Design Review

Video Lecture

Video, Slides

Description

The design review is a 30-minute meeting intended to ensure that the team has a successful project. Students will present (using slides in tandem with their design document) and defend their design while instructors critique it, ask questions, and indentify any infeasible or unsafe aspects. Note that the instructors are not here to attack your design, but to straightforwardly inform you when you may be heading down an unsuccessful path.

Instructors and TAs will ask questions throughout and may choose the order of the blocks to be discussed. Specifically, here is what the course staff are primarily looking for:

  1. Evidence that the overall design and high-level requirements solve the problem stated.
  2. Check if the overall design has suitable difficulty for course standards and completion in one semester. Scope may need to be adjusted if otherwise.
  3. Check team members' engineering preparedness to implement each module.
  4. Check that each team member is assigned an equal portion of the project effort.

Prepare for the following sequence.

  1. Promptly project your slides or other content on projector.
  2. Introduce team members (name, major, and the project part each is in charge of).
  3. Present problem statement and proposed solution (<1 minutes) following the template in DDC (see Description 1.a)
  4. Present design overview (<5 minutes)
    1. High-level requirements: check DDC
    2. Block diagram: check DDC
    3. Physical design
  5. For the remainder of the review, you will participate in a detailed discussion of the design. Plan to cover each block, one at a time, beginning with the most critical. The course staff will ask questions and may step in to guide the discussion. Be prepared to discuss all aspects of your design with a focus on the following.
    1. Requirements & Verification: (see DDC); We'll look at all the important block requirements. Prepare to justify the components chosen and compare with important alternatives.
    2. Evidence that the design meets requirements (use the following as applicable)
      • Simulations
      • Calculations
      • Measurements
      • Schematics
      • Flowcharts
      • Mechanical drawings
      • Tolerance analysis: check DDC
      • Schedule: Suggestions:
        1. Think about what you can do in parallel, what has to be sequential;
        2. Work on hardware before software;
        3. Perform unit testing before system testing;
        4. Unit test each module on a breadboard before starting PCB design);
        5. Leave margin for unexpected delays or accidents. You are mostly responsible for those exceptions, just as if you were the owner of this senior design business;
      • Cost:hourly rate is ~$50 not $10. In addition, apply the 2.5x overhead multiplier ($125/hr is the cost of your senior design business), which includes the cost of salaries of you, your boss, CxOs, sales, janitors, etc.

Grading

The DR Grading Rubric is available to guide your DR preparation. Two sample Design Review documents are available as examples of what we expect: a Good Sample DR, a Moderate Sample DR, and a good example R&V table as it was presented in a final report. Notes are made in red type to point out what is lacking. Note that the grading rubrics and point structure may have evolved since these reports were generated, so use them only as a guide as to what we are generally expecting.

Submission and Deadlines

Your design review presentation should be ready before your Design Review. You do not need to upload this powerpoint to the course website. You will be graded on your live presentation on the day of the Design Review with the course staff.

An Intelligent Assistant Using Sign Language

Qianzhong Chen, Howie Liu, Haina Lou, Yike Zhou

Featured Project

# TEAM MEMBERS

Qianzhong Chen (qc19)

Hanwen Liu (hanwenl4)

Haina Lou (hainal2)

Yike Zhou (yikez3)

# TITLE OF THE PROJECT

An Intelligent Assistant Using Sign Language

# PROBLEM & SOLUTION OVERVIEW

Recently, smart home accessories are more and more common in people's home. A center, which is usually a speaker with voice user interface, is needed to control private smart home accessories. But a interactive speaker may not be the most ideal for people who are hard to speak or hear. Therefore, we aim to develop a intelligent assistant using sign language, which can understand sign languages, interact with people, and act as a real assistant.

# SOLUTION COMPONENTS

## Subsystem1: 12-Degree-of-Freedom Bionic Hand System

- Two moveable joints every finger driven by 5-V servo motors

- The main parts of the hand manufactured with 3D printing

- The bionic hand is fixed on a 2-DOF electrical platform

- All of the servo motors controlled by PWM signals transmitted by STM32 micro controller

## Subsystem2: The Control System

- The controlling system consists of embedded system modules including the microcontroller, high performance edge computing platform which will be used to run dynamic gesture recognition model and more than 20 motors which can control the delicate movement of our bionic hand. It also requires a high-precision camera to capture the hand gesture of users.

## Subsystem3: Dynamic Gesture Recognition System

- A external camera capturing the shape, appearance, and motion of objective hands

- A pre-trained model to help other subsystems to figure out the meaning behind the sign language. To be more specific, at the step of objects detection, we intended to adopt YOLO algorithm as well as Mediapipe, a machine learning framework developed by Google to recognize different sign language efficiently. Considering the characteristic of dynamic gesture, we also hope to adopt 3D-CNN and RNN to build our models to better fit in the spatio-temporal features.

# CRITERION OF SUCCESS

- The bionic hand can move free and fluently as designed, all of the 12 DOFs fulfilled. The movement of single joint of the finger does not interrupt or be interrupted by other movements. The durability and reliability of the bionic hand is achieved.

- The controlling system needs to be reliable and outputs stable PWM signals to motors. The edge computing platform we choose should have high performance when running the dynamic gesture recognition model.

- Our machine could recognize different sign language immediately and react with corresponding gestures without obvious delay.

# DISTRIBUTION OF WORK

- Qianzhong Chen(ME): Mechanical design and manufacture the bionic hand; tune the linking between motors and mechanical parts; work with Haina to program on STM32 to generate PWM signals and drive motors.

- Hanwen Liu(CompE): Record gesture clips to collect enough data; test camera modules; draft reports; make schedules.

- Haina Lou(EE): Implement the embedded controlling System; program the microcontroller, AI embedded edge computing module and implement serial communication.

- Yike Zhou(EE): Accomplish object detection subsystem; Build and train the machine learning models.