3.69. AI363 Autonomous Systems (Elective)

3.69. AI363 Autonomous Systems (Elective)

Figure 3.68: Connection Map. AI363 Autonomous Systems

3.69.1. Justification Back to top

This course covers principles of autonomous systems capable of independent perception, decision-making and action, including decision architectures, autonomous navigation, and safety-critical considerations.

3.69.2. Generales Goals Back to top

  1. Implement perception-decision-action pipelines
  2. Design motion planning systems
  3. Evaluate risks in safety-critical autonomous systems

3.69.3. Contribution to Outcomes Back to top

AG-C02) Ethics: Applies ethical principles and commits to professional ethics and the standards of professional computing practice. (Usage)
AG-C09) Design and Development of Solutions: Designs, implements, and evaluates solutions for complex computing problems. (Assessment)
AG-C12) Applies computer science theory and software development fundamentals to produce computer-based solutions. (Assessment)

3.69.4. Content Back to top

3.69.4.1. Autonomy Fundamentals (12 hours) [Skills AG-C09] Back to top

Bibliography: (Thrun et al., 2005b)

Topics

  1. Control architectures (sense-plan-act vs behavior-based)
  2. Simultaneous Localization and Mapping (SLAM)
  3. Bayesian filters (Kalman, Particle)

Learning Outcomes

  1. Implement localization filters [Usage]
  2. Evaluate control architectures [Assessment]
3.69.4.2. Autonomous Decision-Making (24 hours) [Skills AG-C09] Back to top

Bibliography: (Bojarski et al., 2016)

Topics

  1. End-to-end neural control
  2. Path planning (A*, RRT*)
  3. Reinforcement learning in robotics

Learning Outcomes

  1. Train vehicular control networks [Usage]
  2. Design hybrid logic-AI systems [Assessment]
3.69.4.3. Safety & Ethics (8 hours) [Skills AG-C09] Back to top

Bibliography: (Amodei et al., 2016)

Topics

  1. Cascading failures in autonomous systems
  2. Ethical "kill switch" mechanisms
  3. Regulations for autonomous vehicles

Learning Outcomes

  1. Analyze critical failure cases [Familiarity]
  2. Implement basic safeguards [Usage]

3.69.5. Bibliography Back to top

Thrun, S., Burgard, W., and Fox, D. (2005b). Probabilistic Robotics. MIT Press.

Bojarski, M., Testa, D. D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L., Monfort, M., Muller, U., Zhang, J., Zhang, X., Zhao, J., and Zieba, K. (2016). End to end learning for self-driving cars. arXiv:1604.07316.

Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., and Mané, D. (2016). Concrete problems in ai safety. In NeurIPS.

Spotted a typo, an outdated course, a broken link, or have a suggestion? Let us know.

Scan to open on your phone