Extended Goal Recognition Design with First-Order Computation Tree Logic

Abstract

Goal recognition design (GRD) is the task of modifying environments for aiding observers to recognize the objectives of agents during online observations. The worst case distinctiveness (WCD), a widely used performance measure in GRD research, can fail to provide useful guidance to the redesign process when some goals are too hard to be distinguished. Moreover, the existing WCD-based approaches do not work when an agent aims for a sequence of goals instead of just one goal. The paper presents a new GRD framework called extended goal recognition design (EGRD) for goal recognition that involves multiple goals. The objective of EGRD is to modify an environment to minimize the worst case distinctiveness of a goal condition that describes how an agent can reach a set of goals. A goal condition can be formally expressed in first-order computation tree logic (FO-CTL) that can be evaluated by model checking. We introduce a novel graphical representation of FO-CTL sentences that is suitable for extended goal recognition. Moreover, we present a search algorithm for EGRD with a novel caching mechanism. Our experimental results show that the caching mechanism can greatly speed up our EGRD search algorithm by reusing the previous evaluation of FO-CTL sentences.

Block-Level Goal Recognition Design

“…Keren et al proposed using the WCD as a performance measure in GRD Karpas 2014, 2019). Subsequently, many works extended the WCDbased GRD model to deal with non-optimal agents (Keren, Gal, and Karpas 2015), non-observable actions (Keren, Gal, and Karpas 2016a), privacy preserving in GRD (Keren, Gal, and Karpas 2016b), stochastic domains (Wayllace et al 2016;Wayllace, Hou, and Yeoh 2017), game-theoretic GRD (Ang et al 2017), GRD for plan libraries (Mirsky et al 2019), partially-observable states (Wayllace et al 2020), incomplete information (Keren 2019), information shaping , stochastic domains with suboptimal agents (Wayllace and Yeoh 2022), interleaving between agents and observers (Gall, Ruml, and Keren 2021), and agents with multiple goals (Au 2022). (Keren, Gal, and Karpas 2020) is a survey of the works on GRD before 2020.…”

“…An assumption in GRD research is that an agent cannot move freely but follow a given set Π leg of legal plans whose paths can be either the shortest paths to some goals (Keren, Gal, and Karpas 2014), some feasible paths subject to physical constraints (Au 2022), or some paths in a path library (Mirsky et al 2019). Note that legal plans do not have to be optimal or near-optimal.…”