Inferring Human Intent and Predicting Human Action in Human–Robot Collaboration
Authors:
Top Cited Papers
Open Access
- 10 July 2024
- journal article
- review article
- Published by Annual Reviews in Annual Review of Control, Robotics, and Autonomous Systems
- Vol. 7 (1) , 73-95
Abstract
Researchers in human–robot collaboration have extensively studied methods for inferring human intentions and predicting their actions, as this is an important precursor for robots to provide useful assistance. We review contemporary methods for intention inference and human activity prediction. Our survey finds that intentions and goals are often inferred via Bayesian posterior estimation and Markov decision processes that model internal human states as unobserved variables or represent both agents in a shared probabilistic framework. An alternative approach is to use neural networks and other supervised learning approaches to directly map observable outcomes to intentions and to make predictions about future human activity based on past observations. That said, due to the complexity of human intentions, existing work usually reasons about limited domains, makes unrealistic simplifications about intentions, and is mostly constrained to short-term predictions. This state of the art provides opportunity for future research that could include more nuanced models of intents, reason over longer horizons, and account for the human tendency to adapt.Keywords
This publication has 24 references indexed in Scilit:
- A Shared Control Method for Collaborative Human-Robot Plug TaskIEEE Robotics and Automation Letters, 2021
- Probabilistic Decision Model for Adaptive Task Planning in Human-Robot Collaborative Assembly Based on Designer and Operator IntentsIEEE Robotics and Automation Letters, 2021
- A Unified Bi-Directional Model for Natural and Artificial Trust in Human–Robot CollaborationIEEE Robotics and Automation Letters, 2021
- Human Posture Prediction During Physical Human-Robot InteractionIEEE Robotics and Automation Letters, 2021
- Reverse Psychology in Trust-Aware Human-Robot InteractionIEEE Robotics and Automation Letters, 2021
- A Scalable Approach to Predict Multi-Agent Motion for Human-Robot CollaborationIEEE Robotics and Automation Letters, 2021
- A Survey of Mental Modeling Techniques in Human–Robot TeamingCurrent Robotics Reports, 2020
- People's Adaptive Side-by-Side Model Evolved to Accompany Groups of People by Social RobotsIEEE Robotics and Automation Letters, 2020
- Action understanding as inverse planningCognition, 2009
- Trust, control strategies and allocation of function in human-machine systemsErgonomics, 1992