Revisiting active perception

@article{Bajcsy2018RevisitingAP,
  title={Revisiting active perception},
  author={Ruzena Bajcsy and Yiannis Aloimonos and John K. Tsotsos},
  journal={Autonomous Robots},
  year={2018},
  volume={42},
  pages={177 - 196}
}
Despite the recent successes in robotics, artificial intelligence and computer vision, a complete artificial agent necessarily must include active perception. A multitude of ideas and methods for how to accomplish this have already appeared in the past, their broader utility perhaps impeded by insufficient computational power or costly hardware. The history of these ideas, perhaps selective due to our perspectives, is presented with the goal of organizing the past literature and highlighting… 
Simultaneous Learning of Moving and Active Perceptual Policies for Autonomous Robot
TLDR
In this paper, a reinforcement learning algorithm is proposed to make the robots have the perceptual ability and can obtain better perceptual behavior and achieve higher success rates than conventional reinforcement learning algorithms.
A review of space perception applicable to artificial intelligence robots
Numerous space perception studies have shown that Euclidean 3-D structure cannot be recovered from binocular stereopsis, motion, combination of stereopsis and motion, or even with combined multiple
Insect-inspired AI for autonomous robots.
TLDR
It is argued that inspiration from insect intelligence is a promising alternative to classic methods in robotics for the artificial intelligence needed for the autonomy of small, mobile robots and that even for neuromorphic processors, one should not simply apply existing AI algorithms but exploit insights from natural insect intelligence to get maximally efficient AI for robot autonomy.
Active Perception with Neural Networks
TLDR
This report highlights recent progress in employing active perception based on neural networks for single and multi-agent systems.
Teaching Perception
TLDR
A robotic system whose behavioral policy can be set by verbal instructions it receives is described, and its capabilities are demonstrated in an associated video showing the fully implemented system guiding the perception of a physical robot in simple scenario.
Human-Centric Active Perception for Autonomous Observation
  • David Kent, S. Chernova
  • Computer Science
    2020 IEEE International Conference on Robotics and Automation (ICRA)
  • 2020
TLDR
This work forms a novel Semi-MDP formulation of the autonomous human observation problem that maximizes observation rewards while accounting for both human- and robot-centric costs, and demonstrates that the problem can be solved with both scalarization-based Multi-Objective MDP methods and Constrained MDP Methods.
Bio-inspired robot perception coupled with robot-modeled human perception
TLDR
The overarching research goal is to provide robots with perceptional abilities that allow interactions with humans in a human-like manner and it is useful to study the principles of the human visual system to develop new computer vision algorithms and validate their effectiveness in intelligent robotic systems.
Planning Algorithms for Multi-Robot Active Perception
TLDR
Dec-MCTS is a novel, decentralised variant of the widely-used Monte Carlo tree search algorithm, and also leverages ideas from variational methods to plan over probability distributions of action sequences, which is designed to improve the systemlevel performance of multi-robot systems on many fronts.
GapFlyt: Active Vision Based Minimalist Structure-Less Gap Detection For Quadrotor Flight
TLDR
This philosophy is used to design a minimalist sensorimotor framework for a quadrotor to fly through unknown gaps without an explicit 3-D reconstruction of the scene using only a monocular camera and onboard sensing.
Tactile Perception And Visuotactile Integration For Robotic Exploration
TLDR
This work proposes and evaluates a learning-based method for visuotactile integration for grasping and investigates in making the tactile modality, local and slow by nature, more efficient for the task by predicting the most cost-effective moves using active exploration.
...
...

References

SHOWING 1-10 OF 203 REFERENCES
Active vision in robotic systems: A survey of recent developments
TLDR
A broad survey of developments in active vision in robotic applications over the last 15 years is provided, e.g. object recognition and modeling, site reconstruction and inspection, surveillance, tracking and search, as well as robotic manipulation and assembly, localization and mapping, navigation and exploration.
Attention and Visual Search: Active Robotic Vision Systems that Search
Visual attention is a multi-faceted phenomenon, playing different roles in different situations and for different processing mechanisms. Regardless, attention is a mechanism that optimizes the search
Purposive and qualitative active vision
  • Y. Aloimonos
  • Computer Science
    [1990] Proceedings. 10th International Conference on Pattern Recognition
  • 1990
TLDR
The traditional view of the problem of computer vision as a recovery problem is questioned, and the paradigm of purposive-qualitative vision is offered as an alternative and the design of the Medusa of CVL is described.
Active Perception in Virtual Humans
TLDR
This work proposes and demonstrates a new paradigm for active vision research which draws upon recent advances in the fields of artificial life and computer graphics, and describes a prototype animat vision implementation within realistic virtual human soldiers situated in a virtual environment.
Active Perception
TLDR
The seven chapters in this volume present various aspects of active perception, ranging from general principles and methodological matters to technical issues related to navigation, manipulation, recognition, learning, planning, reasoning, and topics related to the neurophysiology of intelligent systems.
Animat vision: Active vision in artificial animals
TLDR
This work proposes and demonstrates a new paradigm for active vision research that draws upon recent advances in the fields of artificial life and computer graphics, and describes an initial animat vision implementation within lifelike artificial fishes inhabiting a physics-based, virtual marine world.
Active Sensor Planning for Multiview Vision Tasks
TLDR
The sensor planning presented in this book describes an effective strategy to generate a sequence of viewing poses and sensor settings for optimally completing a perception task and will give the robot vision system the adaptability needed in many practical applications.
A mobius automation: an application of artificial intelligence techniques
TLDR
The main theme of the research is the integration of the necessary planning systems, models of the world, and sensory processing systems into an efficient whole capable of performing a wide range of tasks in a real environment.
Visual Saliency Improves Autonomous Visual Search
TLDR
This paper describes a method of visual search that exploits the use of attention in the form of a saliency map to update the probability distribution of which areas to examine next, increasing the utility of spatial volumes where objects consistent with the target's visual saliency are observed.
A Mobile Automaton: An Application of Artificial Intelligence Techniques
TLDR
The main theme of the research is the integration of the necessary planning systems, models of the world and sensory processing systems into an efficient whole capable of performing a wide range of tasks in a real environment.
...
...