Active vision in robotic systems: A survey of recent developments

  title={Active vision in robotic systems: A survey of recent developments},
  author={Shengyong Chen and Youfu Li and Ngai Ming Kwok},
  journal={The International Journal of Robotics Research},
  pages={1343 - 1377}
In this paper we provide a broad survey of developments in active vision in robotic applications over the last 15 years. With increasing demand for robotic automation, research in this area has received much attention. Among the many factors that can be attributed to a high-performance robotic system, the planned sensing or acquisition of perceptions on the operating environment is a crucial component. The aim of sensor planning is to determine the pose and settings of vision sensors for… 

View planning in robot active vision: A survey of systems, algorithms, and applications

Some basic concepts of active robot vision are summarized, representative work on systems, algorithms and applications from four perspectives are reviewed from three perspectives: object reconstruction, scene reconstruction, object recognition, and pose estimation.

Coverage Planning for Robotic Vision Applications in Complex 3D Environment

This thesis developed view planning methods that generate candidate viewpoints using randomized sampling-based and Medial Object-based methods that led to better results with fewer required viewpoints and higher coverage ratios.

Scene perception and motion planning through robotic vision

This thesis aims to apply the theoretical concepts of the coverage strength model in order to achieve a task using robotic vision such that the robotic arm does not collide with an obstacle while performing its operation.

Active Vision via Extremum Seeking for Robots in Unstructured Environments: Applications in Object Recognition and Manipulation

A novel active vision strategy is proposed for optimizing the viewpoint of a robot’s vision sensor for a given success criterion based on extremum seeking control, which is model free and does not require an explicit objective function or any other task model to calculate the gradient direction for viewpoint optimization.

Active Vision for Robot Manipulators Using the Free Energy Principle

This paper casts the problem of active vision as active inference, which states that an intelligent agent maintains a generative model of its environment and acts in order to minimize its surprise, or expected free energy according to this model, to an object-reaching task for a 7-DOF robotic manipulator with an in-hand camera to scan the workspace.

Planning Algorithms for Multi-Robot Active Perception

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.

A Taxonomy of Vision Systems for Ground Mobile Robots

A global picture of the state of the art in the area is offered and some promising research lines are discovered, namely in order to respond to the main questions posed when designing robotic vision systems.

Active In-Hand Object Recognition on a Humanoid Robot

A perception-driven exploration and recognition scheme for in-hand object recognition implemented on the iCub humanoid robot and it is demonstrated that objects are recognized faster and at the same time with a higher accuracy.

Actively Mapping Industrial Structures with Information Gain-Based Planning on a Quadruped Robot

An online active mapping system to enable a quadruped robot to autonomously survey large physical structures, and describes the perception, planning and control modules needed to scan and reconstruct an object of interest, without requiring a prior model.

Active Object Detection Through Dynamic Incorporation of Dempster-Shafer Fusion for Robotic Applications

An active vision object detection system is proposed on a robotic environment that uses a 3D camera mounted on the robot head and an RGB camera on its hand to detect and recognize objects being seen from the head camera, while computing a confidence score on the classification.



Active Sensor Planning for Multiview Vision Tasks

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 survey of sensor planning in computer vision

A survey of research in the area of vision sensor planning is presented, and a brief description of representative sensing strategies for the tasks of object recognition and scene reconstruction are presented.

The MVP sensor planning system for robotic vision tasks

This paper presents a technique that poses the vision sensor planning problem in an optimization setting and determines viewpoints that satisfy all previous requirements simultaneously and with a margin and presents experimental results of this technique when applied to a robotic vision system that consists of a camera mounted on a robot manipulator in a hand-eye configuration.

Automatic sensor placement for model-based robot vision

  • Shengyong ChenY. F. Li
  • Computer Science
    IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
  • 2004
A Viewpoint Planner is developed to generate the sensor placement plan, which includes many functions, such as 3-D animation of the object geometry, sensor specification, initialization of the viewpoint number and their distribution, viewpoint evolution, shortest path computation, scene simulation of a specific viewpoint, parameter amendment.

Active-Vision for the Autonomous Surveillance of Dynamic, Multi-Object Environments

This paper presents a novel method for active-vision-based sensing-system reconfiguration for the autonomous surveillance of an object-of-interest as it travels through a multi-object dynamic

Visual search for an object in a 3D environment using a mobile robot

Computing Camera Viewpoints in an Active Robot Work Cell

A dynamic sensor-planning system that is capable of planning the locations and settings of vision sensors for use in an environment containing objects moving in known ways is presented.

Survey and analysis of multimodal sensor planning and integration for wide area surveillance

Although sensor planning in computer vision has been a subject of research for over two decades, a vast majority of the research seems to concentrate on two particular applications in a rather

Generalized Multi-sensor Planning

This paper addresses and enhances the state-of-the-art in the analysis of scenarios where there are dynamically occuring objects capable of occluding each other, and develops a generic framework for sensor planning, which can then be customized for a particular task.

Monocular Vision for Mobile Robot Localization and Autonomous Navigation

A new real-time localization system for a mobile robot that shows that autonomous navigation is possible in outdoor situation with the use of a single camera and natural landmarks and a three step approach is presented.