REBA: A Refinement-Based Architecture for Knowledge Representation and Reasoning in Robotics
From MaRDI portal
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 non-deterministic 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.
Recommendations
- Representations for robot knowledge in the \textsc{KnowRob} framework
- Robots, Reasoning, and Reification
- scientific article; zbMATH DE number 4203775
- scientific article; zbMATH DE number 1390358
- scientific article; zbMATH DE number 3892616
- Knowledge Representation System for Robot-Based Automated Assembly
Cited in
(10)- What do you really want to do? Towards a theory of intentions for human-robot collaboration
- Representations for robot knowledge in the \textsc{KnowRob} framework
- REBA
- Evaluating robustness in a two layer simulated robot architecture
- Elaboration Tolerant Representation of Markov Decision Process via Decision-Theoretic Extension of Probabilistic Action Language +
- Bridging commonsense reasoning and probabilistic planning via a probabilistic action language
- Risk-aware shielding of partially observable Monte Carlo planning policies
- Inductive learning of robot task knowledge from raw data and online expert feedback
- Knowledge-based reasoning and learning under partial observability in ad hoc teamwork
- Logic-based subsumption architecture
This page was built for publication: REBA: A Refinement-Based Architecture for Knowledge Representation and Reasoning in Robotics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4968371)
