Project
# | Title | Team Members | TA | Documents | Sponsor |
---|---|---|---|---|---|
38 | MassageMate: Smart Robot Masseur |
Jack Bai Ke Xu Wentao Yao Xiuyuan Zhou |
Yutao Zhuang | design_document1.pdf final_paper2.pdf proposal1.pdf |
Liangjing Yang |
# Team Members + Ke Xu [kex5] + Hao Bai [haob2] + Wentao Yao [wentaoy4] + Xiuyuan Zhou [xiuyuan5] # PROBLEM + High-intensity work tends to cause fatigue in people’s neck and waist, so they need massage to relax their shoulders and neck, but frequent visits to massage parlors cost quite time and are expensive. + With the growing need of massage, the quantity and quality of human massagers are hard to meet the demand, especially personalized customization. + Some customers may not want to be touched by an unfamiliar person (i.e. a real human Masseur), or they have some body privacy that hope to be hidden from others, then a Robotic Masseur can help. # SOLUTION OVERVIEW + The proposed solution involves utilizing a high-resolution Automatic Speech Recognition (ASR) module to accurately convert speech to text. The resulting text will be structured and analyzed using Codex, with the Code4Struct methodology proposed by Xingyao W. et. al. applied for enhanced understanding. + Task slots will be generated through slot filling, a method commonly used in task-oriented dialog systems, allowing for seamless integration with OpenCR, a powerful platform for robotics. OpenCR will be utilized to instantiate the robot tasks, with each task assigned to a Resp Pi device. + Finally, the Resp Pi device will be leveraged to physically activate the robot, enabling it to move and perform the assigned tasks. This comprehensive solution offers a professional and efficient method for integrating ASR technology and robotics for enhanced performance and automation. # SOLUTION COMPONENTS ## SUBSYSTEM I: MECHANICAL SYSTEM + OpenManipulator Robotic Arm + Customed Robotic Hands for specific needs of Massage ## SUBSYSTEM II: CONTROL SYSTEM + Resp Pi/Control panel that is Compatible with Robotic Arm + PC with GPT-3 key ## CRITERION FOR SUCCESS + The robotic arm can doing massage in appropriate strength and location under the control of certain instructions. + Build a phone APP that can monitor the current massage status, including force, frequence, position, etc. + Successfully parse the natural language given by the human into structured dialog state and further into natural language # DISTRIBUTION OF WORK + Ke Xu: hardware (Resp Pi & OpenCR) + Wentao Yao: hardware-software interfaces (Resp Pi & OpenCR) + Hao Bai: slot filling, dialog management (API layer, Python strategies) + Xiuyuan Zhou: hardware (Robotic) |