No abstract

No abstract

This article describes an unprecedented alternative to manual procedures for the application of advanced composite materials, such as Fiber Reinforced Polymer (FRP) and epoxy resins. A complete mobile integrated system is presented for the inspection and maintenance of concrete surfaces in tunnels. It allows performance of operations with minimum interference on passing traffic. The core of this system resides in a specially designed light-weight robotic tool, which is sensed and automated for processes. Sensing includes vision and a laser telemeter to assure precise inspection, superficial preparation, and composite application. The designed interconnection flange allows simple and robust attachment of the tool to a robotic arm's tip. The robot-tool set is to be mounted on a standard articulated lift platform. Therefore, an operator can direct the platform and the robot-tool set's operations from a control station placed at ground-level, in a wheeled vehicle on which the articulated lift platform is mounted. A graphical Human-Machine Interface (HMI) has been developed for the system. It allows the operator to identify fissures for the injection of epoxy resin, and weakened surfaces for FRP adhesion. Actual procedures are planned and performed by the system's automatic components.

No abstract

-Tunnels environments are characterized by dust, humidity, and absence of natural light. Artificial and natural impacts, change in load criteria, or the simple effect of ageing, make tunnels require inspection and maintenance. These operations are commonly performed by human workers taking time and expertise without guarantee quality control. Robotic tunnel inspection and maintenance (RTIM) introduces high productivity, quality and repetitiveness. This paper describes the current trends in the subject, and introduces new technologies such as scenario modeling, robotic platforms, image and ultrasound sensors, control algorithms and decision making strategies. Additionally, the result of several recent and ongoing projects will be presented.

Humanoids can learn motor skills through the programming by demonstration framework, which allows matching the kinematic movements of a robot with those of a human. Continuous goal-directed actions (CGDA) is a framework that can complement the paradigm of robot imitation. Instead of kinematic parameters, its encoding is centered on the changes an action produces on object features. The features can be any measurable characteristic of the object such as color, area, etc. The execution of actions encoded as CGDA allows a robot-configuration independent achievement of tasks, avoiding the correspondence problem. By tracking object features during action execution, we create a trajectory in an n-dimensional feature space that represents object temporal states, allowing generalization, recognition, and execution of action effects on the environment. Experiments have been performed, using a humanoid robot in a simulated environment. Evolutionary computation was used for joint parameter calculation of a humanoid robot. The objective is to generate a motor trajectory which leads to a feature trajectory equal to the objective one. In one of the experiments, the robot performs a spatial trajectory based on spatial object features. In a new experiment, the robot paints a wall by following a color feature encoding.

No abstract

No abstract