Mobile robots play a crucial role in cleaning, maintenance, and surveillance applications. This article advocates for the use of a novel robust output feedback based path following controller, for a class of self-reconfigurable mobile robot under actuator saturation. The reconfigurability property of such platforms is captured via an uncertain Euler-Lagrange dynamics. The proposed control framework estimates the unmeasurable states and the uncertain dynamics terms through two extended high gain observers, whereas the actuator limits are honored via a fast dynamic compensator. The closed-loop stability is analyzed via contraction theory, which, compared to the conventional Lyapunov based approaches, avoids the requirement of arbitrarily large controller and observer gains. Such a feature is of particular interest in view of actuator saturation. The experimental results with PANTHERA self-reconfigurable robot validate the effectiveness of the proposed technique over the state of the art.

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.

Routine cleaning the pavement is an essential requirement to maintain a sustainable environment for social life. The different width and type of pavements raise the challenges for autonomous vehicles with fixed shape to operate effectively. In this paper, we introduce the vision based reconfiguration of self-reconfigurable pavement sweeping robot called Panthera, which can adjust its frame width to ease the cleaning tasks to become friendly with different pavement geometry. The expansion and compression operations of the Panthera width are implemented by rotating one high torque motor connecting with the lead screw rod to change the opening angle of linkage hinges. The Panthera cleaning and locomotion operations are synchronized with changing the robot width according to the output of detected pavement width. To this end, the segmented pavement leveraged on the masked based deep convolutional neural network (DCNN) is used as input for the proposed closed-loop feedback control method, enabling the robot to adjust the requirement of changing the width during locomotion accurately. The proposed PID scheme takes into account the robot kinematic design with the flexibility of width changing modes. The experiments were carried out in real environments demonstrated the autonomous reconfiguration robot width with various locomotion scenarios on pavements of varying width.

The design of cleaning and maintenance (CaM) robots is generally limited by their fixed morphologies, resulting in limited functions and modes of operation. Contrary to fixed shape robots, the design of reconfigurable robots presents unique challenges in designing their system, subsystems, and functionalities with the scope for innovative operational scenarios and achieving high performance in multiple modalities without compromise. This paper proposes a heuristic framework using three layers, namely input, formulation, and output layer, for designing reconfigurable robots with the aid of established transformation principles including expand/collapse, expose/cover, and fuse/divide observed in several products, services, and systems. We apply this heuristic framework approach to the novel design of a pavement CaM robotic system and subsystems, namely, (i) varying footprint, (ii) transmission, (iii) outer skin or cover, (iv) storage bin, (v) surface cleaning, and (vi) vacuum/suction and blowing. The advances in the design method using the heuristic approach are demonstrated by developing an innovative reconfigurable design for the CaM task. Kinematic analysis and control architecture enables the unique locomotion behavior and gaits, namely, (a) static reconfiguration and (b) reconfiguration while locomotion, supported by the control architecture. Experiments were conducted, and outcomes were discussed along with the failure mode analysis to support the design robustness and limitations through the observations made from the development to testing phase over one year. A detailed video demonstrating the design capabilities is linked.