Specification Patterns for Robotic Missions
Not on the map. Why?
Abstract (arXiv)
Mobile and general-purpose robots increasingly support our everyday life, requiring dependable robotics control software. Creating such software mainly amounts to implementing their complex behaviors known as missions. Recognizing the need, a large number of domain-specific specification languages has been proposed. These, in addition to traditional logical languages, allow the use of formally specified missions for synthesis, verification, simulation, or guiding the implementation. For instance, the logical language LTL is commonly used by experts to specify missions, as an input for planners, which synthesize the behavior a robot should have. Unfortunately, domain-specific languages are usually tied to specific robot models, while logical languages such as LTL are difficult to use by non-experts. We present a catalog of 22 mission specification patterns for mobile robots, together with tooling for instantiating, composing, and compiling the patterns to create mission specifications. The patterns provide solutions for recurrent specification problems, each of which detailing the usage intent, known uses, relationships to other patterns, and---most importantly---a template mission specification in temporal logic. Our tooling produces specifications expressed in the LTL and CTL temporal logics to be used by planners, simulators, or model checkers. The patterns originate from 245 realistic textual mission requirements extracted from the robotics literature, and they are evaluated upon a total of 441 real-world mission requirements and 1251 mission specifications. Five of these reflect scenarios we defined with two well-known industrial partners developing human-size robots. We validated our patterns' correctness with simulators and two real robots.
Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Jan 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2019: 1; 2020: 0; 2021: 1; 2022: 0; 2023: 2; 2024: 4; 2025: 5; 2026: 3.
16 papers.
Sort:
By area:
- 2023Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agentscited by 69
- 2023Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environmentscited by 53
- 2024SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environmentscited by 18
- 2024Verifiably Following Complex Robot Instructions with Foundation Modelscited by 16
- 2019From explanation to synthesis: Compositional program induction for learning from demonstrationcited by 9
- 2024Neural Reward Machinescited by 7
- 2025Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Datacited by 5
- 2025Constrained Decoding for Safe Robot Navigation Foundation Modelscited by 5
- 2024Logically Constrained Robotics Transformers for Enhanced Perception-Action Planningcited by 4
- 2025Pretrained Embeddings as a Behavior Specification Mechanismcited by 3
- 2021Supervised Bayesian Specification Inference from Demonstrationscited by 1
- 2025Fully Learnable Neural Reward Machinescited by 1
4 more
- 2025INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violationscited by 0
- 2026DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applicationscited by 0
- 2026Towards an Agentic LLM-based Approach to Requirement Formalization from Unstructured Specificationscited by 0
- 2026Coherency through formalisations of Structured Natural Language, A case study on FRETishcited by 0
- 2026Coherency through formalisations of Structured Natural Language, A case study on FRETish11 May 2026
- 2026Towards an Agentic LLM-based Approach to Requirement Formalization from Unstructured Specifications20 Apr 2026
- 2026DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applications3 Feb 2026
- 2025Fully Learnable Neural Reward Machines23 Sep 2025
- 2025Constrained Decoding for Safe Robot Navigation Foundation Models1 Sep 2025
- 2025Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data14 Jul 2025
- 2025INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violations17 Mar 2025
- 2025Pretrained Embeddings as a Behavior Specification Mechanism3 Mar 2025
- 2024SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments3 Oct 2024
- 2024Neural Reward Machines16 Aug 2024
- 2024Logically Constrained Robotics Transformers for Enhanced Perception-Action Planning9 Aug 2024
- 2024Verifiably Following Complex Robot Instructions with Foundation Models18 Feb 2024
4 more
- 2023Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents18 Sep 2023
- 2023Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments22 Feb 2023
- 2021Supervised Bayesian Specification Inference from Demonstrations6 Jul 2021
- 2019From explanation to synthesis: Compositional program induction for learning from demonstration27 Feb 2019
- 2024Neural Reward Machinescited by 7
- 2025Fully Learnable Neural Reward Machinescited by 1
- 2025Fully Learnable Neural Reward Machines23 Sep 2025
- 2024Neural Reward Machines16 Aug 2024
- 2023Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environmentscited by 53
- 2024SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environmentscited by 18
- 2024Verifiably Following Complex Robot Instructions with Foundation Modelscited by 16
- 2025Constrained Decoding for Safe Robot Navigation Foundation Modelscited by 5
- 2024Logically Constrained Robotics Transformers for Enhanced Perception-Action Planningcited by 4
- 2025Pretrained Embeddings as a Behavior Specification Mechanismcited by 3
- 2021Supervised Bayesian Specification Inference from Demonstrationscited by 1
- 2025INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violationscited by 0
- 2026DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applicationscited by 0
- 2026Coherency through formalisations of Structured Natural Language, A case study on FRETishcited by 0
- 2026Coherency through formalisations of Structured Natural Language, A case study on FRETish11 May 2026
- 2026DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applications3 Feb 2026
- 2025Constrained Decoding for Safe Robot Navigation Foundation Models1 Sep 2025
- 2025INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violations17 Mar 2025
- 2025Pretrained Embeddings as a Behavior Specification Mechanism3 Mar 2025
- 2024SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments3 Oct 2024
- 2024Logically Constrained Robotics Transformers for Enhanced Perception-Action Planning9 Aug 2024
- 2024Verifiably Following Complex Robot Instructions with Foundation Models18 Feb 2024
- 2023Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments22 Feb 2023
- 2021Supervised Bayesian Specification Inference from Demonstrations6 Jul 2021