Goto

Collaborating Authors

 segment 3


CoRI: Communication of Robot Intent for Physical Human-Robot Interaction

arXiv.org Artificial Intelligence

We introduce CoRI, a pipeline that automatically generates natural language communication of a robot's upcoming actions directly from its motion plan and visual perception. Our pipeline first processes the robot's image view to identify human poses and key environmental features. It then encodes the planned 3D spatial trajectory (including velocity and force) onto this view, visually grounding the path and its dynamics. CoRI queries a vision-language model with this visual representation to interpret the planned action within the visual context before generating concise, user-directed statements, without relying on task-specific information. Results from a user study involving robot-assisted feeding, bathing, and shaving tasks across two different robots indicate that CoRI leads to statistically significant difference in communication clarity compared to a baseline communication strategy. Specifically, CoRI effectively conveys not only the robot's high-level intentions but also crucial details about its motion and any collaborative user action needed. Video and code of our project can be found on our project website: https://cori-phri.github.io/ .


MATLAB Master Class: Go from Beginner to Expert in MATLAB

#artificialintelligence

MATLAB (matrix laboratory) is one of the fundamental and leading programming language and is a must learn skill for anyone who want to develop a career in engineering, science or related fields. Excellent MATLAB programming skills is therefore a crucial factor in making or breaking your career. This course is designed from a perspective of a student who has no prior knowledge of MATLAB. The course starts from the very basic concepts and then built on top of those basic concepts and move towards more advanced topics such as visualization, exporting and importing of data, advance data types and data structures and advance programming constructs. To get the real feel of MATLAB in solving and analyzing real life problems, the course includes machine learning topics in data science and data preprocessing. To convert the source codes into meaningful pieces of softwares, the course also covers topics in building GUI's using GUIDE and App Designer utilities of matlab.


10.22.19 Episode 637 Segment 3 – The Good and the Bad of AI

#artificialintelligence

He says AI will change the world, but we need to contemplate how to put it to good use. At the end of the day, the job of AI is not to be a silver bullet, but to help people do a better job. He adds that we have to use AI from an inventive perspective. It isn't a question anymore, because the bad guys will use it against us.


10.01.19 Episode 634 Segment 3 – Trusting AI

#artificialintelligence

Peggy and Joshua Peschel, assistant professor of agricultural and biosystems engineering, Iowa State University, answer the question: Do people with more experience trust AI (artificial intelligence)? They identify how to make AI more trustworthy in every part of our lives, saying that it has to consistently work and there needs to be public awareness when it is being used.


09.03.19 Episode 630 Segment 3 – The Convergence of Tech and Gen Z

#artificialintelligence

He says Generation Z wants to see greater gratification and empowerment in the work they do and that they have an expectation that technology is going to be there.


01.08.19 Episode 596 Segment 3 – The Future of Food Science

#artificialintelligence

Peggy and Dr. Cathy Kapica, founder and CEO, The Awegrin Institute, discuss why food science is important--and how technology factors in. She says 2020 is the next update of the U.S. Dietary Guidelines, and they are the foundation of health nutrition and health messaging. She adds that food is the original medicine, and food does not become nutrition until it is eaten, and that artificial intelligence has helped to bring a more affordable and safe food supply.


10.02.18 Episode 583 Segment 3 – Future of Smart Devices

#artificialintelligence

Peggy wraps up the show by talking with Robin Raskin, founder, Living in Digital Times, who explains says users get frustrated when each device requires an app of its own. She reveals that there are already more devices than humans on the planet. As an example, a thermostat can be set, or it can learn behaviors about you and can save you money and time. The new generation of IoT devices will have some analytics and machine learning behind it to predict what you want. She also explains that some great things have happened in the IoT space for seniors and accessibility.