Checking that a robot does what it should while it runs, and what it does when it doesn’t. The formal side (temporal logic, timed and hybrid automata, shields) sits next to learned failure detectors for policies, and both meet the same problem: neither checks its own inputs.
Concepts
- Failure recovery: detection, recovery, and why most robots stop.
- Runtime monitoring: what a monitor can decide, and what it can’t promise.
- Safe control, filed under control.
- Robust estimation, filed under mapping and localisation.
Comparisons
Entities
Datasets, platforms, tools and groups that come up in this subfield: linear temporal logic, ROS. The entity index has the rest.
Open questions
- How long does a robot stay useful after its safety layer acts?
- Can a monitor know when its own inputs are uncertified, and say so?
- What should a monitor do when it fires on a teammate: warn, exclude, or ask a third robot?
Papers
| Paper | Year | Venue | Domain | Threads |
|---|---|---|---|---|
| Semantic DoS | 2026 | arXiv preprint 2026 | general | robustness |
| Intermittent faults in swarms | 2025 | arXiv 2025 | general | robustness |
| AAPD model | 2025 | Royal Society Open Science 2025 | land | robustness, long-term |
| SCAD | 2025 | IEEE S&P 2025 (listed as Oakland 2025 on the authors' site) | general | robustness |
| Range-based integrity monitoring | 2025 | IEEE Robotics and Automation Letters 2025 | air | robustness |
| ROS RV and field testing guidelines | 2024 | IEEE Transactions on Software Engineering 2024 | general | robustness |
| INVARLLM | 2024 | arXiv 2024 (v2, June 2025) | general | robustness |
| LLM-guided scene graph planning | 2023 | arXiv preprint | land | perception, robustness |
| Verified AI | 2022 | Communications of the ACM 65(7) | general | robustness |
| Resilient task allocation | 2021 | IEEE Robotics and Automation Letters 2021 | land, air | robustness |
| ROSMonitoring | 2020 | TAROS 2020 | general | robustness |
| Design vs data invariants | 2020 | International Journal of Critical Infrastructure Protection, vol. 28, 2020 | general | robustness |
| SOTER | 2019 | DSN 2019 | air | robustness |
| Formal methods for robots survey | 2019 | ACM Computing Surveys 52(5) | general | robustness |
| RoboChart | 2019 | Software and Systems Modeling 2019 | general | robustness |
| Shielded RL | 2018 | AAAI 2018 | general | robustness |
| CBF-QP | 2017 | IEEE Transactions on Automatic Control 2017 | land | robustness |
| Selective classification | 2017 | NeurIPS 2017 | general | robustness |
| Calibration | 2017 | ICML 2017 | general | robustness |
| Deep ensembles | 2017 | NeurIPS 2017 | general | robustness, perception |
| MCMAS | 2017 | International Journal on Software Tools for Technology Transfer 19(1) | general | robustness |
| Observability-aware trajectory optimisation | 2016 | arXiv preprint 2016 | air | robustness |
| Distributed attack detection (SSMP) | 2016 | ACM AsiaCCS 2016 | general | robustness |
| Shield synthesis | 2015 | TACAS 2015 | general | robustness |
| LTL3 | 2011 | ACM Transactions on Software Engineering and Methodology 20(4) | general | robustness |
| STL robustness | 2010 | FORMATS 2010 (LNCS 6246) | general | robustness |
| PRISM swarm verification | 2010 | ANTS 2010, Swarm Intelligence (LNCS 6234) | general | robustness |
| Brief account of RV | 2009 | Journal of Logic and Algebraic Programming 78(5) | general | robustness |
| Z3 | 2008 | TACAS 2008 (LNCS 4963) | general | robustness |
| Simplex | 2001 | IEEE Software 2001 | general | robustness |
| Hybrid automata | 1996 | LICS 1996 | general | robustness |
| Timed automata | 1994 | Theoretical Computer Science 126(2) | general | robustness |
| Temporal logic of programs | 1977 | FOCS 1977 | general | robustness, long-term |
| Paper | Year | Venue | Domain | Threads |
|---|---|---|---|---|
| Feel-WM | 2026 | arXiv preprint | land | long-term |
| MemoGuard | 2026 | IEEE Embedded Systems Letters (ESWEEK CODES 2026) | land | long-term, robustness |
| CP-Cert | 2026 | arXiv preprint | general | robustness |
| RIWM | 2026 | arXiv preprint (perspective) | general | long-term, robustness |
| FailBench | 2026 | arXiv preprint | general | robustness |
| Hide-and-Seek | 2026 | NeurIPS 2026 | general | robustness |
| No Free Checker | 2026 | arXiv preprint (survey) | general | robustness |
| Agentic Robot | 2025 | arXiv 2025 | land | robustness, long-term |
| SAFE | 2025 | NeurIPS 2025 | general | robustness |
| FAIL-Detect | 2025 | RSS 2025 | general | robustness |
| C-3PO | 2023 | IEEE Transactions on Robotics 2023 (first arXiv version 2022, titled "Correct and Certify") | general | robustness, perception |
Other subfields: perception, mapping and localisation, semantic mapping, planning and navigation, control, robot learning, multi-robot systems, security, Human-robot interaction, field robotics.