Behavior Trees in Robot Control Systems

Behaviour trees are a proven concept in the creation of complex task-switching control and artificial intelligence for robotic systems and non-player characters in the computer games industry. Requirements such as flexibility, maintainability, reusability of functionalities or expandability also apply to the control of decentralised energy systems. Despite this, there is a noticeable research gap regarding the application of behaviour trees in that sector. Based on a foundational heating system, including thermodynamic modelling of a part-load capable heat pump with TESPy , tree structures for its control are created using the Python library py_trees for implementation. With a view to minimising the annual operational performance indicators electricity price and CO 2 emissions, which reflect the optimal use of renewable shares, several control strategies are compared. We identify and illustrate the principal limitations of decision trees, mixed-integer linear optimisation performed with oemof-solph , as well as a classic rule-based approach. The proposed higher-level behaviour tree combines the strengths of such approaches whilst pursuing the additional target of reducing the start-up and associated wear of the heat pump without significantly increasing the computation time. • Transfer of the behaviour tree concept into the energy sector. • Proposal of a superordinate behaviour tree based control strategy. • Validation of a dynamic strategy, which results from inserting a decision tree. • Consideration of sensitivity to demand profiles, energy standard and heating period. • Part-load capable heat pump model including domestic hot water and space heating.

Behavior trees(BTs) provide a systematic and structured control architecture extensively employed in game AI and robotic behavior control, owing to their modularity, reactivity, and reusability. Nonetheless, manual BTs design requires significant expertise and becomes inefficient as task complexity increases. Recent automation technologies have avoided manual work, but often have high application barriers and face challenges in adapting to new tasks, making it difficult to easily configure them to specific requirements. Code-BT introduces a novel approach that utilizes large language models(LLMs) to automatically generate BTs, representing the task planning process as the process of coding and organizing sequences. By retrieving control flow information from the generated code, BTs can be efficiently constructed to address the complexity and diversity of task planning challenges. Rather than relying on manual design, Code-BT uses task instructions to guide the selection of relevant APIs, and then systematically assembles these APIs into modular code to align with the BTs structure. Finally, action sequences and control logic are extracted from the generated code to construct the BTs. Our approach not only ensures the automation of BTs generation but also guarantees the scalability and adaptability for long-term tasks. Experimental results demonstrate that Code-BT substantially improves LLM performance in BTs generation, achieving improvements ranging from16.67% to 29.17%.

Robotic systems have significantly transformed the landscape of minimally invasive surgery, offering enhanced precision, reduced recovery times, and improved patient outcomes. These systems have evolved from simple mechanical tools to sophisticated platforms integrating advanced control algorithms and real-time feedback mechanisms. This paper provides a comprehensive overview of the role of robotic systems in minimally invasive surgery, exploring the various benefits, inherent risks, and the challenges associated with their adoption and development. We examine the technical aspects of robotic control systems, such as kinematics, force control, and haptic feedback, which enable greater surgical accuracy. Despite these advantages, challenges such as system complexity, high costs, and ethical concerns remain significant barriers to widespread adoption. The future of robotic surgery lies in overcoming these obstacles, with advancements in system miniaturization and further refinement of control systems poised to enhance the efficacy and accessibility of robotic platforms. This paper explores the role of robotic systems in minimally invasive surgery, focusing on three key areas: bronchoscopy and ureteroscopy. By reviewing the benefits, risks, case studies, and future directions of these technologies, the paper seeks to provide an in-depth understanding of how robotic systems are shaping the future of surgery. Key words: Robotic Surgery, Minimally Invasive Surgery, Robotic Control Systems, Surgical Precision, PID Control, Kinematics, Inverse Kinematics, Forward Kinematics, Dynamic Control, Force Control, Impedance Control, Surgical Robotics, Haptic Feedback, Robotic Arm, Robotic Surgery Benefits, Robotic Surgery Risks, Robot-Assisted Surgery, Surgeon Console, Real-Time Feedback, Surgical Training, Robotic System Development, System Testing, Clinical Trials, Surgical Robot Performance, Robotics in Urology, Telepresence Surgery, Robotic Surgery Cost, Robotic Surgery Future Directions.

The manufacture, maintenance and inspection of a ship involve a series of works on the ship shell plate, which were always seen as harmful for human operators and time-consuming work. The shipping industry is looking to replace manual work with automation equipment. A magnetic climbing robot that can omnidirectionally move on ship shell plate was presented in this paper. This article summarized the mechanical structure, control system, kinematic model, and autonomy of robot. The mechanical structure of the robot was inspired by bionics and adopted a wheel-leg hybrid locomotion system. In the control system of this robot, industrial control computer (IPC) was adopted as the core controller and brushless direct current servomotor was chosen as the actuating station. Finally, the motion analysis of the designed robot was performed. The results of the analysis show that the magnetic climbing robot adapted to the ship curved shell plate and crossed obstacles.

Motivated by formation control of multiple non-holonomic mobile robots, this paper presents a trajectory tracking control scheme design for nonholonomic mobile robots that are equipped with low-level linear and angular velocities control systems. The design includes a nonlinear kinematic trajectory tracking control law and a tracking control gains selection method that provide a means to implement the nonlinear tracking control law systematically based on the dynamic control performance of the robot's low-level control systems. In addition, the proposed scheme, by design, enables the mobile robot to execute reference trajectories that are represented by time-parameterized waypoints. This feature provides the scheme a generic interface with higher-level trajectory planners. The trajectory tracking control scheme is validated using an iRobot Packbot's parameteric model estimated from experimental data.

<abstract> <p>This study proposes a centralized control system for an islanded multivariable minigrid to improve its performance, stability and resilience. The integration of renewable energy sources and distributed energy storage systems into microgrid networks is a growing trend, particularly in remote or islanded areas where centralized grid systems are not available. The proposed control system is designed to be implemented at two levels a high-level control system and a low-level control system. Hence, the high-level control system balances energy resources and demand, makes decisions for effective resource utilization and monitors energy transactions within the minigrid. Real-time data from various sources and advanced algorithms are used to optimize energy management and distribution enabling the integration of renewable energy sources and enhancing the resilience of the minigrid against power outages.</p> <p>Moreover, the low-level control system monitors energy parameters such as voltage, current, frequency and mechanical energy. The control system ensures these parameters remain within the specified range, maintaining system stability and ensuring efficient energy distribution. It also protects the minigrid against power outages improving system reliability and security. Finally, the proposed centralized control system offers a promising solution for improving the performance, stability and resilience of microgrid networks. The system provides real-time monitoring, efficient energy management and distribution, and the integration of renewable energy sources. These results have important implications for the development and deployment of microgrid networks in remote or islanded areas.</p> </abstract>

As the industrial robot manipulators are widely used in various industrial fields, the limitation of traditional closed architectures for robot control systems becomes increasingly evident. It is almost impossible to modify the planning algorithms, the robot model, or the type of servo amplifier block. In this paper, an open architecture of robot control system is presented. It allows users to change the hardware architecture of the control system, e.g. change the geometric parameters of robots, the number/type of axes, and the servo amplifier block. It allows users to modify both the motion and interfacing software, e.g., modify/replace motion planning/control algorithms or change the human-machine interface to make it friendlier. In most traditional robot control systems, it is not provided to plan velocity profile on-line, which becomes essential in some applications. An on-line velocity filter with the function of look-ahead is thus proposed and implemented. It is integrated in the open-architecture robot control system, which provides users great flexibility to plan the motion on-line. Furthermore, the velocity look-ahead function guarantees the motion accuracy by imposing limits on velocity. Experiments validated the proposed velocity filter and the control system.

The control system of a free-flying space manipulation robot with force-torque sensing is considered. As part of this work, a control circuit of the remote control system of a free-flying robot with variable delays in the data channel is proposed. The passivation method for TDPA (Time Domain Passivity Approach) communication cannel has been used to ensure the stability of the control system. The TDPA method is a flexible and convenient approach to ensure the passivity of the space manipulation robot's remote control system, but as a usage effect a drift of the position of the processing device happens. The method of compensating the drift of the executive device was applied to eliminate this drawback. To test the proposed control algorithms, a "virtual" stand was created and a simulation of a remote control system of a free-flying space manipulation robot with force-torque sensing was done under variable delays.

The joint anti-accident exercises between multilevel dispatching and control systems are using dispatcher training simulator (DTS). There are many problems with the existing DTS, such as communication difficulties, extraterritorial role simulation difficulties, uniformity of the training process, thus trainees cannot conduct self-training. This paper introduces non-player character (NPC) simulation technology into DTS to customize and intelligentize the training process. This paper firstly fused the NPC features of the game with the DTS system and established NPC model and behavior tree in DTS. Then simulation is conducted in behaviac software to realize the autonomous guidance and intelligent control of the simulation training process. The feasibility and effectiveness of NPC application in DTS are verified by comparison with the traditional DTS training process.

Robots should be able to exercise reasoning in both symbolic and geometric levels in order to plan a manipulation task. The execution of such tasks needs to be robust enough to cope with real environments. In an attempt to address this pertinent industry need, the paper proposes the use of behavior trees for effective robotic manipulation in dynamic environments. This paper presents a method to automatically generate a behavior tree and showcases its ability to enable the robot to reason at different levels and adapt to an uncertain and changing environment. This allows for a complex task to be robustly executed, pioneering the advancement towards fully functional service robots.

Mobile robot, especially wheeled mobile robot, with its simple mechanical structure and inherent agility, has attracted significant attentions for dynamic environment applications in the last two decades (Pin et al. 1994 and Purwin 2006). A general mobile robot Guidance, Navigation and Control (GNC) system is illustrated in the following figure. The main function of guidance system is to generate a feasible trajectory command, usually in multiple dimension of freedom (DOF) to achieve a robot task. The objective of control system is to drive the mobile robot following the commanded trajectory with acceptable tracking errors and stability margin. The function of robot navigation system is to provide accurate position, velocity and/or orientation information for the control system and guidance system. A stable and accurate navigation system is the bridge between the guidance system and control system of mobile robots, which ultimately determines the robot performance.

With the rise of Urban Air Mobility, vision-based object recognition using ground-fixed observation systems is gaining significance as a key component for ensuring aerial safety. In urban environments, however, consistent and reliable recognition of UAM vehicles remains a challenge due to complex visual backgrounds, the small size of aircraft, and their irregular flight trajectories. To address these issues, this study proposes a visual inference framework based on Behavior Tree. Inspired by human visual cognition, the proposed recognition pipeline mimics the process in which a human observer first applies global attention to a scene and then focuses selectively on uncertain areas for further analysis. Following an initial recognition stage using YOLOv8, ROI are re-examined through SAHI-based slicing to enhance recognition of small or partially missed objects. This modular structure separates the processes of image input, primary recognition, ROI inference, and result storage, while the Behavior Tree framework enables clear execution flow and real-time state tracking through explicit node transitions. Experimental evaluations conducted in a ROS2-based environment demonstrate that the proposed architecture significantly outperforms a conventional single-stage YOLO system, particularly under conditions involving cluttered backgrounds and small-scale aerial targets. Additionally, per-frame state logging and automatic result saving enhance system analysis and debugging capabilities. This work validates Behavior Tree-based visual inference as an effective control framework for object recognition systems and suggests its potential for future integration with real-time autonomous flight and control systems.

In recent years, with the steady and rapid growth of the national economy, various industries have developed rapidly and the resulting fire accidents have also been on the rise. This study mainly discusses the control system of a fire rescue robot for a high‐rise building design. Robot fire detection method involves obtaining the video image of the fire detection area through a high‐definition camera, performing image preprocessing on the current frame image of the video in the robot operating system to obtain the image; and performing the flame area segmentation based on the Ohta color space and the Otsu threshold segmentation algorithm on the image, to obtain the segmented image; through the interframe difference method, the preprocessed image of the previous frame is subtracted from the current frame image and the moving area of the image is segmented to obtain the segmented image; the obtained segmented image is combined with the segmented image in the robot operating system and images are intersected to obtain a segmented image with the characteristics of flame motion; based on other characteristics of the flame, flame recognition is performed on the area in the segmented image. Fires in high‐rise buildings are increasing gradually, which seriously endangers the safety of human life and property. The firefighting robot and its control system play an important role in the fire protection of high‐rise buildings. The purpose of this study is to analyze the disaster relief effect of a firefighting robot and control system in high‐rise buildings. In this study, we use MATLAB software to model and simulate the rescue situation of a firefighting robot in high‐rise buildings. The fuzzy control system established in the fuzzy logic toolbox of MATLAB can easily replace human field work and can change the control rules and membership function in the FIS editor. The results show that the rise time and adjustment time of the system are basically the same under the condition of variable load stiffness. The maximum overshoot is 0.59%, and the steady‐state error is 0.19%. The maximum overshoot is 1.0148%, and the stability error is 0.46%. It is concluded that the expert PID algorithm is efficient and practical. It can be concluded that the robot position control system adopts PID control algorithm, and the attitude control system adopts expert PID control algorithm. This research provides some value for the development and design of firefighting robots in high‐rise buildings in the future and also brings important significance.

Based on complex industrial field environment, modern industrial robots need good real-time, safety and stability, put forward higher requirements for control system. In this paper, real-time control technology and three-dimensional simulation technology of six-degree-of-freedom industrial robot are studied. A six-degree-of-freedom robot control system is developed by using CODESYS software supporting EtherCAT fieldbus. The hardware, software and core algorithm of the control system are designed. Different from the traditional CNC machine tool processing, six axial industrial robot is used to weld the trajectory of sphere-tube intersection curve, 3D simulation and welding code are automatically generated, and the algorithm rationality is tested and simulated. The proven six-degree-of-freedom robot control system can complete the real-time position and attitude control of the torch, acquire the state of the robot in real time, and support a variety of industrial robot models. It realizes automatic programming, 3D simulation, program uploading and downlinking, etc. The entire system has good real-time and reliability.

Theory of nonlinear control