Active Perception

Active Perception is the task of actively controlling the sensors of a system, e.g., a robot, to focus on regions of potential interest in the sensor date. The objective of active perception is to maximize the amount of information about the world. We develop information-theoretic and decision-theoretic approaches to plan where to look next.

More information about this topic can be found here and the corresponding publications are listed below.

Publications

Mikko Lauri, Frans A. Oliehoek: Multi-agent active perception with prediction rewards, in: Advances in Neural Information Processing Systems 33 (NeurIPS 2020). [PDF], [webpage], [code]
Lauri, M., Pajarinen, J., Peters, J., & Frintrop, S.: Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization. IEEE Robotics and Automation Letters, 2020. [arXiv], [webpage], [PDF]
Lauri, M., Pajarinen, J., & Peters, J.: Multi-agent active information gathering in discrete and continuous-state decentralized POMDPs by policy graph improvement. Autonomous Agents and Multi-Agent Systems, 34(42), 2020. [webpage], [code and more details]
Jan Fabian Schmid, Mikko Lauri, Simone Frintrop: Explore, Approach and Terminate: Evaluating Subtasks in Active Visual Object Search Based on Deep Reinforcement Learning, in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019, [PDF], [video], [code]
Simone Frintrop and Patric Jensfelt: Attentional Landmarks and Active Gaze Control for Visual SLAM, IEEE Transactions on Robotics, Special Issue on Visual SLAM, vol. 24, no. 5, Oct. 2008. Download the article here. If you don't have access, you can download a preprint here.
Simone Frintrop and Patric Jensfelt: Active Gaze Control for Attentional Visual SLAM, Proceedings of the IEEE 2008 International Conference Robotics and Automation (ICRA '08), Pasadena, California, May 2008 [PDF]