Complete coverage path planning (CCPP) is essential for autonomous cleaning robots, particularly in complex and variable environments where traditional, fixed-footprint designs may fall short. This paper presents adaptive Glasius bio-inspired neural network (aGBNN) approach to CCPP, specifically tailored for an omnidirectional self-reconfigurable cleaning robot (OSCR). The aGBNN method dynamically generates a complete coverage path by leveraging the ability to change sweeping footprint of the robot (SFR) assisted by reconfiguring brushes design. The sweeping is carried out both longitudinally and laterally, thereby complementing the omnidirectional locomotion with cleaning. Unlike conventional CCPP algorithms that assume a fixed robot footprint, the proposed aGBNN adapts in real-time to spatial and moving obstacles, significantly enhancing coverage efficiency. Experimental and simulation results demonstrate the advantage of the aGBNN approach, in terms of path length, and total time to complete area coverage compared to state-of-the-art methods.

Efficient fire drill evacuation in high-rise buildings demands real-time perception and optimized path planning. This study presents an autonomous evacuation framework that integrates deep learning-based object detection with multi-objective trajectory planning. Using RGB-D vision, the system detects human traffic and staircases, projecting them into the robot’s workspace. The evacuation task is modeled as a Moving Target Traveling Salesman Problem (MT-TSP) and solved via a modified NSGA-II algorithm, balancing travel time, path length, safety, and accessibility. Experiments show over 90% detection accuracy and significant improvements in navigation efficiency, demonstrating the effectiveness of combining deep learning with evolutionary optimization for robotic fire drill planning.

In reconfigurable robotics, intra-reconfiguration enables a robot to change its functional abilities, while inter-reconfiguration manipulates the specification limits of the robot hardware. Although the versatility of inter-reconfigurable robots is desired in advanced autonomous systems, the O(n3) algorithm computational time complexity challenge comes when multiple modular robots combine and reconfigure into a bigger form structure for autonomous navigation tasks. This phenomenon has limited the inter-reconfiguration potential of expansion, versatility, and robustness. In this paper, a navigation framework with non-complex transformation states is proposed for inter-reconfigurable robots to perform combining and splitting control dimensions. Simulations have shown the complexity from O(n) to constant time O(1) in the reconfiguration states of the framework on a considerable number of robot agents. Additionally, a set of inter-reconfigurable robots, Wasp Biggie, was used to demonstrate the proof-of-concept in experiments as a fully functional centralized planner system. These experiments showed outperforming results on the consistent utility of CPU consumption while performing navigation and reconfiguration. Note to Practitioners—This study aims to provide controls for combining multiple robots into a single system. The research study enables the robots in the system to vary and manipulate their physical structure and mechanism limitations. Onboard computation resources are often finite and incapable of computing for multiple functions that are actively in demand. Hence, this paper is motivated by the severe increase in computational demands common in a multi-robot centralized system. The paper has provided the technical details of the system architecture of the state machine and how it integrates with a typical navigation stack. The state-machine of the framework can be easily constructed using the SMACH package in the Robot Operating System and integrated by reconstruction of the navigation stack by providing the command velocity as an input and producing the transformed command velocity for the controls of the respective robots. The outcome of the paper provides a method of control in inter-reconfigurability and takes in a consistent amount of computational resources as the number of robots varies in utilization.

Autonomous mobile robots (AMRs) face challenges in efficiently covering complex environments. To navigate narrow and expansive areas, AMRs must have two essential attributes: compact size for confined spaces and larger size with omnidirectional locomotion for broader spaces. This study utilizes omnidirectional expand and collapse robots (OECRs) to demonstrate efficient area coverage. OECRs can collapse to navigate through confined spaces and expand for efficient coverage in broad spaces. However, current complete coverage path planning (CCPP) methods do not account for the expanded and collapsed states of OECRs. To address this, a depth-first search (DFS) approach is proposed for OECRs' CCPP, which can adjust the robotic footprint along the CCPP path to reduce path length. The proposed DFS outperforms the state-of-the-art CCPP in terms of increased area coverage and reduced distance traveled on a selected map.

Pavement cleaning is a labor-intensive, repetitive task and can be automated. Several autonomous pavement cleaning robots have been developed, pushing research towards their design and autonomous capabilities. Advances in design have been reported in earlier works on a self-reconfigurable robot with four independent steering drive (4ISD) capabilities, Panthera, for pavement cleaning and maintenance. Moreover, autonomous navigation requires sharp turns, heading angle adjustments, sideways movement, and locomotion without col-lision through constrained pavement conditions. The present work proposes an algorithm to ingeniously select the instan-taneous center of rotation (ICR) within the self-reconfigurable robot footprint and perform static rotation to adjust its heading angle during the waypoint navigation while avoiding collision with the constrained environment. Finally, the proposed algorithm is implemented, and experiments are conducted in real-world pavement scenarios. The experimental outcome success-fully demonstrates the self-reconfigurable robot's capability to navigate constrained pavement scenarios using the proposed algorithm during autonomous cleaning and maintenance tasks.

Cleaning robots are one of the market dominators in the commercialized robot space. So far, numerous robots have been introduced that can perform cleaning tasks in various settings, including floor, pavement, pool, lawn, windows, etc. However, none of the existing commercial cleaning robots targets the staircase, commonly found in multi-story buildings. Even though few works in the literature introduced robotic solutions for staircase cleaning, they primarily focused on cleaning the ascending staircase often, with a loose connection to access the descending staircase. In this paper, we propose a novel autonomous reconfigurable robotic platform called sTetro-D that can autonomously detect the descending staircase, approach the step, and perform area coverage in an unknown environment. The developed autonomy framework consists of two modes which are search mode and clean mode. In search mode, we implemented an RGB-D camera-based fusion technique wherein we combined the image bounding box from DCNN (Deep Convolution Neural Network) with the depth information to find the 3D first step pose that assists the robot in approaching it precisely. After the successful stair approach, the cleaning mode enables the staircase area coverage process. We described all these aspects and concluded with an experimental analysis of the proposed robotic system in a real-world scenario. The results demonstrate that the robot has a significant performance in detecting the descending staircase, staircase approach, and area coverage.

Planning the energy-efficient and collision-free paths for reconfigurable robots in complex environments is more challenging than conventional fixed-shaped robots due to their flexible degrees of freedom while navigating through tight spaces. This article presents a novel algorithm, energy-efficient batch informed trees* (BIT*) for reconfigurable robots, which incorporates BIT*, an informed, anytime sampling-based planner, with the energy-based objectives that consider the energy cost for robot’s each reconfigurable action. Moreover, it proposes to improve the direct sampling technique of informed RRT* by defining an$L^2$greedy informed setthat shrinks as a function of the state with the maximum admissible estimated cost instead of shrinking as a function of the current solution, thereby improving the convergence rate of the algorithm. Experiments were conducted on a tetromino hinged-based reconfigurable robot as a case study to validate our proposed path planning technique. The outcome of our trials shows that the proposed approach produces energy-efficient solution paths, and outperforms existing techniques on simulated and real-world experiments.

An efficient sensors fusion framework in an autonomous robot is necessary for various functions like object detection and perception enhancement. Multi-sensor calibration techniques are used to fuse multiple static sensors into a single frame of reference. However, for reconfigurable robots, sensors can change pose during reconfiguration need a robust adaptive sensor fusion to account for the relative change in sensor position and orientation. We propose an adaptive sensor fusion framework that can be implemented on any reconfiguration robot to adjust calibration parameters. Our paper formulated an adaptive sensor fusion method, implemented it in real-time on an autonomous reconfigurable pavement sweeping robot called Panthera, and demonstrated qualitatively the accuracy of the proposed sensor fusion framework for environment perception during robot reconfiguring on the pavement.

Since the appearance of humanoid robots is similar with real human, a method is proposed to discriminate these robots from real human in a perception sensor network (PSN) which uses multiple Kinects and PTZ cameras to provide the location and name of tracked human to these robots. To this end, the global map which is acquired by fusing and calibrating one local map built by a robot and the other local map by the PSN system is used to provide the location of the robot. Since the PSN updates periodically the location of the robot by subscribing the ROS (Robot Operating System) topics, the robot which is wrongly detected as human but yields the closest distance to the location can be correctly identified as a robot in the system. Therefore, the misunderstood cases when robots are recognized as human in the PSN system are removed effectively. The experimental results demonstrate the outperforming of the proposed method in various scenarios.