Author: zhexic

The most significant risks is the integration, which during our test, we found that sometimes the voice command was severely delayed due to unknown reasons, which only after several voice prompts, the corresponding output can be delivered. The current solution has been using multithreading to manage all long-delay tasks such as speaking the obstacle. The contingency plans including merge different voice prompt into one, spawn less process, and prioritize for high-important obstacles such as humans (since they are moving).

No change is made to the system design. No updates to the schedule. We are on track now for testing.

The most significant risk right now is training of the collected dataset. As the collected dataset will mostly be used to facilitate the accuracy in certain locations, where the collected data will actually improve detection accuracy will be significant to the meeting of the overall requirement. We manages those risks by trying to change the existing YOLO algorithm by slimming the output layers only for a limited amount of obstacles that might appear in hallway, and then, using public dataset will have a better effect.

We have not changed the block diagram as of now. Depend on the output accuracy of the training data, we might have to lower the accuracy and detection range due to hardware/software limitations.

The schedule is unchanged. We plan to deliver the model by Monday.

Team Status Report for 10/07

What are the most significant risks that could jeopardize the success of the
project? How are these risks being managed? What contingency plans are ready?

Sensor integrity within a short amount of time had posed challenges for our implementation of the design. As we are trying the test the LIDARS and Cameras, we realize that the LIDAR’s range change is dependent on the amount of light, so we need to factor the effect of solar power into our design. As we are still in the early stages of the design cycle those problems can be easily managed by autotuning the parameters depending on the camera light input level and internal API from realSense LIDAR.
Were any changes made to the existing design of the system (requirements, block diagram, system spec, etc)? Why was this change necessary, what costs does the change incur, and how will these costs be mitigated going forward?

There are no changes to the requirement since the design review presentation. We will continue to work to have one goal in mind.
Provide an updated schedule if changes have occurred.

N/A

Please enumerate one or more principles of engineering, science and mathematics that your team used to develop the design solution for your project.

To develop the design solution of the project, we have utilized system engineering principles of high-level designs and block diagrams to clarify the solution using high-level logic. Additionally, we utilized knowledge of software engineering to carry out the coding. We have utilized the idea of a controlled experiment to test out the behavior of the real-time LIDAR in different lighting conditions and environments. Then, we are developing a statistically based machine learning model to detect and tag the object, which is a mathematical model.