-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
31 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,31 @@ | ||
--- | ||
title: "Progress Meeting Notes 05/21" | ||
tags: PhD Robotics LLM RAG | ||
categories: PhD | ||
imgUrl: /assets/source/image/blog/ | ||
--- | ||
|
||
|
||
## Progresses | ||
|
||
- Implemented Manual Control | ||
- Replaced distance sensors with Lidar data line plots saving | ||
- Reworked Safety Module based on the lidar data | ||
- developed LLM hard-coded pipeline | ||
- Will test the pipeline with LLM once the prompt design is finished | ||
|
||
## Issues | ||
|
||
- VWSetSpeed has deviations in time | ||
- May be due to the time taken to set the speed | ||
- Try turning 180 degrees - with 60 degree/s, 3 seconds, only approximately 120 degrees turned | ||
- Graph for RAG | ||
- Human psychology seems a good idea to prompt LLM | ||
- how to collect data | ||
- from camera image / bird view screenshots, then feed into LLM to get a description of the scene and store | ||
into the database | ||
- How to construct the graph | ||
- we have spatial / temporal relationships, but can be inferred from csv data already. | ||
- | ||
- ontology? | ||
|