Drain Structural Defect Detection and Mapping Using AI-Enabled Reconfigurable Robot Raptor and IoRT Framework

Human visual inspection of drains is laborious, time-consuming, and prone to accidents. This work presents an AI-enabled robot-assisted remote drain inspection and mapping framework using our in-house developed reconfigurable robot Raptor. The four-layer IoRT serves as a bridge between the users and the robots, through which seamless information sharing takes place. The Faster RCNN ResNet50, Faster RCNN ResNet101, and Faster RCNN Inception-ResNet-v2 deep learning frameworks were trained using a transfer learning scheme with six typical concrete defect classes and deployed in an IoRT framework remote defect detection task. The efficiency of the trained CNN algorithm and drain inspection robot Raptor was evaluated through various real-time drain inspection field trials using the SLAM technique. The experimental results indicate that robot’s maneuverability was stable, and its mapping and localization were also accurate in different drain types. Finally, for effective drain maintenance, the SLAM-based defect map was generated by fusing defect detection results in the lidar-SLAM map.

sTetro-Deep Learning Powered Staircase Cleaning and Maintenance Reconfigurable Robot

Staircase cleaning is a crucial and time-consuming task for maintenance of multistory apartments and commercial buildings. There are many commercially available autonomous cleaning robots in the market for building maintenance, but few of them are designed for staircase cleaning. A key challenge for automating staircase cleaning robots involves the design of Environmental Perception Systems (EPS), which assist the robot in determining and navigating staircases. This system also recognizes obstacles and debris for safe navigation and efficient cleaning while climbing the staircase. This work proposes an operational framework leveraging the vision based EPS for the modular re-configurable maintenance robot, called sTetro. The proposed system uses an SSD MobileNet real-time object detection model to recognize staircases, obstacles and debris. Furthermore, the model filters out false detection of staircases by fusion of depth information through the use of a MobileNet and SVM. The system uses a contour detection algorithm to localize the first step of the staircase and depth clustering scheme for obstacle and debris localization. The framework has been deployed on the sTetro robot using the Jetson Nano hardware from NVIDIA and tested with multistory staircases. The experimental results show that the entire framework takes an average of 310 ms to run and achieves an accuracy of 94.32% for staircase recognition tasks and 93.81% accuracy for obstacle and debris detection tasks during real operation of the robot.

Modelling and Control of a Reconfigurable Robot for Achieving Reconfiguration and Locomotion with Different Shapes

Area coverage is a crucial factor for a robot intended for applications such as floor cleaning, disinfection, and inspection. Robots with fixed shapes could not realize an adequate level of area coverage performance. Reconfigurable robots have been introduced to overcome the limitations of fixed-shape robots, such as accessing narrow spaces and cover obstacles. Although state-of-the-art reconfigurable robots used for coverage applications are capable of shape-changing for improving the area coverage, the reconfiguration is limited to a few predefined shapes. It has been proven that the ability of reconfiguration beyond a few shapes can significantly improve the area coverage performance of a reconfigurable robot. In this regard, this paper proposes a novel robot model and a low-level controller that can facilitate the reconfiguration beyond a small set of predefined shapes and locomotion per instructions while firmly maintaining the shape. A prototype of a robot that facilitates the aim mentioned above has been designed and developed. The proposed robot model and controller have been integrated into the prototype, and experiments have been conducted considering various reconfiguration and locomotion scenarios. Experimental results confirm the validity of the proposed model and controller during reconfiguration and locomotion of the robot. Moreover, the applicability of the proposed model and controller for achieving high-level autonomous capabilities has been proven.

A multiple working mode approach to robotic hammering: Analysis and experiments

A robot arm may be in need for performing various operations, especially for service robots and space robots. This paper presents a strategy that allows a modular and reconfigurable robot to safely perform nail hammering without hardware enhancements. The purpose is to equip a versatile robot arm with hammering capability that can be used if needed. To do this, a multiple working mode approach is applied to switch the selected joint(s) to passive mode with friction compensation to allow free rotation during impact. Analytic impulse models are used to predict joint impulses and serve as criteria for mode switching. Advantages of the proposed approach include savings on space, weight, costs, and complexity for a limited range of nail/board environments. An experimental study has validated analytic models of hammering and demonstrated the effectiveness of the proposed approach.