Project

# Title Team Members TA Documents Sponsor
9 Robot Vacuum
 Kailong Jin
Long Chang
Tianyu Zhang
Zheyi Hang
 Tielong Cai design_document2.pdf
final_paper2.pdf
other11.pdf
proposal1.pdf
 Meng Zhang
**Team Members**

Tianyu Zhang tianyu7
Long Chang longc2
Zheyi Hang zheyih2
Kailong Jin kailong3


**Project Title**

Robot Vacuum


**Problem Description**

As technology evolves, robot vacuums are gradually evolving from having only a single sweeping function to having a certain level of intelligence, including laser navigation as well as home map building. But the fact is, in the daily use of robot vacuums, there are still problems such as easy to fall, cannot completely sweep all space. Many large companies are working hard to develop new robot vacuums, which are expected to greatly reduce the work that workers need to do personally, freeing people's hands for a long time and meeting people's expectations of the value of "robots".


**Solution Overview**

The idea is to solve four problems with existing robot vacuums. Automatically steer the robot at the edge of the stairs by adding a mechanical structure. Improve the suspension structure of the robot vacuum to give it better pass ability. By designing a linkage system with the elevator, the robot vacuum can perform multi-floor sweeping operations. In addition, we will optimize the 3D vision of today's robot vacuums and optimize the pathfinding algorithm. This will allow the robot to become powerful enough to really free people's hands.


**Solution Components**

*Anti-fall steering subsystem*
- It allows the robot to automatically turn when it approaches the edge of stairs to avoid falling and this function is completely mechanical and does not require software.
- The robot has a four-wheel structure and is driven by the rear wheels. The front wheels are set to a cone shape.
- An extra steering wheel is installed on the chassis, with a rough rubber surface to provide sufficient friction. The direction of steering wheel is perpendicular to the forward direction and is linked to the rear wheel, which provides power. The steering wheel is slightly higher than the four wheels and does not contact the ground during normal progress.
- As the robot approaches the edge of the stairs, the conical front wheels will be the first to detangle from the platform, causing the chassis to lower. The steering wheel contacts the ground of the platform and turns quickly to avoid falling.

*Low obstacles passing subsystem*
- The system allows the robot to pass low thresholds or obstacles to avoid getting stuck during the cleaning process.
- This function requires the use of infrared sensor, steering gear and mechanical structure coordination.
- We will redesign the structure of the connection between the wheel and the main body of the robot. The connector will be set as a folding telescopic structure, which can be powered by the steering engine to temporarily raise the main body of the robot.
- Infrared sensors will be used to detect the height of obstacles in front of the robot to determine whether to turn or pass.

*Elevator Interaction Subsystem*
- Signal sender and receiver to interact with the elevator.
- State machine inside the robot to control the robot's behavior.
- Simple elevator (for demo only) with signal sender and receiver to interact with the robot.

*Effective Path Finding Subsystem*
- Laser sensor to capture and store the 3D/2D surrounding information.
- Path decision algorithm inside programmable chip based on archived 3D/2D surrounding information that can make wise decisions on low obstacles.


**Criterion for Success**
- When approaching the edge of stairs, the robot automatically turns to avoid falling.
- The robot can pass 1-2cm high thresholds or obstacles smoothly without getting stuck.
- When finishing the cleaning work of one floor, the robot can call for the elevator to send itself to the next floor to continue its cleaning work.
- The robot adopts an algorithm developed by us to find the most effective route considering the existence of low obstacles.


**Intra-group Division of Labor**
- Long is in charge of the implementation of the Anti-fall steering subsystem and the mechanical structure of the elevator.
- Zheyi is in charge of the implementation of the Low obstacles passing subsystem and the overall mechanical structure of our robot.
- Kailong is in charge of the implementation of the Elevator Interaction Subsystem.
- Tianyu is in charge of the implementation of the Effective Path Finding Subsystem and the overall software component of our robot.

Intelligent Texas Hold 'Em Robot

Xuming Chen, Jingshu Li, Yiwei Wang, Tong Xu

Featured Project

## Problem

Due to the severe pandemic of COVID-19, people around the world have to keep a safe social distance and to avoid big parties. As one of famous Poker games in the western world, the Texas Hold’em is also influenced by the pandemic and tends to turn to online game platform, which, unfortunately, brings much less real excites and fun to its players. We hope to develop a product to assist Poker players to get rid of the limit of time and space, trying to let them enjoy card games just as before the pandemic.

## Solution Overview

Our solution is to develop an Intelligent Texas Hold’em robot, which can make decisions in real Texas poker games. The robot is expected to play as an independent real player and make decisions in game. It means the robot should be capable of getting the information of public cards and hole cards and making the best possible decisions for betting to get as many chips as possible.

## Solution Components

-A Decision Model Based on Multilayer Neural Network

-A Texas Hold'em simulation model which based on traditional probabilistic models used for generating training data which are used for training the decision model

-A module of computer vision enabling game AI to recognize different faces and suits of cards and to identify the game situation on the table.

-A manipulation robot hand which is able to pick, hold and rotate cards.

-Several Cameras helping to movement of robot hand and the location of cards.

## Criterion for Success

- Training a decision model for betting using deep learning techniques (mainly reinforcement learning).

- Using cv technology to transform the information of public cards and hole cards and the chips of other players to valid input to the decision-making model.

- Using speech recognition technology to recognize other players’ actions for betting as valid input to the decision model.

Using the PTZ to realize the movement of the cameras which are used to capture the information of pokers and chips.

- Finish the mechanical design of an interactive robot, which includes actions like draw cards, move cards to camera, move chips and so on. Utilize MCU to control the robot.

Project Videos