Visual Servoing in the Large

Abstract

In this paper we consider the problem of maneuvering an autonomous robot in complex unknown environments using vision. The goal is to accurately servo a wheeled vehicle to a desired posture using only feedback from an on-board camera, taking into account the nonholonomic nature of the vehicle kinematics and the limited field-ofview of the camera. With respect to existing visual servoing schemes, which achieve similar goals locally (i.e. when the desired and actual camera views are sufficiently similar), we propose a method to visually navigate the robot through an extended visual map before eventually reaching the desired goal. The map comprises a set of images, previously stored in an exploratory phase, that convey both topological and metric information regarding the connectivity through feasible robot paths and the geometry of the environment, respectively. Experimental results on a laboratory setup are reported showing the practicality of the proposed approach

Visual navigation with obstacle avoidance

“…Here, we report the experiments obtained with controller (14) and shown in the video attached to this paper. All experiments have been carried out on a CyCab robot equipped with a 70…”

“…The two other specifications are ensured by v and ω: the linear velocity is reduced (and even zeroed to v = v u = 0, for H = 1), while the angular velocity aligns the robot with f . 3) Control law (14) can also be derived using a redundancy-based framework, as has been done in [1].…”

A bio-plausible design for visual pose stabilization

“…Bias compensation is usually a long trial-and-error manual operation that must be often repeated. However, we discovered that the bilinear velocity estimatesω BL andv BL defined in (12) were so reliable that they provided an opportunity to perform simple and effective automatic bias compensation. For example, ifω BL,z > 0, we know, even if the magnitude is unknown, that the helicopter is rotating to the left, and we can compensate by decreasing the rudder command.…”

“…Related work: Visual servoing is a classical problem in industrial robotics, with applications in controlling robot manipulators [9], [10] or visual navigation [11], [12]. The classical approach normally consists of extracting and tracking fiducial point/segments from the image [13].…”

Sliding Mode Control for Visual Servoing of Mobile Robots using a Generic Camera

“…The schemes in this control approach can be classified according to the nature of the feedback information. Image data can be used directly in the control loop (image-based schemes IBVS), for instance (Abdelkader et al (2005), Benhimane & Malis (2006)), or can be used to compute an estimate of pose parameters (position-based schemes: PBVS) as in (Das et al (2001), Fontanelli et al (2009)). Hybrid schemes combining these both approaches have been performed as well (Malis et al (1999), Fang et al (2005)).…”