Learning Human Behavior Research Articles

Learning Human Behavior in Shared Control: Adaptive Inverse Differential Game Approach.

To enhance the collaborative intelligence of a machine, it is important for the machine to understand what behavior a human may adopt to interact with the machine when performing a task in shared control. In this study, an online behavior learning method is proposed for continuous-time linear human-in-the-loop shared control systems by using the system state data only. A two-player nonzero-sum linear quadratic dynamic game paradigm is used for modeling the control interaction between a human operator and an automation that actively compensates for human control action. In this game model, the cost function representing the human behavior is assumed to have an unknown weighting matrix. Here, we want to learn the human behavior or retrieve the weighting matrix by using the system state data only. Accordingly, a new adaptive inverse differential game (IDG) method, which integrates concurrent learning (CL) and linear matrix inequality (LMI) optimization, is proposed. First, a CL-based adaptive law and an interactive controller of the automation are developed to estimate the feedback gain matrix of the human online, and second, an LMI optimization problem is solved to determine the weighting matrix of the human cost function. Finally, simulation results on a cooperative shared control driver assistance system are provided to elucidate the feasibility of the developed method.

Online Learning Human Behavior for a Class of Human-in-the-Loop Systems via Adaptive Inverse Optimal Control

To enhance the machines’ intelligence, it is important for them to learn how humans perform tasks. In this article, the issue of online adaptive learning human behavior is addressed for a class of human-in-the-loop (HiTL) systems using the state measurement only. The hypothesis underlying our study is that human behavior can be described by a linear quadratic optimal control model with an unknown weighting matrix for the quadratic cost function. In this model, the weighting matrix depicts the human tradeoff of various objectives. Our aim is thus to only use the system state measurement for learning the weighting matrix under the condition that human feedback gain matrix is unknown. A novel adaptive inverse optimal control approach to online learning human behavior is proposed for the HiTL system, which integrates adaptive estimation and linear matrix inequality (LMI) optimization techniques. Our approach consists of two steps: First, an adaptive law is developed to learn the human feedback gain matrix online using the system state measurement only, and second, the weighting matrix of human cost function is retrieved by solving an LMI optimization problem with the learned feedback gain matrix. Finally, simulation and experiment results on a steering assist system of intelligent vehicles are presented to illustrate the effectiveness of the proposed method.

Robot learning through observation via coarse-to-fine grained video summarization

Learning human daily behavior is important for enabling robots to perform tasks and assist people. However, most prior work either requires specific sensors for capturing data or heavily relies on prior knowledge of human motion, which can be difficult to obtain. To alleviate the above problems, we propose a novel pipeline for robots to learn human behavior based on coarse-to-fine video summarization using a single Kinect camera. Specifically, the robot first retrieves information of general interest followed by a task-specific content retrieval, then focuses on fine-grained motion clips of human behavior, and guides itself by using an object-centric learning method to complete the desired task. Our work has three unique advantages: (1) it enables the robot to effectively capture granularity hierarchies of human behavior which efficiently exploits multi-stage information while alleviating disturbances and redundancies in visual data; (2) it obtains knowledge by focusing on object movements in summarized motion clips which does not require any prior knowledge of human motion; (3) it only requires a single Kinect sensor for the robot to learn human behavior which is fully accessible and easy to equip. Experiments in an office environment were performed to validate the efficiency and effectiveness of the proposed framework, and the results indicate that this approach exhibits good learning efficacy for the robot to understand human behavior and learn to perform tasks.