Robot task planning and explanation in open and uncertain worlds

Abstract

A long-standing goal of AI is to enable robots to plan in the face of uncertain and incomplete information, and to handle task failure intelligently. This paper shows how to achieve this. There are two central ideas. The first idea is to organize the robot's knowledge into three layers: instance knowledge at the bottom, commonsense knowledge above that, and diagnostic knowledge on top. Knowledge in a layer above can be used to modify knowledge in the layer(s) below. The second idea is that the robot should represent not just how its actions change the world, but also what it knows or believes. There are two types of knowledge effects the robot's actions can have: epistemic effects (I believe X because I saw it) and assumptions (I'll assume X to be true). By combining the knowledge layers with the models of knowledge effects, we can simultaneously solve several problems in robotics: (i) task planning and execution under uncertainty; (ii) task planning and execution in open worlds; (iii) explaining task failure; (iv) verifying those explanations. The paper describes how the ideas are implemented in a three-layer architecture on a mobile robot platform. The robot implementation was evaluated in five different experiments on object search, mapping, and room categorization.

Planning Beyond The Sensing Horizon Using a Learned Context

“…Object-based approaches have also noted that the spatial relationships between objects are particularly beneficial for search (e.g., keyboards are often on desks) [6]- [8], but are not well-suited to represent geometries like floorplans/terrains. Hierarchical planners improve search performance via a human-like ability to make assumptions about object layouts [10], [11].…”

“…Therefore, this paper investigates the problem of efficiently planning beyond the robot's line-of-sight by utilizing context within the local vicinity. Existing approaches use context and background knowledge to infer a geometric understanding of the high-level goal's location, but the representation of background knowledge is either difficult to plan from [3]- [11], or maps directly from camera image to action [12]- [19], reducing transferability to real environments. This work proposes a solution to efficiently utilize context for planning.…”

Towards a science of integrated AI and Robotics

“…Finally, paper [15] describes an ambitious EU project that deals with representing knowledge (CA1) and reasoning with it (CA2) under strong uncertainty (RC1). The paper descibes an embedded robot platform along with a theory of how it can plan information gathering tasks and explain failure in environments that have uncertain sensing, uncertain actions, incomplete information and epistemic goals.…”

BWIBots: A platform for bridging the gap between AI and human–robot interaction research

“…For instance, Zhang, Sridharan and Wyatt (2015) combined ASP and POMDPs for integrating logical reasoning and probabilistic planning, but bridging the gap between answer sets (i.e., the reasoning results of ASP) and POMDP beliefs requires significant domain knowledge. Hanheide et al (2015) used a switching planner for deterministic and probabilistic planning and used commonsense knowledge for diagnostic tasks and generating explanations. In contrast, CORPP is an algorithm that integrates commonsense reasoning and probabilistic planning while exploiting their complementary features in a principled way.…”