What did I do this week?
This week was focused on working with my teammates to make progress to our interim demo, as well as development focused on setting up the navigation system.
The first thing for the webapp development was to add a new model for the rooms in a building, storing the room’s name, floor, and position on a map (relative to the actual pixel locations on the floor plan map). Then, I added an API endpoint so that users would be able to “search” for a room to go to. With the backend done, I needed to provide the rooms to the front end of the server so the users would be able to select and search for them. To create the connection between the user and the server, I created a form to post the data (offering more security due to having a csrf token). Form submissions by default reload the page, which would interrupt the user experience, so I created a handler that would prevent the page from reloading, validate the form, before sending the form as an AJAX request to the server. The server would be doing further validation to make sure the data is safe before running its algorithms to process the data.
I made a graph of HH A-level, then focused on utilizing the A star algorithm I had written previously. To use it, I needed to write a breadth-first search algorithm to identify the closest portion of the graph to the user (due to the graph featuring only a narrow walkable section in the middle of the hallways). I just needed to call this code in my background endpoint to determine the navigation paths the user should take. The final task at hand was to visualize the paths on the frontend. This was mostly trivial due to previously experimenting with drawing lines on a canvas element.
The overall results seem to be fairly positive. The below video shows a demo of the system working, such that the webserver is running on my local machine and I have a script sending in “dummy data” for the user’s position. Entering a new room using the search bar sends the asynchronous request to the server, which responds with the path the user should take, and is drawn on the user’s map. My local machine takes approximately 150 ms to run the navigation algorithms, which is sufficient (to my surprise/dismay, the EC2 instance runs the algorithm faster than my local machine, despite being the cheapest option AWS offers).
Is my progress on schedule?
This week I made significant progress on the navigation system; crucially, I added the necessary core functionality for providing directions to users. Hence, my schedule is on track and aligns with what my team planned to do.
Next week’s deliverables:
Next week I would like to augment the application’s user interface to include human-readable user directions to tell the user when they should turn or how far they need to walk. The navigation system, in return, needs to be able to constantly track the user’s progress. It may be worth looking into ways to optimize the graph. For example, I could try scaling the graph down and seeing if there are any significant performance improvements. It is possible my team wants to try offloading some of the localization computation to the server; in this case, I would need to provide more assistance with the server.
Verification and Validation Tests:
My role on the team is primarily working on the user interface and the web application. This subsystem affects several of the tests we must run for verification and validation; particularly, navigation optimality, latency of localization updates, and quality of directions and user experience.
Navigation optimality refers to our navigational algorithm’s capability of generating the most efficient route for our users. Assuming the average walking speed is the same for all hallways, this ends up being the shortest paths between two points. I have already written the A* pathfinding algorithm for navigation and have spent time benchmarking its performance on graphs of buildings as well as verifying the paths it provides are indeed the shortest. In particular, the algorithm runs fairly quickly. It is able to find navigation paths within 100 ms on our webserver. In terms of verifying the algorithm is actually finding a shortest path, a significant amount of testing has been put in. Firstly, it is always able to find the shortest and simplest obvious path between two points. Then, it is capable of finding an optimal path when given multiple paths between targets. Next, it is more than capable of navigating around obstacles in the graph. Then, I have tested the algorithm in larger and more complicated graphs, comparing the result with Dijkstra’s algorithm (which runs slower than A* but is guaranteed to find the shortest path) to make sure both are equivalent, as well as making sure that the resulting path it finds is always less than or equal to a simple breadth first search algorithm.
Another facet of the webserver is low latency between the tag’s communication and the user’s front end. Through testing, this has been shown to take an average of 70 milliseconds to complete updating through our websocket. We want to have a latency between positional changes in real life to be reflected on the application’s user interface within 2000 ms. Hence, this information shows that there is plenty of “delay” that is still allowable from the perspective of the localization system.
Additionally, it typically only takes around 30 milliseconds for the tag to send the data. We initially stated we wished to have a total latency of the localization system and the server updates to take less than 500 ms, so this value gives my partners, who are working on the localization system, approximately 470 ms to work with. Further testing is needed with the RPi to determine the latency of the entire algorithm. With this information, we would be able to determine the maximum update frequency of the device, which we wish to be greater than 2 Hz.
The final tests revolve around the navigation system. Firstly, it should provide “distance” updates in a timely manner–at least once every two seconds to provide accurate estimates of how far the user should move. Then, we will need to run trials with our clients to garner feedback from them and a quantitative rating out of 5. If the feedback is positive, this would be an indicator that the navigation system is actually providing useful feedback to the users.