REBA: A Refinement-Based Architecture for Knowledge Representation and Reasoning in Robotics

Abstract

This paper describes an architecture for robots that combines the complementary strengths of probabilistic graphical models and declarative programming to represent and reason with logic-based and probabilistic descriptions of uncertainty and domain knowledge. An action language is extended to support non-boolean fluents and nondeterministic causal laws. This action language is used to describe tightly-coupled transition diagrams at two levels of granularity, with a fine-resolution transition diagram defined as a refinement of a coarse-resolution transition diagram of the domain. The coarse-resolution system description, and a history that includes (prioritized) defaults, are translated into an Answer Set Prolog (ASP) program. For any given goal, inference in the ASP program provides a plan of abstract actions. To implement each such abstract action, the robot automatically zooms to the part of the fine-resolution transition diagram relevant to this action. A probabilistic representation of the uncertainty in sensing and actuation is then included in this zoomed fine-resolution system description, and used to construct a partially observable Markov decision process (POMDP). The policy obtained by solving the POMDP is invoked repeatedly to implement the abstract action as a sequence of concrete actions, with the corresponding observations being recorded in the coarse-resolution history and used for subsequent reasoning. The architecture is evaluated in simulation and on a mobile robot moving objects in an indoor domain, to show that it supports reasoning with violation of defaults, noisy observations and unreliable actions, in complex domains. 1 We use the terms "robot" and "agent" interchangeably in this paper. 1 arXiv:1508.03891v4 [cs.RO] 21 Sep 2018 probability reason optimally (or near optimally) about the effects of numerically quantifiable uncertainty in sensing and action. There have been many attempts to combine the benefits of these two classes of systems, including work on joint (i.e., logic-based and probabilistic) representations of state and action, and algorithms for planning and decisionmaking in such formalisms. These approaches provide significant expressive power, but they also impose a significant computational burden. More efficient (and often approximate) reasoning algorithms for such unified probabilisticlogical paradigms are being developed. However, practical robot systems that combine abstract task-level planning with probabilistic reasoning, link, rather than unify, their logic-based and probabilistic representations, primarily because roboticists often need to trade expressivity or correctness guarantees for computational speed. Information close to the sensorimotor level is often represented probabilistically to quantitatively model and reason about the uncertainty in sensing and actuation, with the robot's beliefs including statements such as "the robotics book is on the shelf with probability 0.9". At the same time, logic-based systems are used to reason with (more) abstract commonsen...

Towards a Theory of Explanations for Human–Robot Collaboration

“…We also describe an implementation of this theory in an architecture that supports scalable reasoning. An initial version of this work appeared as a symposium paper [33].…”

Non-monotonic Logical Reasoning and Deep Learning for Explainable Visual Question Answering

“…For instance, recent work has demonstrated that ASP-based non-monotonic logical reasoning can be combined with: (i) probabilistic reasoning for reliable and efficient planning and diagnostics [41]; and (ii) relational reinforcement learning and active learning methods for interactively learning or revising commonsense domain knowledge based on input from sensors and humans [42]. A domain's description (i.e., the knowledge base) in ASP comprises a system description D and a history H. System description D comprises a sorted signature Σ and axioms.…”

“…As described in Section 3.2, the domain history is a record of observations (of fluents), the execution of actions, and the values of fluents in the initial state. Also, planning (similar to inference) is reduced to computing answer set(s) of the program Π(D, H) after including some helper axioms for computing a minimal sequence of actions; for examples, please see [13,41]. If the robot's knowledge of the domain is incomplete or incorrect, the computed plans may be suboptimal or incorrect.…”

What do you really want to do? Towards a Theory of Intentions for Human-Robot Collaboration

“…Action languages are formalisms that are used to model domain dynamics (i.e., action effects). We chose to use an extension to action language AL d [13], which we introduced in prior work to model non-Boolean fluents and non-deterministic causal laws [26], because it provides the desired expressive power for robotics domains. Also, we chose to translate our action language descriptions to programs in CR-Prolog [2], an extension of Answer Set Prolog (ASP) [14], because it supports non-monotonic logical reasoning with incomplete commonsense knowledge in dynamic domains, which is a key desired capability in robotics.…”

“…1 Furthermore, for the execution of each concrete action, we use existing algorithms that include probabilistic models of the uncertainty in perception and actuation. Our architecture builds on the complementary strengths of prior work on an architecture that used declarative programming to reason about intended actions to achieve a given goal [5], and an architecture that introduced step-wise refinement of tightly-coupled transition diagrams at two different resolutions to support non-monotonic logical reasoning and probabilistic reasoning for planning and diagnostics [26]. Prior work on the refinementbased architecture did not include a theory of intentions.…”