Scenario-based testing
Autonomous systems are tested in simulation and on test tracks across catalogues of scenarios, including rare and hazardous situations, before field operation.
GCRI · Artificial Intelligence and Autonomous Systems
Robotics and autonomy
Robotics and automation bring AI into physical systems. In this field it covers the perception, control, safety engineering and human-robot interaction of robots, drones and automated vehicles, and how their safety is demonstrated.
01Contents
Robotics and autonomy in five parts.
02Application
What robotics and automation does here.
Robotics and automation design machines that sense, decide and act in physical environments. They are used in manufacturing, logistics, inspection and disaster response, and change patterns of operational risk and labour. In artificial intelligence and data and compute, automation can reduce human exposure to hazardous tasks and speed recovery operations. It also concentrates dependence on software, sensors and supply chains. The canonical description is on the STEM Commons.
Collaborative robot safety
Force, speed and separation limits for robots working near people are set and verified against safety standards.
Operating domain monitoring
Systems are instrumented to detect when they leave their design domain and to trigger a safe fallback.
03Monitor
Verification and test.
The screen a team would use to follow this method: its measures, states and decisions. Names are examples and values are illustrative.
Verification and test
AI and autonomous systems · Robotics and autonomy · Run R-3104
Test campaignGCRI · Artificial Intelligence and Autonomous Systems
Requirements coverage
| REQ-01 safe stop | 21 | 31 | Covered |
| REQ-07 fault detection | 6 | 9 | Gaps |
| REQ-12 timing | 12 | 20 | Covered |
Method card
- Method
- Robotics and automation
- Standard
- traceability matrix
- Reviewer
- independent
- Label
- MODELLED
Findings by severity
04Data
What the method consumes.
Datasets and records used by robotics and automation on this platform, with the role each plays and the label its values carry. Sources are listed in the source register.
| Data | Role | Label |
|---|---|---|
| Simulation scenario libraries | Test coverage | MODELLED |
| Field logs | Operational behaviour | OBSERVED |
| Incident reports | Failures | REPORTED |
05Methods and evidence
How robotics and autonomy is modelled, measured and tested.
The model, its assumptions, its data and its uncertainty, in the form a scientist or engineer would check. Structures follow published methods. The values drawn are illustrative, not findings.
Model, equations and assumptions
The model structure used for robotics and autonomy, the assumptions it makes and how each is tested.
Risk of element i
Ri = f(Hi, Ei, Vi, Ci)hazard, exposure, vulnerability and coping capacityExpected annual loss
EAL = ∑k pk · Lkover events k with annual probability pkCoupled systems
xt+1 = A xt + B ut + εtA carries the couplings, u the shock, ε the error| Assumption | Why it is made | How it is tested |
|---|---|---|
| Hazard and exposure are independent within an event | Keeps the loss integral tractable | Compare with a copula fit on joint records |
| Couplings are linear near the operating point | Lets shocks propagate through A | Perturb beyond the linear range and compare |
| Vulnerability curves transfer between places | Local curves are rarely available | Validate against observed losses where they exist |
- Inputs
- versioned datasets with provenance
- Outputs
- distributions, never single numbers
- Code
- released with the model card and tests
- Reproduction
- same data, code, environment and seed
FAIR guiding principles · GO FAIR and FORCE11W3C PROV · World Wide Web ConsortiumGuidance on consistent treatment of uncertainties · IPCCCEOS Analysis Ready Data · Committee on Earth Observation Satellites
06Validation
How results are checked.
Systems are validated through simulation, staged field trials and conformance to functional safety standards. Operational monitoring checks performance after deployment.
| Check | How it is done |
|---|---|
| Scenario coverage | Test catalogues are reviewed for coverage of the design domain |
| Simulation validity | Simulators are validated against real-world tests |
| Standards conformity | Safety functions are verified against applicable standards |
Robots may behave unpredictably in unstructured environments not covered by testing. Interaction with people raises safety and liability questions.
07Process
How the process runs.
Process
Robotics and autonomy: Risk management process
ISO 31000:2018 sets out an iterative risk management process, from scope, context and criteria through assessment and treatment to monitoring, review and reporting.
01 Frame
- 01Scope, context and criteriaDataset · Evaluation leadThe frame for the process: the scope, the external and internal context, and the risk criteria. Later steps are read against this frame.
02 Risk assessment
- 04Risk identificationStep · Evaluation leadThe first part of risk assessment. Risk is usually expressed by risk sources, potential events, their consequences and likelihood.
- 05Risk analysisModel · Evaluation leadThe second part of risk assessment. It considers consequences and likelihood of the identified risks, with guidelines, not a formula.
- 06Risk evaluationStep · Evaluation leadThe last part of risk assessment. Results of the analysis are compared with the risk criteria to see where more action is needed.
03 Treatment
- 07Risk treatmentStep · Evaluation leadTreatment options are selected, then plans are prepared and implemented. Residual risk is documented and goes to monitoring and review.
04 Across the process
- 02Communication and consultationStep · Evaluation leadCommunication and consultation with stakeholders is its own process element. The standard draws it alongside the others, not in sequence.
- 03Monitoring and reviewStep · Evaluation leadMonitoring and review take place at every stage. New experience, knowledge and analysis can revise elements, actions and controls.
05 Record and report
- 08Recording and reportingRecord · Evaluation leadThe process and its outcomes are documented and reported. The standard does not name who receives the report in the clauses read.
Outline of an external standard or method, from its public sources. It describes what the framework says, not a record of any run. It does not show that Nexus or any partner performs, certifies or approves a step. A gate is a step of the method, never a Nexus approval.
08Connections
Topics that rely on this method.
09Stewardship
Who maintains the method.
Advanced Industry and Robotics stewards robotics and automation for the Consortium and reviews how it is applied across platforms.
10Connected
Where this page leads across the Consortium.
11Questions
Questions and answers.
What are the limits of robotics and automation in this field?
Robots may behave unpredictably in unstructured environments not covered by testing. Interaction with people raises safety and liability questions.
How are results checked?
Systems are validated through simulation, staged field trials and conformance to functional safety standards. Operational monitoring checks performance after deployment.
Are the values on this page real?
The data names, roles and checks are real descriptions of practice. The canvas shows a design of the method’s use, not a run; no result is reported here.
Where else is this method applied?
The canonical method page lists every platform that applies it.
ReportsContribute
Contribute evidence from this page.
Reports is the Consortium’s quarterly publication. What you know about this subject can become evidence, a case or a correction in the next edition, credited to you and published under CC BY 4.0 where it is your own work.
GCRIArtificial Intelligence and Autonomous SystemsExponential TechnologyLabs Evidence
- EmailGateway GW-GCRISend it from this pageEvidence, a correction, a case, a method, a review, a translation or profile input. It arrives tagged with this page, so the editor who owns it receives it.
- ZenodoOpen depositDeposit it and submit to the communityPublish your own record on Zenodo with your ORCID iD, then submit it to the Reports community there. Curators review it; the DOI stays yours.
- ReportsGCRISee every way to contributeThe contribution types, how each is reviewed, what credit you receive, the licence and what is never accepted.
Never send personal data, sensitive infrastructure detail or anything you have no right to share. A contribution is reviewed before use; sending it confers no authorship or editorial rights, and sponsorship never buys a finding.
Artificial Intelligence and Autonomous Systems
Bring a method, a dataset or a question.
Information and enquiries are open today. An enquiry receives a reference and names the next step; applications, payments, compute allocations and registrations open only when their team, terms and review capacity exist.
Legal
Legal documents.
Maps, data and figures on this site are shown for context and general information. They are not advice, forecasts or warnings; the limits of the information are set out in the Disclaimers and Data Notices.