BS Robotics & Intelligent Systems · Machine Learning

Unit 2: Data Preparation MCQs

50 solved multiple choice questions with answers and short explanations.

Q1. Which statement best describes Data Preparation Concepts within Data Preparation? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIt can be evaluated without considering interfaces or operating conditions.
  2. BIt should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.
  3. CIt is only a naming convention with no effect on robot behavior.
  4. DIt guarantees autonomous performance regardless of sensors or environment.
Show answer
Answer: B. It should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.Machine Learning → Data Preparation → Data Preparation Concepts: It should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.
Report a mistake

Q2. What is the primary purpose of Data Preparation Concepts in a robotics or intelligent-systems context? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIts sole purpose is to maximize robot speed.
  2. BIt removes the need for sensing, modeling, and verification.
  3. CIt guarantees perfect autonomy in every environment.
  4. DIt supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.
Show answer
Answer: D. It supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.Machine Learning → Data Preparation → Data Preparation Concepts: It supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.
Report a mistake

Q3. A robotics team is working with Data Preparation Concepts. Which approach is most appropriate? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ASkip physical validation once software runs successfully.
  2. BDefine requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.
  3. CSelect hardware and algorithms before defining the task.
  4. DIgnore operating conditions because simulation covers all cases.
Show answer
Answer: B. Define requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.Machine Learning → Data Preparation → Data Preparation Concepts: Define requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.
Report a mistake

Q4. Which principle best supports correct modeling involving Data Preparation Concepts? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIgnore coordinate frames if numerical values look reasonable.
  2. BUse any model regardless of its assumptions.
  3. CTreat uncertainty and dynamics as irrelevant to robotic systems.
  4. DUse a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.
Show answer
Answer: D. Use a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.Machine Learning → Data Preparation → Data Preparation Concepts: Use a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.
Report a mistake

Q5. Which consideration is most important when designing a system involving Data Preparation Concepts? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AChoose the most complex architecture even when requirements are simple.
  2. BBalance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.
  3. CAlways maximize speed regardless of safety or power.
  4. DIgnore sensing limitations when selecting control methods.
Show answer
Answer: B. Balance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.Machine Learning → Data Preparation → Data Preparation Concepts: Balance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.
Report a mistake

Q6. How should an engineer verify work involving Data Preparation Concepts? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ATest only one ideal condition.
  2. BAssume simulation proves all real-world behavior.
  3. CTreat successful compilation as complete system validation.
  4. DTest against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.
Show answer
Answer: D. Test against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.Machine Learning → Data Preparation → Data Preparation Concepts: Test against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.
Report a mistake

Q7. When a problem related to Data Preparation Concepts appears, what should be done first? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIgnore logs and sensor data during diagnosis.
  2. BEstablish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.
  3. CReplace several components before collecting evidence.
  4. DAssume the first suspected cause is correct.
Show answer
Answer: B. Establish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.Machine Learning → Data Preparation → Data Preparation Concepts: Establish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.
Report a mistake

Q8. Which evidence best supports a performance assessment involving Data Preparation Concepts? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AUse an unrelated metric because it is easy to measure.
  2. BReport results without stating test conditions.
  3. CAssume theoretical peak performance equals field performance.
  4. DUse task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.
Show answer
Answer: D. Use task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.Machine Learning → Data Preparation → Data Preparation Concepts: Use task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.
Report a mistake

Q9. Which trade-off should be considered when selecting an approach to Data Preparation Concepts? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ASafety can always be traded away for higher speed.
  2. BBalance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.
  3. COnly maximum accuracy matters in every robot.
  4. DEnergy and latency never affect intelligent systems.
Show answer
Answer: B. Balance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.Machine Learning → Data Preparation → Data Preparation Concepts: Balance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.
Report a mistake

Q10. Which practice best supports safe and responsible use of Data Preparation Concepts? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ADisable safety limits during normal operation.
  2. BDeploy untested autonomous behavior around people.
  3. CIgnore foreseeable failure modes if average performance is high.
  4. DDefine operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.
Show answer
Answer: D. Define operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.Machine Learning → Data Preparation → Data Preparation Concepts: Define operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.
Report a mistake

Q11. Which statement best describes Data Preparation Principles within Data Preparation? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIt is only a naming convention with no effect on robot behavior.
  2. BIt guarantees autonomous performance regardless of sensors or environment.
  3. CIt can be evaluated without considering interfaces or operating conditions.
  4. DIt should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.
Show answer
Answer: D. It should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.Machine Learning → Data Preparation → Data Preparation Principles: It should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.
Report a mistake

Q12. What is the primary purpose of Data Preparation Principles in a robotics or intelligent-systems context? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIt guarantees perfect autonomy in every environment.
  2. BIt supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.
  3. CIts sole purpose is to maximize robot speed.
  4. DIt removes the need for sensing, modeling, and verification.
Show answer
Answer: B. It supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.Machine Learning → Data Preparation → Data Preparation Principles: It supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.
Report a mistake

Q13. A robotics team is working with Data Preparation Principles. Which approach is most appropriate? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ASelect hardware and algorithms before defining the task.
  2. BIgnore operating conditions because simulation covers all cases.
  3. CSkip physical validation once software runs successfully.
  4. DDefine requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.
Show answer
Answer: D. Define requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.Machine Learning → Data Preparation → Data Preparation Principles: Define requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.
Report a mistake

Q14. Which principle best supports correct modeling involving Data Preparation Principles? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ATreat uncertainty and dynamics as irrelevant to robotic systems.
  2. BUse a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.
  3. CIgnore coordinate frames if numerical values look reasonable.
  4. DUse any model regardless of its assumptions.
Show answer
Answer: B. Use a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.Machine Learning → Data Preparation → Data Preparation Principles: Use a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.
Report a mistake

Q15. Which consideration is most important when designing a system involving Data Preparation Principles? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AAlways maximize speed regardless of safety or power.
  2. BIgnore sensing limitations when selecting control methods.
  3. CChoose the most complex architecture even when requirements are simple.
  4. DBalance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.
Show answer
Answer: D. Balance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.Machine Learning → Data Preparation → Data Preparation Principles: Balance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.
Report a mistake

Q16. How should an engineer verify work involving Data Preparation Principles? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ATreat successful compilation as complete system validation.
  2. BTest against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.
  3. CTest only one ideal condition.
  4. DAssume simulation proves all real-world behavior.
Show answer
Answer: B. Test against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.Machine Learning → Data Preparation → Data Preparation Principles: Test against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.
Report a mistake

Q17. When a problem related to Data Preparation Principles appears, what should be done first? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AReplace several components before collecting evidence.
  2. BAssume the first suspected cause is correct.
  3. CIgnore logs and sensor data during diagnosis.
  4. DEstablish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.
Show answer
Answer: D. Establish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.Machine Learning → Data Preparation → Data Preparation Principles: Establish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.
Report a mistake

Q18. Which evidence best supports a performance assessment involving Data Preparation Principles? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AAssume theoretical peak performance equals field performance.
  2. BUse task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.
  3. CUse an unrelated metric because it is easy to measure.
  4. DReport results without stating test conditions.
Show answer
Answer: B. Use task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.Machine Learning → Data Preparation → Data Preparation Principles: Use task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.
Report a mistake

Q19. Which trade-off should be considered when selecting an approach to Data Preparation Principles? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AOnly maximum accuracy matters in every robot.
  2. BEnergy and latency never affect intelligent systems.
  3. CSafety can always be traded away for higher speed.
  4. DBalance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.
Show answer
Answer: D. Balance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.Machine Learning → Data Preparation → Data Preparation Principles: Balance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.
Report a mistake

Q20. Which practice best supports safe and responsible use of Data Preparation Principles? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIgnore foreseeable failure modes if average performance is high.
  2. BDefine operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.
  3. CDisable safety limits during normal operation.
  4. DDeploy untested autonomous behavior around people.
Show answer
Answer: B. Define operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.Machine Learning → Data Preparation → Data Preparation Principles: Define operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.
Report a mistake

Q21. Which statement best describes Data Preparation Modeling within Data Preparation? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIt can be evaluated without considering interfaces or operating conditions.
  2. BIt should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.
  3. CIt is only a naming convention with no effect on robot behavior.
  4. DIt guarantees autonomous performance regardless of sensors or environment.
Show answer
Answer: B. It should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.Machine Learning → Data Preparation → Data Preparation Modeling: It should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.
Report a mistake

Q22. What is the primary purpose of Data Preparation Modeling in a robotics or intelligent-systems context? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIts sole purpose is to maximize robot speed.
  2. BIt removes the need for sensing, modeling, and verification.
  3. CIt guarantees perfect autonomy in every environment.
  4. DIt supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.
Show answer
Answer: D. It supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.Machine Learning → Data Preparation → Data Preparation Modeling: It supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.
Report a mistake

Q23. A robotics team is working with Data Preparation Modeling. Which approach is most appropriate? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ASkip physical validation once software runs successfully.
  2. BDefine requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.
  3. CSelect hardware and algorithms before defining the task.
  4. DIgnore operating conditions because simulation covers all cases.
Show answer
Answer: B. Define requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.Machine Learning → Data Preparation → Data Preparation Modeling: Define requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.
Report a mistake

Q24. Which principle best supports correct modeling involving Data Preparation Modeling? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIgnore coordinate frames if numerical values look reasonable.
  2. BUse any model regardless of its assumptions.
  3. CTreat uncertainty and dynamics as irrelevant to robotic systems.
  4. DUse a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.
Show answer
Answer: D. Use a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.Machine Learning → Data Preparation → Data Preparation Modeling: Use a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.
Report a mistake

Q25. Which consideration is most important when designing a system involving Data Preparation Modeling? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AChoose the most complex architecture even when requirements are simple.
  2. BBalance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.
  3. CAlways maximize speed regardless of safety or power.
  4. DIgnore sensing limitations when selecting control methods.
Show answer
Answer: B. Balance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.Machine Learning → Data Preparation → Data Preparation Modeling: Balance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.
Report a mistake

Q26. How should an engineer verify work involving Data Preparation Modeling? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ATest only one ideal condition.
  2. BAssume simulation proves all real-world behavior.
  3. CTreat successful compilation as complete system validation.
  4. DTest against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.
Show answer
Answer: D. Test against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.Machine Learning → Data Preparation → Data Preparation Modeling: Test against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.
Report a mistake

Q27. When a problem related to Data Preparation Modeling appears, what should be done first? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIgnore logs and sensor data during diagnosis.
  2. BEstablish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.
  3. CReplace several components before collecting evidence.
  4. DAssume the first suspected cause is correct.
Show answer
Answer: B. Establish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.Machine Learning → Data Preparation → Data Preparation Modeling: Establish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.
Report a mistake

Q28. Which evidence best supports a performance assessment involving Data Preparation Modeling? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AUse an unrelated metric because it is easy to measure.
  2. BReport results without stating test conditions.
  3. CAssume theoretical peak performance equals field performance.
  4. DUse task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.
Show answer
Answer: D. Use task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.Machine Learning → Data Preparation → Data Preparation Modeling: Use task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.
Report a mistake

Q29. Which trade-off should be considered when selecting an approach to Data Preparation Modeling? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ASafety can always be traded away for higher speed.
  2. BBalance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.
  3. COnly maximum accuracy matters in every robot.
  4. DEnergy and latency never affect intelligent systems.
Show answer
Answer: B. Balance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.Machine Learning → Data Preparation → Data Preparation Modeling: Balance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.
Report a mistake

Q30. Which practice best supports safe and responsible use of Data Preparation Modeling? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ADisable safety limits during normal operation.
  2. BDeploy untested autonomous behavior around people.
  3. CIgnore foreseeable failure modes if average performance is high.
  4. DDefine operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.
Show answer
Answer: D. Define operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.Machine Learning → Data Preparation → Data Preparation Modeling: Define operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.
Report a mistake

Q31. Which statement best describes Data Preparation Evaluation within Data Preparation? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIt is only a naming convention with no effect on robot behavior.
  2. BIt guarantees autonomous performance regardless of sensors or environment.
  3. CIt can be evaluated without considering interfaces or operating conditions.
  4. DIt should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.
Show answer
Answer: D. It should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.Machine Learning → Data Preparation → Data Preparation Evaluation: It should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.
Report a mistake

Q32. What is the primary purpose of Data Preparation Evaluation in a robotics or intelligent-systems context? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIt guarantees perfect autonomy in every environment.
  2. BIt supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.
  3. CIts sole purpose is to maximize robot speed.
  4. DIt removes the need for sensing, modeling, and verification.
Show answer
Answer: B. It supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.Machine Learning → Data Preparation → Data Preparation Evaluation: It supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.
Report a mistake

Q33. A robotics team is working with Data Preparation Evaluation. Which approach is most appropriate? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ASelect hardware and algorithms before defining the task.
  2. BIgnore operating conditions because simulation covers all cases.
  3. CSkip physical validation once software runs successfully.
  4. DDefine requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.
Show answer
Answer: D. Define requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.Machine Learning → Data Preparation → Data Preparation Evaluation: Define requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.
Report a mistake

Q34. Which principle best supports correct modeling involving Data Preparation Evaluation? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ATreat uncertainty and dynamics as irrelevant to robotic systems.
  2. BUse a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.
  3. CIgnore coordinate frames if numerical values look reasonable.
  4. DUse any model regardless of its assumptions.
Show answer
Answer: B. Use a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.Machine Learning → Data Preparation → Data Preparation Evaluation: Use a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.
Report a mistake

Q35. Which consideration is most important when designing a system involving Data Preparation Evaluation? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AAlways maximize speed regardless of safety or power.
  2. BIgnore sensing limitations when selecting control methods.
  3. CChoose the most complex architecture even when requirements are simple.
  4. DBalance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.
Show answer
Answer: D. Balance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.Machine Learning → Data Preparation → Data Preparation Evaluation: Balance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.
Report a mistake

Q36. How should an engineer verify work involving Data Preparation Evaluation? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ATreat successful compilation as complete system validation.
  2. BTest against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.
  3. CTest only one ideal condition.
  4. DAssume simulation proves all real-world behavior.
Show answer
Answer: B. Test against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.Machine Learning → Data Preparation → Data Preparation Evaluation: Test against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.
Report a mistake

Q37. When a problem related to Data Preparation Evaluation appears, what should be done first? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AReplace several components before collecting evidence.
  2. BAssume the first suspected cause is correct.
  3. CIgnore logs and sensor data during diagnosis.
  4. DEstablish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.
Show answer
Answer: D. Establish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.Machine Learning → Data Preparation → Data Preparation Evaluation: Establish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.
Report a mistake

Q38. Which evidence best supports a performance assessment involving Data Preparation Evaluation? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AAssume theoretical peak performance equals field performance.
  2. BUse task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.
  3. CUse an unrelated metric because it is easy to measure.
  4. DReport results without stating test conditions.
Show answer
Answer: B. Use task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.Machine Learning → Data Preparation → Data Preparation Evaluation: Use task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.
Report a mistake

Q39. Which trade-off should be considered when selecting an approach to Data Preparation Evaluation? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AOnly maximum accuracy matters in every robot.
  2. BEnergy and latency never affect intelligent systems.
  3. CSafety can always be traded away for higher speed.
  4. DBalance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.
Show answer
Answer: D. Balance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.Machine Learning → Data Preparation → Data Preparation Evaluation: Balance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.
Report a mistake

Q40. Which practice best supports safe and responsible use of Data Preparation Evaluation? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIgnore foreseeable failure modes if average performance is high.
  2. BDefine operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.
  3. CDisable safety limits during normal operation.
  4. DDeploy untested autonomous behavior around people.
Show answer
Answer: B. Define operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.Machine Learning → Data Preparation → Data Preparation Evaluation: Define operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.
Report a mistake

Q41. Which statement best describes Data Preparation Applications within Data Preparation? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIt can be evaluated without considering interfaces or operating conditions.
  2. BIt should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.
  3. CIt is only a naming convention with no effect on robot behavior.
  4. DIt guarantees autonomous performance regardless of sensors or environment.
Show answer
Answer: B. It should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.Machine Learning → Data Preparation → Data Preparation Applications: It should be understood through its physical or computational role, assumptions, interfaces, inputs, outputs, and system context.
Report a mistake

Q42. What is the primary purpose of Data Preparation Applications in a robotics or intelligent-systems context? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIts sole purpose is to maximize robot speed.
  2. BIt removes the need for sensing, modeling, and verification.
  3. CIt guarantees perfect autonomy in every environment.
  4. DIt supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.
Show answer
Answer: D. It supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.Machine Learning → Data Preparation → Data Preparation Applications: It supports a defined perception, estimation, planning, control, interaction, or autonomy objective within system constraints.
Report a mistake

Q43. A robotics team is working with Data Preparation Applications. Which approach is most appropriate? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ASkip physical validation once software runs successfully.
  2. BDefine requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.
  3. CSelect hardware and algorithms before defining the task.
  4. DIgnore operating conditions because simulation covers all cases.
Show answer
Answer: B. Define requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.Machine Learning → Data Preparation → Data Preparation Applications: Define requirements and operating conditions, model the relevant system, implement the method, and validate it with representative tests.
Report a mistake

Q44. Which principle best supports correct modeling involving Data Preparation Applications? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIgnore coordinate frames if numerical values look reasonable.
  2. BUse any model regardless of its assumptions.
  3. CTreat uncertainty and dynamics as irrelevant to robotic systems.
  4. DUse a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.
Show answer
Answer: D. Use a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.Machine Learning → Data Preparation → Data Preparation Applications: Use a model whose assumptions, coordinate conventions, dynamics, uncertainty, and boundary conditions match the system being analyzed.
Report a mistake

Q45. Which consideration is most important when designing a system involving Data Preparation Applications? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AChoose the most complex architecture even when requirements are simple.
  2. BBalance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.
  3. CAlways maximize speed regardless of safety or power.
  4. DIgnore sensing limitations when selecting control methods.
Show answer
Answer: B. Balance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.Machine Learning → Data Preparation → Data Preparation Applications: Balance task performance with sensing, computation, latency, power, mechanical limits, reliability, maintainability, and safety.
Report a mistake

Q46. How should an engineer verify work involving Data Preparation Applications? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ATest only one ideal condition.
  2. BAssume simulation proves all real-world behavior.
  3. CTreat successful compilation as complete system validation.
  4. DTest against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.
Show answer
Answer: D. Test against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.Machine Learning → Data Preparation → Data Preparation Applications: Test against explicit requirements using simulation and representative physical or data-driven experiments, with measurable acceptance criteria.
Report a mistake

Q47. When a problem related to Data Preparation Applications appears, what should be done first? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AIgnore logs and sensor data during diagnosis.
  2. BEstablish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.
  3. CReplace several components before collecting evidence.
  4. DAssume the first suspected cause is correct.
Show answer
Answer: B. Establish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.Machine Learning → Data Preparation → Data Preparation Applications: Establish the symptoms and operating conditions, collect sensor, software, or hardware evidence, then isolate likely causes systematically.
Report a mistake

Q48. Which evidence best supports a performance assessment involving Data Preparation Applications? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. AUse an unrelated metric because it is easy to measure.
  2. BReport results without stating test conditions.
  3. CAssume theoretical peak performance equals field performance.
  4. DUse task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.
Show answer
Answer: D. Use task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.Machine Learning → Data Preparation → Data Preparation Applications: Use task-relevant metrics measured under stated conditions, including accuracy, latency, robustness, repeatability, or control error as appropriate.
Report a mistake

Q49. Which trade-off should be considered when selecting an approach to Data Preparation Applications? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ASafety can always be traded away for higher speed.
  2. BBalance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.
  3. COnly maximum accuracy matters in every robot.
  4. DEnergy and latency never affect intelligent systems.
Show answer
Answer: B. Balance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.Machine Learning → Data Preparation → Data Preparation Applications: Balance performance with computational cost, energy, latency, robustness, precision, complexity, and safety requirements.
Report a mistake

Q50. Which practice best supports safe and responsible use of Data Preparation Applications? Context: BS Robotics & Intelligent Systems / Machine Learning / Data Preparation.

  1. ADisable safety limits during normal operation.
  2. BDeploy untested autonomous behavior around people.
  3. CIgnore foreseeable failure modes if average performance is high.
  4. DDefine operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.
Show answer
Answer: D. Define operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.Machine Learning → Data Preparation → Data Preparation Applications: Define operational limits, handle uncertainty and failures, protect people and equipment, document assumptions, and retain human oversight where needed.
Report a mistake