Lab: Harold Frank Hall 4148
Hong (Herbert) Cai
Ph.D. Candidate [CV]
Dept. of Electrical and Computer Engineering
University of California, Santa Barbara
M.S., University of California, Santa Barbara, 2015
B.Eng., Hong Kong University of Science and Technology, 2013
Email: hcai [at] ece.ucsb.edu
I am currently a 6th-year Ph.D. student under the supervision of Prof. Yasamin Mostofi. My main research interest is in the optimization of robot decision-making, with a focus on human-robot collaborations. I study how to learn and predict human performance based on collected large-scale human data. Such human predictions are then incorporated into the robot's decision-making to improve the overall collaboration performance. I also take into account other factors to jointly optimize the robotic operation, such as communication, path planning, and team coordination. Apart from robotics, I am also interested in learning and predicting image quality/error. In my research, I utilize tools from deep learning, computer vision, integer optimization, wireless channel modeling, optimal control, and statistical/probabilistic modeling, and try to develop new methodologies.
Paper Repository on Human-Robot Collaboration
We have compiled a paper repository to provide a comprehensive overview of the state-of-the-art of different aspects of human-robot collaboration. Please check out the repository for more details.
Released Data and Code for Predicting Human Visual Performance:
We have made publicly available our data and code for predicting human visual performance using machine learning, which is developed in our RSS16 paper. For more details, please check out the data and code site.
- H. Cai and Y. Mostofi, "When Human Visual Performance is Imperfect - How to Optimize the Collaboration between One Human Operator and Multiple Field Robots," Trends in Control and Decision-Making for Human-Robot Collaboration
Systems (Y. Wang and F. Zhang (Eds.)), Springer, 2017. [pdf]
- H. Cai and Y. Mostofi, "Human-Robot Collaborative Site Inspection under Resource Constraints," IEEE Transactions on Robotics, 2018. [pdf]
- U. Ali, H. Cai, Y. Mostofi, and Y. Wardi, "Motion-Communication Co-optimization with Cooperative Load Transfer in Mobile Robotics: An Optimal Control Perspective," IEEE Transactions on Control of Network Systems, 2018. [pdf]
- E.Prashnani*, H. Cai*, Y. Mostofi, and P. Sen, "PieAPP: Perceptual Image-Error Assessment through Pairwise Preference," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [pdf][supplementary material][project page]
- H. Cai and Y. Mostofi, "Asking for Help with the Right Question by Predicting Human Visual Performance," Robotics: Science and Systems (RSS), 2016. [pdf][project page][data and models] (acceptance rate: 20.6%)
- H. Cai and Y. Mostofi, "A Human-Robot Collaborative Traveling Salesman Problem: Robotic Site Inspection with Human Assistance," American Control Conference (ACC), 2016. [pdf]
- U. Ali, H. Cai, Y. Mostofi, and Y. Wardi, "Motion and Communication Co-Optimization with Path Planning and Online Channel Estimation," American Control Conference (ACC), 2016. [pdf]
- H. Cai and Y. Mostofi, "To Ask or Not to Ask: A Foundation for the Optimization of Human-Robot Collaborations," American Control Conference (ACC), 2015.[pdf]
- Co-organized invited session "Human-Robot Collaborations: Opportunities and Challenges" at ACC 2016.
- Reviewer of IEEE Transactions on Robotics, IEEE Transactions on Signal Processing, IEEE Transactions on Mobile Computing, IEEE Journal on Selected Areas on Communications, IEEE Robotics and Automation Letters, IEEE Int'l Conference on Robotics and Automation, American Control Conference, IEEE Int'l Conference on Intelligent Transportation Systems, IEEE Int'l Conference on Global Communications.
Prof. Yasamin Mostofi's Homepage
Electrical & Computer Engineering at UCSB