Pareto efficiency in synthesizing shared autonomy policies with temporal logic constraints
This work addresses the challenge of optimizing human-autonomy interaction in control systems, offering an incremental improvement in policy synthesis methods for shared autonomy.
The paper tackles the problem of balancing human operator workload and system performance in shared autonomy systems by proposing a two-stage policy synthesis algorithm that generates Pareto efficient coordination and control policies, achieving trade-offs with user-specified weights and using Tchebychev scalarization for better coverage of Pareto solutions.
In systems in which control authority is shared by an autonomous controller and a human operator, it is important to find solutions that achieve a desirable system performance with a reasonable workload for the human operator. We formulate a shared autonomy system capable of capturing the interaction and switching control between an autonomous controller and a human operator, as well as the evolution of the operator's cognitive state during control execution. To trade-off human's effort and the performance level, e.g., measured by the probability of satisfying the underlying temporal logic specification, a two-stage policy synthesis algorithm is proposed for generating Pareto efficient coordination and control policies with respect to user specified weights. We integrate the Tchebychev scalarization method for multi-objective optimization methods to obtain a better coverage of the set of Pareto efficient solutions than linear scalarization methods.