Skip to content

GCRI · Inteligência artificial e sistemas autônomos

Sistemas físicos autônomos

Autonomous vehicles, drones, industrial and service robots sense their surroundings and act in the physical world, where errors can injure people and damage property. Their safety depends on perception, decision-making, fallback behaviour and the environments they are allowed to operate in. This page sets out how autonomous physical sistemas fail, how their safety is assessed, and what evidence serves the regulators, operators and communities involved.

01Registrar

Autonomous physical systems on the record.

02A pergunta

Autonomous physical systems: how the risk develops.

Robots, sensors and controls. The dossier below sets out how the risk develops, what is measured, where the data come from, how it is modelled and who decides.

Mecanismo

Perception meets the unexpected

Sensors and models misread rare situations: unusual objects, poor weather, glare or confusing road layouts. Rare cases dominate risk because they are hard to test.

Mecanismo

Operating domains set limits

sistemas are designed for an operational design domain of roads, weather, speeds or spaces. Failures increase when systems are used outside it.

Mecanismo

Handover to humans is hard

Supervisors lose attention when automation works most of the time, and cannot take over instantly when it fails.

Mecanismo

Safety cases must be argued

Showing that a system is acceptably safe needs a structured argument combining design, testing, simulation and field data, because driving or operating enough to see rare failures is impractical.

03Monitoramento

Agent oversight console.

A tela que uma equipe usaria para acompanhar esta matéria: suas medidas, estados e decisões. Os nomes são exemplos e os valores são ilustrativos.

Agent oversight console

Autonomous physical systems · Agent sandbox · Session AG-7276

Human approval pendingGCRI · Inteligência artificial e sistemas autônomos

Tool calls

  1. 10:27Informaçãosearch(documents) · read-only
  2. 10:20Informaçãorun_model(flood_nowcast) · sandbox
  3. 10:39Marcosend_message(external) · needs approval
  4. 10:45Errorwrite_file(outside workspace) · denied

Políticas públicas

Escopo
workspace only
External actions
human approval
Spend limit
11 units
Kill switch
Armed

Actions by approval class

050100count this weekAutomáticoRegistradoAprovadoDeniedEscalado
Agent oversight console: the screen’s structure, terms and states for Autonomous physical systems.Nomes de exemplo e valores ilustrativos; um projeto, não um registro nem um sistema ativo.
04Em todos os domínios

Autonomous machines operate in physical domains with physical risks.

Findings are designed for the série Labs Evidence. SAE J3016 defines levels of driving automation, and the EU Machinery Regulation (2023) addresses machines with self-evolving behaviour.

  • Field safety incident data.
  • Test protocols for autonomy in unstructured settings.
05Métodos e evidência

How autonomous physical systems is modelled, measured and tested.

O modelo, os seus pressupostos, os seus dados e a sua incerteza, na forma que um cientista ou engenheiro verificaria. As estruturas seguem métodos publicados. Os valores representados são ilustrativos, não conclusões.

Modelo de sistema

The couplings between the systems in autonomous physical systems: signs of influence, a reinforcing and a balancing loop, and cross-links where stress jumps.

++−+Inteligência artificialDadosComunidadesEconomiaR de reforçoB equilíbrio
Causal loop diagram from the page’s systems; signs show the direction of influence. Illustrative structure for a system dynamics or network model, not estimated couplings.
Princípios orientadores FAIR · GO FAIR e FORCE11W3C PROV · World Wide Web ConsortiumOrientação sobre o tratamento consistente das incertezas · IPCCCEOS Analysis Ready Data · Committee on Earth Observation Satellites
06Indicadores

O que é medido e com que qualidade.

Cada indicador leva sua unidade, sua periodicidade, o tipo de fonte por trás dele e a etiqueta de evidência que um valor levaria. Nenhum valor é mostrado: um programa os fornece sob sua própria autoridade.

IndicadorUnidadeCadênciaTipo de fonteRótulo
Crashes involving automated driving sistemascount by severitymensalMandatory crash reportingEstatísticas publicadas
Disengagements or interventionscount per distance or houranualOperator reports to regulatorsREPORTADO
Distance driven autonomouslykilometresanualOperator reportsDECLARADO
Industrial robot injuriescontagemanualOccupational injury statisticsEstatísticas publicadas
Operating domain exceedancescount of events outside design domainper deploymentOperator logsOBSERVADO
Drone incidents near aircraftcontagemanualAviation safety reportingREPORTADO
07Fontes

De onde vêm as evidências.

Conjuntos de dados públicos nomeados e registros institucionais, cada um com sua classe de licença. As fontes obtidas por acordo só são usadas nos seus termos e nunca são republicadas.

FonteO que ofereceClasse de licença
NHTSA Standing General Order crash reportsCrashes involving automated driving and driver assistance sistemas in the USPublic domain, US government
California DMV autonomous vehicle reportsCollision and disengagement reports from permit holdersRegistros públicos
UNECE regulations on automated driving, including UN Regulation No. 157Type approval requirements for automated lane keeping and related systemsPublic, UNECE terms
ISO 10218 e ISO/TS 15066Safety requirements for industrial and collaborative robotsLicensed standards, purchase required
Nacional occupational injury statisticsInjuries involving machinery and robotsPublic records, licence per government
08Decisões

Quem decide, e a que servem as evidências.

Estúdio de Inteligência artificial e sistemas prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.

Quem decideA perguntaEvidências a que esta página serve
Transport and aviation regulatorsWhether and where to permit autonomous operationCrash data with exposure; safety case reviews
Workplace safety regulatorsWhat safety requirements to set for robotsInjury statistics; standards
Operators and manufacturersHow to define and enforce operating domainsDomain documentation; exceedance logs

Produtos que este tema gera

  • Safety case review frameworks
  • Analyses of crash and intervention reports with exposure stated
  • Operational design domain documentation templates
  • Evidence notes for regulators
09Questões centrais

What safety engineers ask.

  • Does the system perceive its environment correctly across weather, lighting and unusual objects?
  • How does it behave at the edges of its operating conditions, and does it know when it is outside them?
  • Can it fail safely, handing over to a person or stopping without creating new hazards?
  • How is safety demonstrated when learned components cannot be fully specified?
10Mecanismos

Where physical autonomy fails.

Perception is the weak link: cameras, lidar and radar each fail differently in rain, glare, dust or darkness, and learned perception models can misclassify rare objects. Planning must handle uncertain predictions of other agents’ behaviour. Control must remain stable as conditions change.

Handover to humans is difficult because people monitoring automation lose situational awareness and may not respond in time. Classical safety engineering assumes components whose behaviour can be fully specified, which learned components are not.

11Métodos e dados

Assurance for systems that move.

  1. 01

    Domínio de projeto operacional

    Defining the conditions a system is designed for and detecting when it leaves them.

  2. 02

    Simulation and scenario testing

    Testing across large numbers of simulated scenarios, using robótica e automação and high-performance, cloud and edge computing. Simulation fidelity limits what it can reveal.

  3. 03

    Safety cases

    Structured arguments, supported by evidence, that a system is acceptably safe for a use, drawing on Engenharia de avaliação e garantia de IA. A safety case is only as strong as its weakest evidence.

  4. 04

    Field monitoring

    Collecting incidents and near misses after deployment. Under-reporting is common.

13Where this page’s references

Where this page’s references lead.

Os organismos e documentos à luz dos quais esta página é lida. O estado e as edições mudam; cada ligação leva ao organismo emissor.

14Perguntas

Perguntas e respostas.

What is an operational design domain?
The conditions under which an automated system is designed to operate, such as road types, speeds, weather and time of day.
Are self-driving cars safer than human drivers?
Evidence is still accumulating. Fair comparison needs crash data with matched exposure, road types and conditions, which public reports often lack.
What is a safety case?
A structured argument, supported by evidence, that a system is acceptably safe for a specific use in a specific environment.
Are autonomous vehicles safer than human drivers?
It depends on the system, the conditions and how safety is measured. Comparisons need like-for-like conditions and enough exposure to observe rare events, which is why claims should be read with their data.
Can learned components be safety-assured?
Partly, through testing, monitoring and architectures that constrain them with simpler verified components. Assurance of learned components remains an active research area.
Does the platform test products?
No. It develops and publishes methods. Product testing and approval are the roles of manufacturers, testing bodies and regulators.
RelatóriosContribuir

Contribua com evidências a partir desta página.

Relatórios 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.

GCRIInteligência artificial e sistemas autônomosTecnologia exponencialEvidências de Labs
Inteligência artificial e sistemas autônomos

Traga um método, um conjunto de dados ou uma pergunta.

A informação e os pedidos estão abertos hoje. Um pedido recebe uma referência e indica o próximo passo; candidaturas, pagamentos, alocações de computação e registros só abrem quando existem a equipa, os termos e a capacidade de revisão.