E-PashuHaat Transportal

GPMS TRANSPORTAL APPLIED AI COURSES

AI

Course 71:Multi Agent Interaction Design Metaverse

Duration - 36 Hours ( 6 Hours per week - 2 Hrs x 3)

Week 1 - The Role of the Server
Learning Outcome
What the server does in preserving and ensuring multiple agents can interact.
1.1 Client Server Interaction with Effective Division of Tasks.
1.2 Latency, Bandwidth, and common issues arising.
1.3 Preservation of states, and Data on server.

Practical Component
Practical Demonstrations on the role of the server, and complications that arise from incorrect planning and development.
Week 2 - Two User Case
Learning Outcome
Interaction design for two user cases, between users, and with objects
2.1 Nuances of custom interactions, and preserving changes in position across devices.
2.2 Potential of simultaneous interaction, and solutions.
2.3 Agent to Agent Interaction workflows

Practical Component
Understand the practical nuances having two agents interact with objects across the same environment, and how to ensure apt management of interactions, location, and space

Week 3 - Extending to AI Agents in Addition
Learning Outcome
increasing complexity through involving additional AI based agents that conduct interactions in addition to 2 users
3.1 Design an AI Agent Workflow.
3.2 Levels of Complexity, and Human Character-like behaviour achievability.
3.3 Live examples and case studies of AI Agent Workflows.

Practical Component
Practical Demonstrations showcasing the AI agents designed, and their behaviour and interaction, along with all practical nuances.
Week 4 - Multi Agent Scenarios
Learning Outcome
Allow for a large amount of agents to continually arrive at certain locations, and key consideration across interactions
4.1 Interaction design across multi agent scenarios.
4.2 Understanding common problems in Multi Agent Scenarios
4.3 Case Studies and Examples

Practical Component
Practical Understanding of how multi agent systems are built and experiences achieved.
Week 5 - Validation and Limitations
Learning Outcome
Common limitations when designing multi agent systems, and complex systems.
5.1 Local Storage versus Bandwidth.
5.2 Edge Case Scenarios, Delays, and incorrect rendering across machines
5.3 In accurate behaviour of agent, and design failure in dynamic scenarios.

Practical Component
Practical Nuances, and ensuring appropriate and sophisticated testing to ensure all scenario working through examples.
Week 6 - Project and Assessment
Learning Outcome
Here students work on a custom project of choice selected by the group to finish within a week from end to end with peer review, and complete presentation of outcomes.
6.1 Selection of multi agent story line, creation of assets, and experience through chosen methods
6.2 Initial Self Assessment, and Peer Assessment and review of outcomes
6.3 Final Presentations and Scoring of outcome Achieved.

Practical Component
Practical Demonstrations of student made models at various stages, with fixes, and live demonstrations to a committee of peers or prospective recruiters.