Purpose The purpose of this paper is to provide details of the role of autonomous robots in the transportation and delivery sector of the logistics industry. Design/methodology/approach Following an introduction, this first discusses autonomous cargo shipping. It then considers autonomous road transport which is followed by details of short-distance and last-mile delivery robots. Finally, conclusions are drawn. Findings Transportation and delivery is a central element of the logistics industry but the sector faces operational, environmental and economic challenges. The industry is increasingly adopting automation and robotics, and this is now being extended to the transportation and delivery sector. Autonomous cargo ships have been demonstrated and have the potential to reduce costs and improve safety. The main barriers to widespread adoption are regulations and legislation. Autonomous road transport is gaining momentum and autonomous trucks are increasingly being deployed, particularly in the USA, where they operate on hub-to-hub routes. Short-distance and last-mile delivery is a rapidly growing sector and drones, autonomous vehicles and sidewalk robots are used widely to deliver foods, groceries and mail. Autonomous vehicles confer benefits which include improved safety, reduced environmental impact, lower fuel and labour costs and more rapid delivery and represent the most significant development in the drive to achieve full automation of the logistics industry. Originality/value This provides details of the rapidly growing role of robotics in the transportation and delivery sector of the logistics industry.

Purpose While existing 2D LiDAR algorithms can support mobile robots to perform localization and mapping in industrial scenarios, they often consume substantial computational resources, a critical limitation for lightweight robotic platforms. To enhance computational efficiency while maintaining localization accuracy, this paper aims to propose an efficient 2D LiDAR odometry algorithm based on the constraint of the intersection of lines and coordinate axes (LIA-LO). Design/methodology/approach The proposed LIA-LO algorithm consists of three key components: (1) in the body coordinate system, a seed region growing strategy is used to extract straight line segments from the environmental point cloud and fit their general expression parameters; (2) the intersection points between these line segments and the body coordinate axes are used as features to determine the matching relationship of line segments between two consecutive frames; and (3) the Gauss–Newton equation is applied to minimize the point-to-line distance residual, thereby solving the robot’s pose. Findings Experimental results demonstrate that the proposed algorithm achieves positioning accuracy comparable to established methods such as Hector-SLAM and PLICP, while taking less than 15 ms to compute on low-cost devices. Originality/value The novelty of this research lies in the introduction of line-axis intersection constraints as features for 2D LiDAR odometry. This approach, combined with a specialized line segment extraction and matching strategy, enables efficient and accurate pose estimation, offering a valuable contribution to lightweight SLAM systems, particularly in indoor environments where geometric structure information can be leveraged.

Purpose For flexible grippers, people always hope that they can grasp objects accurately, stably and compliantly. This study aims to focus on robotic arm and flexible gripper, considers both position and grip control, while improving the compliantly of movements, which is a challenging task. Design/methodology/approach This study constructs the mathematical model of collaborative robotic arm and flexible gripper, designs an intelligent iterative learning control strategy with modular convolutional neural network and demonstrates the superiority of the proposed method over existing control methods through experiment. Findings The results show that compared to the existing methods, the proposed method can improve position accuracy while reducing chattering and improving initial transient impact force, thereby improving the operational compliantly and stability of the robotic arm and flexible gripper. And the control strategy proposed in this study is applied to grasp some typical flexible and brittle objects, which can effectively handle the flexible and brittle objects. Using the method proposed in this study, the robot’s end position error in the XYZ-direction is controlled within ±0.5 mm, and the Jerk in the XYZ-direction is within ±70mm/s³. Initially, when external interference is applied, the grasping force of the four fingers varies between 0.135 and 0.185 N. During the stable phase of external interference, the grasping force ranges from 0.140 to 0.160 N. Originality/value This study proposes an intelligent iterative learning control method with modular convolutional neural network for the combination of a collaborative robotic arm and a flexible gripper. While simplifying the control structure, it achieves dexterous and compliance grasping for the flexible, brittle and irregularly shaped objects. This study conducts physical experiments, thereby laying the foundation for the research of the dexterous and compliance grasping requirements for the flexible, brittle objects with different shapes.

The publisher of Industrial Robot is issuing an Expression of Concern for the article J. Norberto Pires, Chung‐Hao Chen, Chang Cheng, David Page, Andreas Koschan, Mongi Abidi; Tracking a moving object with real‐time obstacle avoidance. Industrial Robot 1 November 2006; 33 (6): 460–468. Link to the cited article, to inform readers that concerns have been raised regarding the originality of this paper. It has come to our attention that a large portion of this article is taken, without full and proper attribution, from an earlier original work by Chung-Hao Chen, Chang Cheng, David Page, Andreas Koschan and Mongi Abidi, a moving object tracked by a mobile robot with real-time obstacles avoidance capacity, ICPR ′06: Proceedings of the 18th International Conference on Pattern Recognition – Vol. 03, pp. 1091–1094, Link to the cited article. The submission guidelines for Industrial Robot make it clear that articles must be original and not infringe any existing copyright. The publisher sincerely apologizes to the readers.

Purpose Faults in multi-mobile robot systems (MMRS) can lead to task failures or other serious consequences. The purpose of this paper is to accurately estimate faults in cooperative MMRS, which communication topology is directed graphs, with scenarios such as collaborative transportation, and the authors propose a fault estimation method based on the intermediate observer. Design/methodology/approach The method solves the observer gain using the H8 performance criterion. It improves estimation accuracy by using centralized and local estimation errors. For calculating the observer’s parameter matrices, a solution to linear matrix inequality based on Schur decomposition theorem is proposed. Findings Simulation and physical experimental results demonstrate that, in MMRS cooperative tasks, the proposed method can accurately estimate the fault of each robot. Originality/value The proposed method can accurately estimate faults caused by external interference, centralized errors and localized errors transmitted through communication, providing a basis for control decisions and mitigating the impact of faults on MMRS collaborative transportation with the effectiveness of a greater number of robots and more complex scenarios awaits verification through subsequent research.

Purpose This study aims to propose a method for collision avoidance and hovering, enabling robots to perform efficient and safe inspection tasks in complex inlet environments, while also having capabilities for collision avoidance and trajectory planning. Through precise trajectory planning, the robot can safely enter and exit the inlet environment, ensuring the safety and efficiency of the inspection process. Design/methodology/approach A novel robot configuration was proposed, and by integrating the genetic algorithm-particle swarm optimization (GA-PSO) algorithm and sensor fusion technology, a collision-avoidance and immersion trajectory planning method was designed. The feasibility of the proposed method was verified through computer simulation and experiments. Findings Through experimental verification, the air intake duct inspection robot achieved remarkable performance in the simulated air intake duct experimental environment. The robot was able to successfully complete complex inspection tasks. Originality/value The innovation of this research lies in combining machine learning with robot navigation technology and innovatively applying the GA-PSO algorithm to optimize robot trajectory planning in a complex intake environment to solve the intake inspection problem in practical applications. By autonomously optimizing the joint angles, an efficient automated inspection process is achieved, reducing the risk and cost of manual inspection. It not only optimizes the motion path of the robot, but also enhances its adaptability and stability in complex environments, providing a more efficient and reliable solution for air intake inspection.

Purpose This study aims to explore the integration of large language models (LLMs) and vision-language models (VLMs) in robotics, highlighting their potential benefits and the safety challenges they introduce, including robustness issues, adversarial vulnerabilities, privacy concerns and ethical implications. Design/methodology/approach This survey conducts a comprehensive analysis of the safety risks associated with LLM- and VLM-powered robotic systems. The authors review existing literature, analyze key challenges, evaluate current mitigation strategies and propose future research directions. Findings The study identifies that ensuring the safety of LLM-/VLM-driven robots requires a multi-faceted approach. While current mitigation strategies address certain risks, gaps remain in real-time monitoring, adversarial robustness and ethical safeguards. Originality/value This study offers a structured and comprehensive overview of the safety challenges in LLM-/VLM-driven robotics. It contributes to ongoing discussions by integrating technical, ethical and regulatory perspectives to guide future advancements in safe and responsible artificial intelligence-driven robotics.

Purpose This paper aims to introduce a grasping configuration planning method suitable for grippers featuring three individually controllable fingers. This approach can effectively improve the stability of grasping for objects of various shapes. Design/methodology/approach Inspired by the Fermat point in geometric triangles, this paper establishes two planning objectives: minimizing the distance from the palm axis to the object’s center of mass and maximizing the displacement of the three fingers. Based on these objectives, this paper proposes specific steps for the grasping configuration planning method. In addition, by considering the effect of gravity on grasping, this paper analyzes the trends in contact point frictions under different planning objectives. The position of the palm axis is further determined by identifying the configuration that maximizes static friction. Findings Simulation and experiment results demonstrate the feasibility of applying the grasp configuration planning method to specific grippers, which can improve both the success rate and stability compared to manual grasping. Originality/value This paper proposes a new grasping configuration planning method based on the Fermat point principle, which is introduced step by step with a focus on two planning objectives and considers the effect of friction changes on grasping under the influence of gravity.

Purpose This paper proposes a robot posture optimization method and a workpiece setup optimization approach for robotic milling to improve machining quality. Design/methodology/approach A force-induced error index is established by considering spindle weight and milling force, along with the identification of spindle gravity and center of mass. A robot posture optimization model is then formulated based on the force-induced error and motion smoothness, and solved using the artificial potential field method. Finally, a bi-level optimization algorithm is applied to address the coupled optimization of robot posture and workpiece setup. Findings Experimental results show that the proposed robot posture optimization method ensures high computational efficiency and improved machining quality. Moreover, the bi-level workpiece setup optimization further enhances machining accuracy. Originality/value The proposed method improves machining quality by simultaneously optimizing tool orientation and redundant degree of freedom, while maintaining high computational efficiency. The bi-level optimization enables simultaneous optimization of workpiece setup and robot posture.

Purpose Interaction force control is crucial for robotic manipulators in contact tasks. For different tasks, robotic manipulators are expected to possess adaptive capability to modulate interaction force performance. To this end, this paper aims to propose an interaction force control scheme for robotic contact tasks via prescribed performance-enhanced impedance regulation. Design/methodology/approach The proposed scheme integrates Dual Prescribed Performance boundary in impedance outer loop and position inner loop in parallel, named DPP-IC. Based on the performance boundary, the interaction force deviation is transformed into matching position adjustment compensation for enhancing impedance regulation in contact tasks. The compensation together with the output of the standard impedance model is then used as desired input in our designed prescribed performance PID controller (PPC-PID) in position loop. This can confine interaction force within prescribed performance boundary, thereby simultaneously improving transient and steady-state control performance. Findings Comparison experiments with three mainstream impedance control methods of standard impedance control, adaptive law-based impedance control and learning-based variable impedance control are conducted on our self-designed robotic manipulators. The results of this study prove that the advantages of the proposed scheme in improving interaction force control. Originality/value This paper first introduces prescribed performance boundary into standard impedance model in parallel, improving inter-action force control performance for robotic contact tasks on a wide range of environmental stiffness.