15-482: Autonomous Agents
Autonomous agents use perception, cognition, actuation, and learning to reliably achieve desired goals, where the agents can be smart homes, mobile robots, intelligent factories, self-driving cars, etc. The goal of this course is to provide students with the techniques needed for developing complete, integrated AI-based autonomous agents. Topics to be investigated include architectures for intelligent agents, task planning, reasoning under uncertainty, optimization, monitoring, execution, error detection and recovery, collaborative and adversarial multi-agent interaction, machine learning, ethical behavior, and explanation. The course is project-oriented where, over the course of the semester, small teams of students will design, implement, and evaluate autonomous agents operating in a real-world environment.
Prerequisites: 15-281 or 15-381 or 10-301 or 10-315 or permission by instructors.
Mondays and Wednesdays 12:00-1:20 in GHC 4102
Stephanie Rosenthal (srosenth@andrew), GHC 6019
- Office Hours: Tuesdays 3-4:30, Wednesdays 9-10:30, or by appointment
Reid Simmons (rsimmons@andrew), NSH 3213
We encourage the use of the textbook Artificial Intelligence: A Modern Approach
by Stuart Russell and Peter Norvig.
Students will work in groups to implement an autonomous greenhouse agent. The agent will be built
up through six assignments and deployed on our greenhouse architecture once a month.
Students will submit write-ups about their algorithm choices and implementation to be graded in simulation and through a real world deployment.
Deployments will also include a graded presentation and written report evaluating the deployment of the agent after the grow periods. Assignments will be submitted following the instructions on Canvas.
Grades will be collected and reported in Canvas. The final grade will be calculated as follows:
- 60% Project Assignments:
- Project code 30% (5% x 6 assignments)
- Grow period presentations/writeups 15% (5% x 3 periods)
- Grow period deployment 15% (5% x 3 periods)
- 20% Midterms (10% each)
- 15% Final Exam
- 5% Peer Evaluation