Inverse Reinforcement Learning with Multi-Relational Chains for Robot-Centered Smart Home
This work addresses robot autonomy in smart homes, but it is incremental as it builds on existing inverse reinforcement learning techniques with a specific application focus.
The authors tackled the problem of enabling a robot to imitate human behaviors in a dynamic smart home environment by using multi-relational chains and inverse reinforcement learning to learn a reward function, resulting in improved accuracy in home state evaluation and robot action selection compared to a baseline method.
In a robot-centered smart home, the robot observes the home states with its own sensors, and then it can change certain object states according to an operator's commands for remote operations, or imitate the operator's behaviors in the house for autonomous operations. To model the robot's imitation of the operator's behaviors in a dynamic indoor environment, we use multi-relational chains to describe the changes of environment states, and apply inverse reinforcement learning to encoding the operator's behaviors with a learned reward function. We implement this approach with a mobile robot, and do five experiments to include increasing training days, object numbers, and action types. Besides, a baseline method by directly recording the operator's behaviors is also implemented, and comparison is made on the accuracy of home state evaluation and the accuracy of robot action selection. The results show that the proposed approach handles dynamic environment well, and guides the robot's actions in the house more accurately.