Ecological Active Vision: Four Bioinspired Principles to Integrate Bottom–Up and Adaptive Top–Down Attention Tested With a Simple Camera-Arm Robot

Abstract

Vision gives primates a wealth of information useful to manipulate the environment, but at the same time it can easily overwhelm their computational resources. Active vision is a key solution found by nature to solve this problem: a limited fovea actively displaced in space to collect only relevant information.Here we highlight that in ecological conditions this solution encounters four problems: (1) the agent needs to learn where to look based on its goals; (2) manipulation causes learning feedback in areas of space possibly outside the attention focus; (3) good visual actions are needed to guide manipulation actions, but only these can generate learning feedback; (4) a limited fovea causes aliasing problems. We then propose a computational architecture ('BITPIC') to overcome the four problems, integrating four bioinspired key ingredients: (1) reinforcement-learning fovea-based top-down attention; (2) a strong vision-manipulation coupling; (3) bottom-up periphery-based attention; (4) a novel action-oriented memory. The system is tested with a simple simulated cameraarm robot solving a class of search-and-reach tasks involving colour-blob 'objects'. The results show that the architecture solves the problems, and hence the tasks, very efficiently, and highlight how the architecture principles can contribute to a full exploitation of the advantages of active vision in ecological conditions.

Bio-Inspired Embedded Vision System for Autonomous Micro-Robots: The LGMD Case

“…In robotics, there have been different visual based navigation and guidance modules proposed [41]- [43]. Nowadays, as the image sensors and micro-controllers are becoming cheaper and more reliable, embedded vision modules are getting popular in intelligent device applications [28], [44]- [46] to enhance their navigation performance.…”

Generalisation, decision making, and embodiment effects in mental rotation: A neurorobotic architecture tested with a humanoid robot

“…Last, the model attention processes are currently hardwired, wherein they could be guided by bottom-up mechanisms based on the features of the image and top-down mechanisms related to the goals of the agent (Ognibene and Baldassare, 2015). Notwithstanding these limitations, the model proposed gives a relevant contribution to the current state-of-the-art with respect to the formulation of an integrated set of hypotheses on the neural mechanisms and processes that may underlie mental rotation in humans.…”

Proactive Intention Recognition for Joint Human-Robot Search and Rescue Missions Through Monte-Carlo Planning in POMDP Environments

“…Active Perception and Active Vision Active Perception is the problem of actively controlling sensors to improve the speed and accuracy in the estimation of behaviourally relevant variables [17,27]. Its applications are numerous, spanning from inspection and localization, to object recognition and autonomous driving, and not only limited to robotics.…”