Optimizing Gaze Direction in a Visual Navigation Task
This addresses the challenge of active sensing in visual navigation for mobile robots, but it is incremental as it builds on existing POMDP and mutual information methods.
The paper tackled the problem of optimizing gaze direction for a mobile robot's visual navigation by modeling it as a POMDP with a mutual information reward, and demonstrated benefits through simulations and real robot experiments.
Navigation in an unknown environment consists of multiple separable subtasks, such as collecting information about the surroundings and navigating to the current goal. In the case of pure visual navigation, all these subtasks need to utilize the same vision system, and therefore a way to optimally control the direction of focus is needed. We present a case study, where we model the active sensing problem of directing the gaze of a mobile robot with three machine vision cameras as a partially observable Markov decision process (POMDP) using a mutual information (MI) based reward function. The key aspect of the solution is that the cameras are dynamically used either in monocular or stereo configuration. The benefits of using the proposed active sensing implementation are demonstrated with simulations and experiments on a real robot.