No abstract

Wall cleaning robots are developed to cater to the demands of the building maintenance sector. The ability to climb vertical surfaces is one of the crucial requirements of a wall cleaning robot. Robots that can climb vertical surfaces by adhesion to a surface are preferred since those do not require additional support structures. Vacuum suction mechanisms are widely used in this regard. The suction force acting on the robot due to the negative pressure built up is used by these robots for the adhesion. A robot will fall off or overturn when the pressure difference drops down a certain threshold. In contrast, if the pressure difference becomes too high, the excessive amount of frictional forces will hinder the locomotion ability. Moreover, a wall cleaning robot should be capable of adapting the adhesion force to maintain the symmetry between safe adhesion and reliable locomotion since adhesion forces which are too low or too high hinder the safety of adhesion and reliability of locomotion respectively. Thus, the pressure difference needs to be sustained within a desired range to ensure a robot’s safety and reliability. However, the pressure difference built up by a vacuum system may unpredictably vary due to unexpected variation of air leakages due to irregularities in surfaces. The existing wall cleaning robots that use vacuum suction mechanisms for adhesion are not aware of the adhesion status, or subsequently responding to them. Therefore, this paper proposes a design for a wall cleaning robot that is capable of adapting vacuum power based on the adhesion-awareness to improve safety and reliability. A fuzzy inference system is proposed here to adapt the vacuum power based on the variation of the adhesion and the present power setting of the vacuum. Moreover, an application of fuzzy logic to produce a novel controlling criterion for a wall cleaning robot to ensure safety and reliability of operation is proposed. A fuzzy inference system was used to achieve the control goals, since the exact underlying dynamics of the vacuum-adhesion cannot be mathematically modeled. The design details of the robot are presented with due attention to the proposed control strategy. Experimental results confirmed that the performance of a robot with proposed adhesion-awareness surpasses that of a robot with no adhesion-awareness in the aspects of safety, reliability, and efficiency. The limitations of the work and future design suggestions are also discussed.

Aircraft surface inspection includes detecting surface defects caused by corrosion and cracks and stains from the oil spill, grease, dirt sediments, etc. In the conventional aircraft surface inspection process, human visual inspection is performed which is time-consuming and inefficient whereas robots with onboard vision systems can inspect the aircraft skin safely, quickly, and accurately. This work proposes an aircraft surface defect and stain detection model using a reconfigurable climbing robot and an enhanced deep learning algorithm. A reconfigurable, teleoperated robot, named as “Kiropter,” is designed to capture the aircraft surface images with an onboard RGB camera. An enhanced SSD MobileNet framework is proposed for stain and defect detection from these images. A Self-filtering-based periodic pattern detection filter has been included in the SSD MobileNet deep learning framework to achieve the enhanced detection of the stains and defects on the aircraft skin images. The model has been tested with real aircraft surface images acquired from a Boeing 737 and a compact aircraft’s surface using the teleoperated robot. The experimental results prove that the enhanced SSD MobileNet framework achieves improved detection accuracy of aircraft surface defects and stains as compared to the conventional models.

No abstract