Laura Humphrey

Controller synthesis for autonomous systems interacting with human operators

We propose an approach to synthesize control protocols for autonomous systems that account for uncertainties and imperfections in interactions with human operators. As an illustrative example, we consider a scenario involving road network surveillance by an unmanned aerial vehicle (UAV) that is controlled remotely by a human operator but also has a certain degree of autonomy. Depending on the type (i.e., probabilistic and/or nondeterministic) of knowledge about the uncertainties and imperfections in the operator-autonomy interactions, we use abstractions based on Markov decision processes and augment these models to stochastic two-player games. Our approach enables the synthesis of operator-dependent optimal mission plans for the UAV, highlighting the effects of operator characteristics (e.g., workload, proficiency, and fatigue) on UAV mission performance; it can also provide informative feedback (e.g., Pareto curves showing the trade-offs between multiple mission objectives), potentially assisting the operator in decision-making.

Synthesis of Human-in-the-Loop Control Protocols for Autonomous Systems

We propose an approach to synthesize control protocols for autonomous systems that account for uncertainties and imperfections in interactions with human operators. As an illustrative example, we consider a scenario involving road network surveillance by an unmanned aerial vehicle (UAV) that is controlled remotely by a human operator but also has a certain degree of autonomy. Depending on the type (i.e., probabilistic and/or nondeterministic) of knowledge about the uncertainties and imperfections in the human-automation interactions, we use abstractions based on Markov decision processes and augment these models to stochastic two-player games. Our approach enables the synthesis of operator-dependent optimal mission plans for the UAV, highlighting the effects of operator characteristics (e.g., workload, proficiency, and fatigue) on UAV mission performance. It can also provide informative feedback (e.g., Pareto curves showing the tradeoffs between multiple mission objectives), potentially assisting the operator in decision-making. We demonstrate the applicability of our approach via a detailed UAV mission planning case study.

Automated UAV tasks for search and surveillance

There is growing interest in using unmanned aerial vehicles to assist in operations that require search and surveillance. However, a challenge remains in providing the right level of automation. Manual teleoperation and waypoint-based planning provide a great deal of flexibility but require significant human effort, whereas high levels of automation reduce the level of human effort but at the cost of flexibility and human judgement in uncertain and dynamic environments. Here, we seek to provide an intermediate level of automation through a set of parameterized tasks that implement common UAV search and surveillance patterns, taking into account low-level details such as dynamics of the UAV, geometry of the sensor footprint, and quality of the sensor imagery. We describe implementation of these tasks and discuss how they can be used by either human operators or by higher levels of automation to plan search and surveillance missions.

Human-interpretable diagnostic information for robotic planning systems

Advances in automation have the potential to reduce the workload required for human planning and execution of missions carried out by robotic systems such as unmanned aerial vehicles (UAVs). However, automation can also result in an increase in system complexity and a corresponding decrease in system transparency, which makes identifying and reasoning about errors in mission plans more difficult. To help explain errors in robotic planning systems, we define a notion of structured probabilistic counterexamples, which provide human-interpretable diagnostic information about requirements violations resulting from complex probabilistic robotic behavior. We propose an approach for generating such counterexamples using mixed integer linear programming and demonstrate the usefulness of our approach via a case study of UAV mission planning demonstrated in the AMASE multi-UAV simulator.

Synthesis of Admissible Shields

Shield synthesis is an approach to enforce a set of safety-critical properties of a reactive system at runtime. A shield monitors the system and corrects any erroneous output values instantaneously. The shield deviates from the given outputs as little as it can and recovers to hand back control to the system as soon as possible. This paper takes its inspiration from a case study on mission planning for unmanned aerial vehicles (UAVs) in which k-stabilizing shields, which guarantee recovery in a finite time, could not be constructed. We introduce the notion of admissible shields, which improves k-stabilizing shields in two ways: (1) whereas k-stabilizing shields take an adversarial view on the system, admissible shields take a collaborative view. That is, if there is no shield that guarantees recovery within k steps regardless of system behavior, the admissible shield will attempt to work with the system to recover as soon as possible. (2) Admissible shields can handle system failures during the recovery phase. In our experimental results we show that for UAVs, we can generate admissible shields, even when k-stabilizing shields do not exist.

Trust-based human-robot interaction for multi-robot symbolic motion planning

Symbolic motion planning for robots is the process of specifying and planning robot tasks in a discrete space, then carrying them out in a continuous space in a manner that preserves the discrete-level task specifications. Despite progress in symbolic motion planning, many challenges remain, including addressing scalability for multi-robot systems and improving solutions by incorporating human intelligence in an adaptive fashion. In this paper, we use local communication, observation, control protocols, and compositional reasoning approaches to decompose the planning problem to address scalability. To address solution quality and adaptability, we use a dynamic and computational trust model to aid this decomposition and to implement real-time switching between automated and human motion planning. A simulation is provided demonstrating the successful implementation of these methods.