The inspection of high-voltage transmission lines is a dangerous and time-consuming job, that relies on especially trained workers operating tens of meters above the ground, and close to live lines with thousands of volts. This paper presents the development of a tele-operated robot designed for preventive maintenance of high-voltage lines. The robot was designed with mobility in mind, so that cable spacers, suspension clamps and other obstacles, which so far have prevented the use of robots for inspection of high-voltage lines, would not hamper the operation of the machine. After careful considerations on mobility, the robot was designed, and a prototype was built. Results of tests, performed on facilities reproducing real field conditions, are also presented in this paper.

There have been several works proposing mobile robots for inspection of high-voltage transmission lines. Those studies addressed mostly locomotion issues, with little attention paid to the sensing task. However, the deployment of sensors around the cables is not an elementary operation. This work indicates which sensors may be most suitable for the inspection of transmission lines, and describes their assembly in a simple and compact structure (Sensor-Unit). In addition, it proposes several manipulator mechanisms (Sensor-Arm) to deploy sensors around the cables and to remove them when necessary. The mechanisms are compared taking into account practical aspects such as assembly, reliability, functionality and results of field experiments. Finally, the design of a high-quality camera for detailed inspection is also described.

This paper presents a new method for a quick similarity-based search through long unlabeled audio streams to detect and locate audio clips provided by users. The method involves feature-dimension reduction based on a piecewise linear representation of a sequential feature trajectory extracted from a long audio stream. Two techniques enable us to obtain a piecewise linear representation: the dynamic segmentation of feature trajectories and the segment-based Karhunen-L\'{o}eve (KL) transform. The proposed search method guarantees the same search results as the search method without the proposed feature-dimension reduction method in principle. Experiment results indicate significant improvements in search speed. For example the proposed method reduced the total search time to approximately 1/12 that of previous methods and detected queries in approximately 0.3 seconds from a 200-hour audio database.