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

arXiv: https://arxiv.org/abs/1508.03891 · HTML: https://mlsanity.com/paper/1508.03891/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2015.

## Built on by (most cited first, 10 of 10)

- [Reasoning with Scene Graphs for Robot Planning under Partial Observability](https://mlsanity.com/paper/2202.10432/) (2022)
- [Logic programming for deliberative robotic task planning](https://mlsanity.com/paper/2301.07550/) (2023)
- [Anticipate & Act : Integrating LLMs and Classical Planning for Efficient Task Execution in Household Environments](https://mlsanity.com/paper/2502.02066/) (2025)
- [Online inductive learning from answer sets for efficient reinforcement learning exploration](https://mlsanity.com/paper/2501.07445/) (2025)
- [Knowledge-Based Hierarchical POMDPs for Task Planning](https://mlsanity.com/paper/2103.10642/) (2021)
- [Abstracting Noisy Robot Programs](https://mlsanity.com/paper/2204.03536/) (2022)
- [Knowledge-based Reasoning and Learning under Partial Observability in Ad Hoc Teamwork](https://mlsanity.com/paper/2306.00790/) (2023)
- [Relevance Score: A Landmark-Like Heuristic for Planning](https://mlsanity.com/paper/2403.07510/) (2024)
- [Combining Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning in Robotics](https://mlsanity.com/paper/2201.10266/) (2022)
- [Knowledge-based and Data-driven Reasoning and Learning for Ad Hoc Teamwork](https://mlsanity.com/paper/2208.11556/) (2022)

## Abstract (arXiv)

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.