Towards Effective Human-AI Collaboration in GUI-Based Interactive Task Learning Agents
Li, Toby Jia-Jun, Chen, Jingya, Mitchell, Tom M., Myers, Brad A.
–arXiv.org Artificial Intelligence
We argue that a key challenge in enabling usable and useful interactive task learning for intelligent agents is to facilitate effective Human-AI collaboration. We reflect on our past 5 years of efforts on designing, developing and studying the SUGILITE system, discuss the issues on incorporating recent advances in AI with HCI principles in mixed-initiative interactions and multi-modal interactions, and summarize the lessons we learned. Lastly, we identify several challenges and opportunities, and describe our ongoing work
arXiv.org Artificial Intelligence
Mar-5-2020
- Country:
- Asia > Singapore (0.05)
- North America > United States
- Pennsylvania > Allegheny County
- Pittsburgh (0.06)
- Illinois > Cook County
- Chicago (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Pennsylvania > Allegheny County
- Genre:
- Research Report (0.64)
- Workflow (0.47)
- Technology: