Active vision in robotic systems: A survey of recent developments

By Shengyong Chen, Youfu Li, N. Kwok. Int. J. Robotics Res., 2011

446 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering, Media Technology

View Paper: https://www.semanticscholar.org/paper/08a9c6d0a938fef5106caaed7dd8f11e8ee9e9d5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Industrial and Manufacturing Engineering

In Media Technology

Citations in the corpus

Personalized machine learning for robot perception of affect and engagement in autism therapy (2018, background): “Although the “active vision” view from the robot’s (moving) perspective would enable more naturalistic interactions, it poses a number of stabilization andmultiview challenges (48).”
Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching (2017, background): “Active perception – exploiting control strategies for acquiring data to improve perception [21], [22] – can facilitate the recognition of novel objects in clutter.”
Learning Visual Affordances for Robotic Manipulation (2019, background): “The act of exploiting control strategies for acquiring data to improve perception ([9, 16]) can facilitate the recognition of novel objects in clutter.”
Revisiting active perception (2016, background): “…been included; other relevant reviews and collections include Crowley et al. (1992), Aloimonos (1993), Christensen et al. (1993), Crowley and Christensen (1995), Vernon (2008), Dahiya et al. (2010), Chen et al. (2011) and Andreopoulos and Tsotsos Andreopoulos and Tsotsos (2013a, b), among others.”
Sampling-based robotic information gathering algorithms (2014, background): “Subsequent works have resulted in an extensive suite of solutions that incorporate information theoretic measures for problems like object recognition, mapping, and scene reconstruction (see (Chen et al., 2011) for a survey).”
Active vision for dexterous grasping of novel objects (2016, unknown): “For visually guided manipulation, researchers have devised strategies for view selection based on recovery of the full shape of the object to be grasped [14], [7].”