Differences

This shows you the differences between two versions of the page.

--- 2025-26:summer [2025/04/18 15:53] – [Enhanced avatar for human-robot interaction] alomari
+++ 2025-26:summer [2025/04/18 15:54] (current) – [Indoor navigation for an omnidirectional robot] alomari
@@ Line 368: / Line 368: @@
 ----
-==== Indoor navigation for an omnidirectional robot  ====
+==== Leveraging local LLMs for interactive office assistance  ====
 **[added 2025-04-18]**
@@ Line 379: / Line 379: @@
 **Project Description:**
-Point to point navigation in an indoor environment requires solutions to a number of problems related to mapping, pose estimation and path planning. Fortunately, existing libraries now exist that support all of these tasks. This project involves deploying standard navigation tools on an omnidirectional robot in the lab and then developing appropriate interfaces to enable an individual to provide high-level instructions to the robot to engage in point-to-point navigation in a previously mapped space.
+Avatars have been proposed as a key element in user interface designs since the development of Microsoft's Clippy, if not before. In the lab, we have been developing a Unity-based avatar that operates as the front end of a LLM-based avatar that can be deployed in various environments. This forward facing avatar provides a natural interaction with individuals in the environment, providing audio-based input and output and literally putting a face on the underlying system. The basic goal of the project is to take the operational system and to enhance it in a number of ways, perhaps most critically through the addition of individual and group-specific control of the avatar interaction structure. Interest in LLMs and Langchain-based user group aware conversational agents.
 **Required skills or prerequisites:**
   - Ability to work independently and as part of a team.
-  - Knowledge of ROS would be helpful
+  - Knowledge/interest in Unity and C# programming
   - Ability to work with external partners