Designing an urban reconnaissance robot is highly challenging work given the nature of the terrain in which these robots are required to operate. In this work, we attempt to extend the locomotion capabilities of these robots beyond what is currently feasible. The design and unique features of our bio-inspired reconfigurable robot, called Scorpio, with rolling, crawling, and wall-climbing locomotion abilities are presented in this paper. The design of the Scorpio platform is inspired by Cebrennus rechenbergi, a rare spider species that has rolling, crawling and wall-climbing locomotion attributes. This work also presents the kinematic and dynamic model of Scorpio. The mechanical design and system architecture are introduced in detail, followed by a detailed description on the locomotion modes. The conducted experiments validated the proposed approach and the ability of the Scorpio platform to synthesise crawling, rolling and wall-climbing behaviours. Future work is envisioned for using these robots as active, unattended, mobile ground sensors in urban reconnaissance missions. The accompanying video demonstrates the shape shifting locomotion capabilities of the Scorpio robot.

This research work presents the development of a novel tetris inspired reconfigurable floor cleaning robot - hTetro, utilizing the hinged dissection theory of polyominoes. The developed robot platform is capable of transforming between any of the seven set of one-sided tetromino morphologies according to the perceived environment with an objective of maximizing the coverage area. Experiments were performed across two different settings to systematically compare the coverage area performance of the developed hTetro robot and a commercially available fixed morphology robot platform. Results indicate significantly higher coverage area performance in the case of hTetro due to its ability to assume optimal morphology in relation to navigating environment.

The need for a novel automated mosquito perception and classification method is becoming increasingly essential in recent years, with steeply increasing number of mosquito-borne diseases and associated casualties. There exist remote sensing and GIS-based methods for mapping potential mosquito inhabitants and locations that are prone to mosquito-borne diseases, but these methods generally do not account for species-wise identification of mosquitoes in closed-perimeter regions. Traditional methods for mosquito classification involve highly manual processes requiring tedious sample collection and supervised laboratory analysis. In this research work, we present the design and experimental validation of an automated vision-based mosquito classification module that can deploy in closed-perimeter mosquito inhabitants. The module is capable of identifying mosquitoes from other bugs such as bees and flies by extracting the morphological features, followed by support vector machine-based classification. In addition, this paper presents the results of three variants of support vector machine classifier in the context of mosquito classification problem. This vision-based approach to the mosquito classification problem presents an efficient alternative to the conventional methods for mosquito surveillance, mapping and sample image collection. Experimental results involving classification between mosquitoes and a predefined set of other bugs using multiple classification strategies demonstrate the efficacy and validity of the proposed approach with a maximum recall of 98%.

The pavement inspection task, which mainly includes crack and garbage detection, is essential and carried out frequently. The human-based or dedicated system approach for inspection can be easily carried out by integrating with the pavement sweeping machines. This work proposes a deep learning-based pavement inspection framework for self-reconfigurable robot named Panthera. Semantic segmentation framework SegNet was adopted to segment the pavement region from other objects. Deep Convolutional Neural Network (DCNN) based object detection is used to detect and localize pavement defects and garbage. Furthermore, Mobile Mapping System (MMS) was adopted for the geotagging of the defects. The proposed system was implemented and tested with the Panthera robot having NVIDIA GPU cards. The experimental results showed that the proposed technique identifies the pavement defects and litters or garbage detection with high accuracy. The experimental results on the crack and garbage detection are presented. It is found that the proposed technique is suitable for deployment in real-time for garbage detection and, eventually, sweeping or cleaning tasks.

Although numerous studies have focused on the development and application of polyomino tiling theories, research of this nature is typically limited to the graphics and gaming fields. In this paper, we are presenting an innovative application of the polyomino tiling theory which is applied to Tetris-inspired reconfigurable robotic cleaning device as a means of solving the area coverage problem. The robotic floor cleaner (hTetro) that was developed as part of this research leverages the polyomino tiling theory to automatically generate the global tiling set required to ensure the full area of a given space is covered. In this paper, three Tetris tiling theorems were validated using our developed hTetro robot. The results of the research clearly indicated that the proposed approach offers a strong area coverage performance across all experimental cases. This paper includes an outline of the system architecture that underpins the hTetro robot and a comprehensive overview of the three tiling theorems that were applied in this research.