Planning for human-robot teaming in open worlds

Abstract

As the number of applications for human-robot teaming continue to rise, there is an increasing need for planning technologies that can guide robots in such teaming scenarios. In this article, we focus on adapting planning technology to Urban Search And Rescue (USAR) with a human-robot team. We start by showing that several aspects of state-of-the-art planning technology, including temporal planning, partial satisfaction planning, and replanning, can be gainfully adapted to this scenario. We then note that human-robot teaming also throws up an additional critical challenge, namely, enabling existing planners, which work under closed-world assumptions, to cope with the open worlds that are characteristic of teaming problems such as USAR. In response, we discuss the notion of conditional goals, and describe how we represent and handle a specific class of them called open world quantified goals. Finally, we describe how the planner, and its open world extensions, are integrated into a robot control architecture, and provide an empirical evaluation over USAR experimental runs to establish the effectiveness of the planning components.

Robot task planning and explanation in open and uncertain worlds

“…There are few integrated robot systems that combine domain-independent planning with domain-specific knowledge. Within that community, the need for a highlevel continual planning and execution monitoring subsystem is widely recognized [52,49,25,56]. The domainspecific knowledge in our approach is structured in three layers, as discussed in Section 1.…”

“…Open-world planning has also been tackled by Talamadupula et al [49], for a team of robots using the notion of open-world quantified goals, which specify rewards over open sets of objects. The planning approach is a replanning approach similar to the continual planning approach here, and objects are generated as effects of the sensing actions.…”

Automated Planning for Peer-to-peer Teaming and its Evaluation in Remote Human-Robot Interaction

“…While there are works that incorporate general planning capabilities into robots to achieve P2P teaming (e.g., [3]), as yet, there exists no empirical investigation of its influence on the teaming performance. In this study, we implement P2P teaming in which the human and robot are viewed as teammates, and the robot exhibits autonomy through automated planning capabilities.…”

“…Both the human subject and robot had access to the floor plan before the disaster. The robot in P2P teaming could use the planning capability (based on SapaReplan [3]) to independently create its own plan based on the floor plan and current status of the task. In both teaming scenarios, the robot displayed a list of applicable actions that it could perform given the current state.…”

A Short-Term Memory for Deliberative Agents in Everyday Environments

“…Talamadupula et al [26] propose open world quantified goals as a means to use standard AI planners in open worlds. In contrast, PDDLMemory supports open-world planning by modularizing goals.…”