also demonstrate how quantum technologies can support autonomous decision making and provide a basis for further research in quantum robotics.