Risk Academy, led by the Nexus Consortium · Technology and Digital Systems · Department of Artificial Intelligence and Autonomous Systems
Industrial robots, autonomous vehicles, drones and functional safety
Amarobhothi nezinhlelo ezizimele
Robotics and autonomous systems covers machines that act in the physical world, from collaborative robots and autonomous vehicles to drones and uncrewed systems.
Map robotics and autonomous systems on a real placeSee the courses
Illustrative: packages on a board with routed traces carrying clocked signals, or a data hall of racks and their status lights
01Ububanzi
What the discipline covers
The subtopics its courses and labs teach.
- Izifundo
- In preparation
- Amazinga
- In development
- Amalabhorethri
- In development
- Industrial and collaborative robots
- Functional safety of machinery
- Autonomous vehicles
- Drones and uncrewed aircraft
- Operational design domains
- Human-machine teaming
- Ukuvikeleka kwe-cyber-physical
- Liability and governance of autonomy
Courses in development extend the scope to further subjects: Industrial automation and robotics safety; Autonomous vehicles, drones and uncrewed systems.
02Amamephu
Build a twin of any place
Search any place or open the world; the layers and generators follow robotics and autonomous systems on the planet map, the globe and in 3D.
- Terrain 0 to 245 m
- 4 satellite dishes
- 74 communication masts and towers
- 12 telephone exchanges
- 7 data centres and cable landing stations
- 12 aerodromes
- 1 telecom offices
- Communication line 161 km
- 729 known exploited vulnerabilities since 2023-10-17
- Night-time lights, VIIRS day-night band: read live when the 3D twin opens
Drag to move, right drag or Shift with a drag to turn and tilt, Ctrl with the wheel to zoom. Keyboard: arrows move, Shift with arrows turn and tilt, + and – zoom, 0 resets, V steps through the views, Escape clears.
Flat plan of the same data: relief as contours from the inline grid, the mapped ground infrastructure by kind, the mapped cables and the numbers below. The 3D twin opens on devices that can draw it, once its data and code have been checked.
The boundaries, names and designations shown do not imply any judgement on the legal status of any territory, or any endorsement or acceptance of such boundaries. Countries: Natural Earth (public domain).
03The subject
The subject, methods and measures and debates and bodies
The discipline
The field and its scope
For safety engineers, fleet operators, regulators and insurers who must decide whether a robot, vehicle or drone can act in a given environment and what evidence that decision needs.
Robotics and autonomous systems covers machines that sense, decide and act in the physical world: industrial arms and collaborative robots on production lines, mobile robots in warehouses and hospitals, road vehicles with driver assistance or full driving automation, uncrewed aircraft from inspection drones to long-range systems, and maritime and agricultural platforms. The risk questions are those of functional safety (does the machine fail safely when a component fails), of the safety of the intended functionality (does the perception and planning stack behave acceptably even when nothing has failed), of the operational design domain within which the system is claimed to work, of human-machine teaming, and of cyber-physical security, since a connected actuator is an attack surface with physical consequences.
The field is organised by sector and standard rather than by a single body. Machinery safety follows ISO 12100, ISO 10218 and ISO/TS 15066 for collaborative operation; road vehicles follow ISO 26262 for functional safety, ISO 21448 for the safety of the intended functionality and the UNECE regulations on automated lane keeping and cyber security; aviation follows the airworthiness and operational rules of national and regional authorities. Evidence comes from hazard analysis, simulation, closed-course and public-road testing and from incident data that is still thin and unevenly reported.
Measures
Quantities and units
| Quantity | Unit or scale | What to know |
|---|---|---|
| Distance or hours between safety-relevant events | kilometres or hours per collision, injury or disengagement | Rare-event statistics: Kalra and Paddock (2016) show that demonstrating a fatality rate better than human drivers at 95 percent confidence would require hundreds of millions of autonomous kilometres, so fleet data alone cannot carry a safety claim. |
| Probability of dangerous failure per hour | per hour, expressed as a safety integrity level or performance level | IEC 61508 bands of 10 to the minus 5 to 10 to the minus 9 per hour for continuous-mode functions; the figure is a design target derived from reliability models, not an observed rate, and does not cover software or perception faults. |
| Collision force and pressure on a human body region | newtons and newtons per square centimetre, against the limits of ISO/TS 15066 | Measured with instrumented test bodies; limits rest on pain-onset studies with small samples of adults and are less certain for children and for repeated contact. |
| Perception recall and false-negative rate per object class | percent, at a stated distance and condition | Measured on labelled scenes; drops under rain, low sun and occlusion. The class list is finite, so unlisted objects are not measured at all. |
| Operational design domain coverage | percent of scenario space exercised, by scenario category | Counts scenarios tested against a taxonomy such as the ISO 34502 scenario framework; coverage is only as good as the taxonomy, and the unknown unsafe scenarios are by definition not in it. |
| Takeover time | seconds from request to driver control, with distribution | Human-factors experiments report medians of several seconds with long tails; laboratory values understate real-world distraction. |
Izindlela
Methods and their limits
Each method is listed with what it assumes and where it fails.
| Indlela | Assumes | Fails when |
|---|---|---|
| Hazard analysis and risk assessment (ISO 12100, ISO 26262 HARA, STPA) | Hazards can be enumerated from the system's functions and environment, and severity, exposure and controllability can be rated consistently. | For learned components whose behaviour is not specified in advance; when the environment changes after the analysis; and when ratings are driven by what the team can mitigate rather than by what can happen. |
| Functional safety lifecycle (IEC 61508 and ISO 26262) | Random hardware failures have quantifiable rates and systematic faults are controlled by process rigour matched to an integrity level. | To address faults in perception or planning that occur with no component failure; this gap is why ISO 21448 (SOTIF) exists, and it still gives no quantitative target for machine learning. |
| Scenario-based simulation testing | The simulator's sensor and vehicle models are faithful, and the scenario set covers the operational design domain. | When simulation-to-reality gaps hide perception failures, when scenarios are hand-written and miss combinations, and when pass criteria are tuned to the simulator. |
| Public-road and field trials with safety drivers | Safety drivers intervene reliably, and disengagement and crash reports are complete and comparable. | When vigilance decays over long uneventful periods, when reporting rules differ between jurisdictions, and when trials run in benign conditions that do not represent the claimed domain. |
| Assurance cases for machine-learnt components (for example AMLAS) | The learnt component's requirements, data, model and deployment can each be argued with evidence and the argument can be reviewed. | When requirements for perception cannot be stated precisely, when the training data's representativeness is unverified, and when the component is updated after the case is written. |
| Threat modelling of cyber-physical interfaces (ISO/SAE 21434, UN Regulation No. 155) | Attack surfaces and attacker goals can be enumerated and controls assigned. | Against supply-chain compromise of components, against attacks on sensors themselves (spoofed GNSS, adversarial objects), and when over-the-air updates change the attack surface after type approval. |
Debates
What the field debates
- How safe is safe enough for an automated vehicle, and against what baseline?
- One position holds that automation should be deployed once it is at least as safe as the average human driver on the same roads, since each year of delay costs lives; it rests on crash statistics and on operator-reported injury rates for driverless services. The other holds that the comparison must be made for the same operational domain, that a system which fails in novel ways will not be accepted at parity, and that the fleet data to prove parity does not yet exist; it rests on the rare-event arithmetic of Kalra and Paddock (2016) and on public reaction to individual crashes.
- Should autonomous weapons and lethal uncrewed systems be governed by a new treaty or by existing law?
- States and civil society groups favouring a binding instrument argue that meaningful human control cannot be assured by current law and point to the pace of discussions under the Convention on Certain Conventional Weapons since 2014. Others hold that international humanitarian law already applies, that definitions of autonomy are unstable, and that weapons reviews under Article 36 are the workable route. The evidence on each side is legal and doctrinal, with limited public data on fielded systems.
- Does collaborative operation without fences reduce or redistribute risk?
- Advocates cite power-and-force-limited designs and ISO/TS 15066 limits that allow contact without injury, and productivity data from shared workcells. Critics cite the small evidence base for the biomechanical limits, the dependence on correct risk assessment for each application, and incident reports where speed-and-separation monitoring was defeated by workplace changes.
Bodies and data
Bodies that set practice, and the data they publish
Bodies and standards are named so learners can find and apply their published work; the Academy teaches their use and links to the publisher, and no affiliation is implied.
| Body | Role in the field |
|---|---|
| ISO/TC 299 Robotics | Maintains ISO 10218 (industrial robot safety), ISO 13482 (personal care robots) and ISO/TS 15066 (collaborative robots). |
| ISO/TC 22 Road vehicles | Maintains ISO 26262 (functional safety), ISO 21448 (safety of the intended functionality), ISO/SAE 21434 (cybersecurity engineering) and ISO 34502 (scenario-based safety evaluation). |
| UNECE World Forum for Harmonization of Vehicle Regulations (WP.29) | Adopts UN Regulations No. 155 (cyber security), No. 156 (software updates) and No. 157 (automated lane keeping) that contracting parties apply to type approval. |
| International Electrotechnical Commission (IEC) | Publishes IEC 61508 on functional safety of electrical, electronic and programmable systems, the parent of sector standards, and IEC 62061 for machinery. |
| European Union Aviation Safety Agency (EASA) | Sets the three operational categories for uncrewed aircraft in the European Union and publishes guidance on machine learning in aviation systems. |
| National Highway Traffic Safety Administration (NHTSA) | Collects crash reports for vehicles with driving automation under its Standing General Order and sets federal vehicle safety rules in the United States. |
| Dataset | Steward |
|---|---|
| Standing General Order crash reporting for automated driving systems | National Highway Traffic Safety Administration |
| Autonomous vehicle disengagement and collision reports | California Department of Motor Vehicles |
| World Robotics statistics | International Federation of Robotics |
04Indlela
From fleet kilometres to a safety claim: why road miles alone cannot carry it
To show a failure rate below a target with stated confidence and no failures observed, a fleet must drive minus ln(1 minus confidence) divided by the target rate; for fatality-class events that is hundreds of millions of kilometres, so a deployment decision needs an argument built from more than fleet data.
Sources: Kalra and Paddock, Driving to safety: How many miles of driving would it take to demonstrate autonomous vehicle reliability? (2016); Koopman and Wagner, Autonomous Vehicle Safety: An Interdisciplinary Challenge (2017); Burton et al., Mind the gaps: Assuring the safety of autonomous systems from an engineering, ethical, and legal perspective (2020); Hawkins et al., Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS) (2021).
05At a glance
At a glance, standards and evidence, research and evidence, what is changing and learning
- Build a twin of any placeTwin builderWorked example: West Cornwall: Goonhilly and the Porthcurno cable landings · 4 generators · 7 layers · 3 instruments
Igrafu ye-3D
Ifakhalthi Yobuchwepheshe Nezinhlelo Zedijithali
295 nodes1,814 relations9 views
06Ikhonsoli
How Robotics and autonomous systems is taught, as a process you can run
Press Play to run this process from this page's own data.
Amarobhothi nezinhlelo ezizimele
How Robotics and autonomous systems is taught
5 subjects in scope, 3 key terms, courses in development, 1 lab, in the Artificial Intelligence and Autonomous Systems department of Technology and Digital Systems: from the scope to the method and its terms, the courses that teach it, the labs on the twin, the assessment and the record.
-
01 Scope
- 01
Industrial and…
Start · the discipline
Industrial and collaborative robots
- 02
Functional safety of…
Start · the discipline
Functional safety of machinery
- 03
Autonomous vehicles
Start · the discipline
Autonomous vehicles
- 04
Drones and uncrewed…
Start · the discipline
Drones and uncrewed aircraft
- 05
Operational design…
Start · the discipline
Operational design domains
- 01
-
02 Method and terms
- 06
From fleet kilometres…
Model · the learner
To show a failure rate below a target with stated confidence and no failures observed, a fleet must drive minus ln(1 minus confidence)…
- 07
Collaborative robot
Record · the discipline
A robot designed to work alongside people in a shared space.
- 09
Operational design…
Record · the discipline
The conditions, such as roads, weather or speeds, under which an autonomous system is designed to work.
- 11
Functional safety
Record · the discipline
Safety that depends on control systems working correctly in response to their inputs.
- 06
-
04 Labs
- 08
Umfanekiso wedijithali
Exercise · the learner, on the faculty twin
The method runs on the faculty twin and the admitted map layers.
- 08
-
05 Assess
- 10
Module checks
Gate · the course
Each module ends with a short check against its outcomes.
- 12
Assessed work
Decision · the learner
The assessed work that closes a course: a lab record, a case memo or an assignment, reviewed against the rubric.
- 10
-
06 Record
- 13
Irekhodi lokuphothula
Outcome · the learner
The record stacks into the discipline achievement.
- 14
Discipline achievement
Record · the Academy
The discipline achievement follows the discipline rule, read from the records.
- 13
Robotics and autonomous systems · Artificial Intelligence and Autonomous Systems An outline of how the work is designed to run; it does not report the status of any decision or record.
07Ukufunda
Achievements, where this is practised, practised in and across the ecosystem
Impumelelo
Achievements in this discipline
Course achievements
One for each course with this as its primary discipline, earned when you pass the course's assessed activities.
An achievement is a record of the learning completed and assessed here. How recognition works.
Where this is practised
Where the subject is practised
- The Global Centre for Risk and Innovation (GCRI Canada)Artificial Intelligence and Autonomous SystemsAutonomous physical systems
- Advanced Industry and RoboticsIndustrial robotics, Industrial automation
Field platforms of the ecosystem where the subject is studied and applied.
Practised in
The two Foundry systems where it is practised
- FoundryNXS-NXQ systemThe operating envelope of an autonomous capability
- NXS-LAB systemField and bench experiments
Foundry system pages describe what each system and its rooms are designed to do; the courses teach the methods these systems apply.
Across the ecosystem
Across the ecosystem
The science, platforms and standards this discipline draws on and contributes to across the ecosystem.
Foundations in the STEM Commons
- The Global Centre for Risk and Innovation (GCRI Canada)Robotics and automationRobotics and automation design machines that sense, decide and act in physical environments.
- Software and safety-critical systems engineeringSoftware and safety-critical systems engineering develops software whose failure could cause harm, loss of life or major disruption.
- Sensors, IoT and observation networksSensors, IoT and observation networks collect continuous measurements of physical, environmental and operational conditions.
Standards for the field
- Nexus StandardsDigital, Cyber and AIThe subsite that keeps the standards this discipline teaches.
- Energy and Critical InfrastructureThe subsite that keeps the standards this discipline teaches.
Pages of the ecosystem, cited so learners can follow the field into research, platforms, standards and national practice.
08Bamba iqhaza
Take part in Technology and Digital Systems
Qala kulokho ongikho.
Izindlela
Indlela
Izikhungo zikazwelonke
Iminyango kahulumeni, amahhovisi ezibalo nama-ejensi: idesiki likazwelonke nesahluko, nesihlalo emaqenjini okusebenza. Izahluko zikazwelonke
Indlela
Imikhakha nemisebenzi
Operators, regulators, banks, insurers and professional bodies whose work touches technology and digital systems. For organisations
Indlela
Ukufunda
Izifundo nokuzijwayeza, nerekhodi lazo zonke izifundo eziqediwe. Mahhala ukufunda. Ukufunda okuvulekile
Indlela
Amazinga
Bhala okusalungiswa, buyekeza futhi wamukele izindlela namazinga edatha namaqembu okusebenza. Amaqembu okusebenza
Indlela
Imiphakathi nocwaningo
Universities, civil society and individual experts: projects, data and review. Write to the Academy
Izimemo ezivulekile
| Isimemo esivulekile | Kufunwa | Kuvalwa |
|---|---|---|
| Isimemo sokusungula sochwepheshe emaqenjini okusebenza CALL-FOUNDING-EXPERTS | uchwepheshe, umhleli, usihlalo | 2026-12-15 |
| Ukuqokwa okuvulekile kwezihlalo ezintathu zochwepheshe abazimele ze-Global Standards Council CALL-GSC-IND | ilungu lomkhandlu | 2026-12-01 |
| Ukuqokwa kwamalungu esifunda esikhashana (kusebenza kuphela uma isinqumo sesikhashana sithathwa) CALL-GSC-REG | ilungu lomkhandlu | 2026-12-15 |
| Ukubuyekezwa kwezinhlaka zomongo wengozi wegagasi 1 (C1, C2, C3, C4, C8, C10, C11) CALL-REVIEW-WAVE1 | umnikeli | 2027-01-31 |
| Ochwepheshe bamazinga ayisisekelo esayensi yengozi: ukungaqiniseki nokulinganiswa kobufakazi, izilinganiso, ukwahlulela kochwepheshe okuhlelekile, ukubekezeleleka, izimo ezeqisayo nezehlakalo ezihlanganisiwe, ingozi eyinhlekelele neyokuphila, izimiso nokulingana, amayunithi nokulinganisa (NRS-C17 kuya ku-NRS-C24) CALL-CORE-SCIENCE | uchwepheshe, umhleli, usihlalo | 2027-01-31 |
| Ababuyekezi abazimele bemindeni ye-atlas yezingozi, abathathu abavela okungenani ezifundeni ezimbili emndenini ngamunye (NHS2-R19), imindeni ehamba phambili kuqala CALL-ATLAS-REVIEW | uchwepheshe | 2027-03-31 |
| Amalungu e-Frontier Safety Review Panel yesikhashana nababuyekezi beqembu elibomvu (ukuphepha kwezinto eziphilayo nokuvikeleka kwazo, ukuphepha nokuvikeleka kwe-AI, ukuvikeleka kwengqalasizinda ebalulekile); izicelo ziphathwa ngokuyimfihlo CALL-FRONTIER-SAFETY-REVIEW | uchwepheshe | 2026-11-30 |
| Ochwepheshe be-ontology, i-metrology, ukuqinisekiswa kwesofthiwe nokuhlolwa kokuhambisana kwerejista yezidingo, ukumelwa komshini kwe-NHS-2, amasethi okuhlola ukuhambisana nohlelo lokuhlola ukuhambisana CALL-CONFORMANCE-ONTOLOGY | uchwepheshe, umhleli | 2027-01-31 |
Izimemo ezidlule usuku lwazo lokuvala zifihlwa ngokuzenzakalelayo. Zonke izimemo, iziphakamiso nezindlela: izindawo nezimemo ezivulekile.
Amaseli nama-CERT
Qoqa iseli
Hlanganisa abantu abathathu kuya kwabayisikhombisa abanamakhono ahambisanayo: idatha, ukusebenza enkundleni, inqubomgomo nokuxhumana.
Libhalise
Write to the team with the cell's name, members, area and region. You receive a reference and a contact. Write to the Academy
Khetha umqulu
Khetha ukugxila okukodwa: ucwaningo nobufakazi, idatha namamephu, ukubuyekezwa kwamazinga, noma ukulungiselela komphakathi.
Funda ndawonye
Landela izindlela zokufunda ezabelwana ngazo e-Risk Academy, nokuzijwayeza nerekhodi lazo zonke izifundo eziqediwe. Izinsongo nokuqina
Hola futhi ubike
Hold regular sessions. Publish what the cell learns through Reports. Bring findings to the working groups. Working groups
Gxila njengeThimba Lomphakathi Lokusabela Ezimweni Eziphuthumayo (CERT)
A CERT prepares its neighbourhood for the hazards it faces. It builds a local hazard profile from this site's map. It trains in household and street preparedness. It learns first aid and light search through recognised local providers, and it runs drills. A CERT works alongside the local emergency services and follows their direction. It never replaces them and is not an emergency service.
I-Index
What a national team or a local community can do on The Global Risks Index (NXS-GRX) today.
NXS-GRX
Your country's profile
Amaphrofayela engozi avulekile amazwe angu-195, nemithombo namalayisense kuyo yonke inani. Vula Inkomba
NXS-GRX
Lungisa noma uphendule
Lungisa inani noma uphendule ngezwe lakho. Ushintsho lurekhodwa kanye nomphumela walo. Vula Inkomba
NXS-GRX
Nikela ngedatha
Nikela ngeqoqo ledatha. Lingena ngesango lelayisense, ubongwa. Vula Inkomba
NXS-GRX
Sebenzisa idatha evulekile
Izendlalelo, amaphrofayela namathayela nge-API evulekile. Vula Inkomba
09References
Core references and where to begin
Start with Koopman, then Kalra, then Leveson.
- Kalra, N. and Paddock, S. M., Driving to safety: How many miles of driving would it take to demonstrate autonomous vehicle reliability? (2016). DOI
- Koopman, P. and Wagner, M., Autonomous Vehicle Safety: An Interdisciplinary Challenge (2017). DOI
- Leveson, N. G., Engineering a Safer World: Systems Thinking Applied to Safety (2011). DOI
- Haddadin, S., De Luca, A. and Albu-Schäffer, A., Robot Collisions: A Survey on Detection, Isolation, and Identification (2017). DOI
- Villani, V., Pini, F., Leali, F. and Secchi, C., Survey on human-robot collaboration in industrial settings: Safety, intuitive interfaces and applications (2018). DOI
- Burton, S., Habli, I., Lawton, T. et al., Mind the gaps: Assuring the safety of autonomous systems from an engineering, ethical, and legal perspective (2020). DOI
- Hawkins, R., Paterson, C., Picardi, C. et al., Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS) (2021). arxiv.org
- Shalev-Shwartz, S., Shammah, S. and Shashua, A., On a Formal Model of Safe and Scalable Self-driving Cars (2017). arxiv.org
- Dulac-Arnold, G., Levine, N., Mankowitz, D. J. et al., Challenges of real-world reinforcement learning: definitions, benchmarks and analysis (2021). DOI
10Imibuzo
Imibuzo, izimpendulo namagama abalulekile
Ukufunda lapha kungamahhala yini?
Yebo. Zonke izinkambo nezinto zokufunda ze-Risk Academy, eholwa yi-Nexus Consortium, zifundwa mahhala, ngesivinini sakho noma neqembu. Ukubamba iqhaza okujwayelekile akunayo inkokhelo; umsebenzi ohlawulelwayo, ukuqeqeshwa emsebenzini nezibonelelo zocwaningo kuyizinhlelo ezihlukile.
Kuyini engikuthola ngokuphothula isifundo?
Irekhodi lokuphothula: isifundo, inguqulo yaso, usuku nokuhlolwe, eliyimfihlo ngokuzenzakalelayo futhi labelwana nguwe. Lihlangana libe yimiphumela yomkhakha, yomnyango neyohlelo. Irekhodi likhomba okufundiwe nokuhlolwe, alisho ukuthi ukhono luqinisekisiwe; akulona ilayisense, isihloko sobuchwepheshe noma isimo somsebenzi.
Idatha nezindawo zivelaphi?
Ifakhalthi ngayinye ifundisa ngamawele endawo yangempela akhiwe ngedatha evulekile; isendlalelo ngasinye siveza umhlinzeki waso, ilayisense nosuku, futhi umphumela ngamunye ku-Academy uveza umthombo wawo. Amamephu nezibalo yizinkombandlela zokufundisa, ayisona isilinganiso sendawo.
How do I take part beyond the courses in robotics and autonomous systems?
Yakha iseli lekhono labantu abathathu kuya kwabayisikhombisa, funda indlela okwabelwana ngayo, thatha umsebenzi ogadiwe kuma-National Working Groups, noma ulethe iqembu labafundi elivela esikhungweni sakho. Ezinhlanganweni.
Amagama abalulekile
- Collaborative robot
- A robot designed to work alongside people in a shared space.
- Operational design domain
- The conditions, such as roads, weather or speeds, under which an autonomous system is designed to work.
- Functional safety
- Safety that depends on control systems working correctly in response to their inputs.
- Uncrewed aircraft system
- An aircraft flown without a pilot on board, with its control station and links.
ImibikoNikela
Nikela ngobufakazi kusuka kuleli khasi.
I-Reports iyincwadi yekota ye-Consortium. Lokho oakwaziyo ngalesi sihloko kungaba ubufakazi, icala noma ukulungisa kuhlelo olulandelayo, kubongwe wena futhi kushicilelwe ngaphansi kwe-CC BY 4.0 lapho kungumsebenzi wakho.
Risk Academy
- EmailGateway GW-ACADEMY Send it from this page Evidence, 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 deposit Deposit it and submit to the community Publish your own record on Zenodo with your ORCID iD, then submit it to the Reports community there. Curators review it; the DOI stays yours.
- ReportsRisk Academy See every way to contribute The contribution types, how each is reviewed, what credit you receive, the licence and what is never accepted.
Ungalokothi uthumele idatha yomuntu siqu, imininingwane ebucayi yengqalasizinda noma noma yini ongenalo ilungelo lokuyabelana ngayo. Umnikelo ubuyekezwa ngaphambi kokusetshenziswa; ukuwuthumela akunikezi ubuqambi noma amalungelo okuhlela, futhi ukusekela akuthengi muphumela.
Amarobhothi nezinhlelo ezizimele
Prepare with a related course
Open courses in connected disciplines teach the methods this discipline will build on.
Buka ikhathalogi yezifundoBack to Department of Artificial Intelligence and Autonomous Systems