Explicability? legibility? predictability? transparency? privacy? security? the emerging landscape of interpretable agent behavior
There has been significant interest of late in generating behavior of agents that is
interpretable to the human (observer) in the loop. However, the work in this area has …
interpretable to the human (observer) in the loop. However, the work in this area has …
Reactivity and statefulness: Action-based sensors, plans, and necessary state
G McFassel, DA Shell - The International Journal of Robotics …, 2023 - journals.sagepub.com
Typically to a roboticist, a plan is the outcome of other work, a synthesized object that
realizes ends defined by some problem; plans qua plans are seldom treated as first-class …
realizes ends defined by some problem; plans qua plans are seldom treated as first-class …
Abstractions for computing all robotic sensors that suffice to solve a planning problem
Whether a robot can perform some specific task depends on several aspects, including the
robot's sensors and the plans it possesses. We are interested in search algorithms that treat …
robot's sensors and the plans it possesses. We are interested in search algorithms that treat …
Parameter Identification for Multirobot Systems Using Optimization-based Controllers
This paper considers the problem of parameter identification for a multirobot system. We
wish to understand how can an adversarial observer reverse-engineer the tasks being …
wish to understand how can an adversarial observer reverse-engineer the tasks being …
[PDF][PDF] Plans that remain private, even in hindsight
We study a model in which a robot executes a plan whilst being observed. The observer is
interested in learning about the robot and its environment, and processes a sequence of …
interested in learning about the robot and its environment, and processes a sequence of …