Pervasive Artificial Intelligence Research (PAIR) Labs

Robotics & Sensing Technology

Pervasive Artificial Intelligence Research (PAIR) Labs

Robotics & Sensing Technology

NTNU – Professor Wei-Yen Wang

Principal Investigator: Prof. Wei-Yen Wang

Research :

Development of Theory and Systems of Robot Learning from Human Demonstration (LfD)-Development of Learning from Human Demonstration Robot

Core Technologies

This project proposes a learning from demonstration (LfD) system that allows robots to be not only taught by human via demonstration but also adjusted by themselves. Moreover, a multimodal perception approach is provided so that the robotic arm can perform flexible automation without complicated coding by professionals. In addition, an edge AI chip is implemented to increase the overall performances and flexibility, expanding the potential of the system to be incorporated with other applications. In the future, we will not only focus on vision-based tasks but also consider other scenarios where voice is required to be learned in the LfD system.

Applications

Smart factory/workshop, smart home, collaborative robots, cultural and scientific development, terminal equipment applications

Technology Transfer

1. We develop the safe and robust mobile robot navigation strategies for an automated guided vehicle in industrial applications.
2. A multimodal perception approach is provided so that the robotic arm can perform flexible automation.

Technologies with Potential for Technology Transfer or Industry-Academia Collaboration

1. A novel hypothesis generation model is proposed to emulate a human cognition system, solving tasks using previous learning experiences.
2. This project implements the proposed intelligent algorithms on an edge AI chip to increase the overall performances and flexibilities, expanding the potential of the system to be incorporated with other applications.

Proposal for Industry-Academia Collaboration

1. The developed AGV incorporates several capabilities to navigate freely between stations while avoiding obstacles and coordinating with the remote control center.
2. We utilize a set of training tools provided by AVSdsp, and the trained model can be loaded into an AI chip to perform a task of detecting human heads.