Humans have an innate ability of environment modeling, perception, and planning while simultaneously performing tasks. However, it is still a challenging problem in the study of robotic cognition. We address this issue by proposing a neuro-inspired cognitive navigation framework, which is composed of three major components: semantic modeling framework (SMF), semantic information processing (SIP) module, and semantic autonomous navigation (SAN) module to enable the robot to perform cognitive tasks. The SMF creates an environment database using Triplet Ontological Semantic Model (TOSM) and builds semantic models of the environment. The environment maps from these semantic models are generated in an on-demand database and downloaded in SIP and SAN modules when required to by the robot. The SIP module contains active environment perception components for recognition and localization. It also feeds relevant perception information to behavior planner for safely performing the task. The SAN module uses a behavior planner that is connected with a knowledge base and behavior database for querying during action planning and execution. The main contributions of our work are the development of the TOSM, integration of SMF, SIP, and SAN modules in one single framework, and interaction between these components based on the findings of cognitive science. We deploy our cognitive navigation framework on a mobile robot platform, considering implicit and explicit constraints for autonomous robot navigation in a real-world environment. The robotic experiments demonstrate the validity of our proposed framework.

Detecting parcels accurately and efficiently has always been a challenging task when unloading from trucks onto conveyor belts because of the diverse and complex ways in which parcels are stacked. Conventional methods struggle to quickly and accurately classify the various shapes and surface patterns of unordered parcels. In this paper, we propose a parcel-picking surface detection method based on deep learning and image processing for the efficient unloading of diverse and unordered parcels. Our goal is to develop a systematic image processing algorithm that emphasises the boundaries of parcels regardless of their shape, pattern, or layout. The core of the algorithm is the utilisation of RGB-D technology for detecting the primary boundary lines regardless of obstacles such as adhesive labels, tapes, or parcel surface patterns. For cases where detecting the boundary lines is difficult owing to narrow gaps between parcels, we propose using deep learning-based boundary line detection through the You Only Look at Coefficients (YOLACT) model. Using image segmentation techniques, the algorithm efficiently predicts boundary lines, enabling the accurate detection of irregularly sized parcels with complex surface patterns. Furthermore, even for rotated parcels, we can extract their edges through complex mathematical operations using the depth values of the specified position, enabling the detection of the wider surfaces of the rotated parcels. Finally, we validate the accuracy and real-time performance of our proposed method through various case studies, achieving mAP (50) values of 93.8% and 90.8% for randomly sized and rotationally covered boxes with diverse colours and patterns, respectively.

This paper presents a state observer for an elastic joint with nonlinear friction via the information from an acceleration sensor. In order to avoid discontinuities, the nonlinear friction of the motor, which includes static, coulomb, and viscous terms, is considered a smooth function. In addition, it uses an acceleration sensor to obtain the information about the link with high uncertainty. The proposed state observer guarantees that the estimation error for the position and velocity of the link connected via an elastic joint containing a nonlinear stiffness (elasticity) converges to zero. In addition, it is shown that the observer gain can be designed by LMI (linear matrix inequality) optimization. Finally, to verify the performance of the proposed observer, the method proposed in this paper is tested by experiments on a two-inertia system with an elastic shaft.

This paper proposes a semantic-based autonomous disinfection robot system for continuous operation in environments where robots coexist with people. Existing UV-C disinfection robots presuppose unoccupied-hours operation owing to their exposed lamp structures, and their uniform irradiation at predefined waypoints ignores the infection risk of individual targets. The proposed system integrates the optical blocking of UV-C and the physical protection of the lamps into a single mechanism through an active shielding blind driven by a single motor, securing the irradiation distance as a control variable for dose. On this basis, we extend the Triplet Ontological Semantic Model (TOSM) to the disinfection domain, defining semantic classes of objects and places with level-specific target doses, and derive irradiation distances and exposure times from a measured irradiance model. Deployed since December 2021 at more than twenty real-world sites across the medical, transport, administrative, commercial and educational domains—of which eight are documented as demonstration sites in this paper—the platform raised the dose achievement rate of high-touch (P3) targets from 50.0% under a uniform waypoint scheme of equal mission time to 90.0% and, at equivalent achievement, shortened the mission time by 10 min with a proportional reduction in lamp energy, while zero lamp breakages over five years of operation verify the safety and reliability of the shielding structure.

Mobile platforms for installing prefabricated pipe and duct modules inside buildings must transport long payloads and lift them to elevated work positions. Changes in payload arrangement and height alter stability margins and load-transfer responses. This paper presents a payload-informed tip-over prevention framework for a previously developed high-lift swerve-drive construction platform. Four platen load cells estimate payload mass and planar center of gravity (CoG), while vertical CoG is supplied from geometry. Support-edge moments and an explicit error budget define conditional limits on directional translational acceleration and deceleration for pre-operation setting selection and compatibility checks. Load-transfer residuals computed using matched causal processing provide online observations during travel. The reported experiments comprise 46 records for normal and eccentric arrangements formed by repositioning the pipes at two nominal payload levels, approximately 1.05 t and 3.13 t, with platen heights up to approximately 5.04 m. Three stationary acquisitions per arrangement give mass standard deviations of 0.23–0.64 kg, characterizing within-layout repeatability. Nineteen LOW-speed driving records support residual characterization and 92 common-window single-stop response comparisons; six stationary HIGH-setting events demonstrate alarm and inhibit requests. The resulting evidence connects payload characterization, setting supervision and response observation for construction transport and lifting. The directional-limit formulation remains conditional on an identified dynamic-response model and an adequate error budget.