Hierarchical Finite State Machine Research Articles

A microservice based control architecture for mobile robots in safety-critical applications

Mobile robots have become more and more common in public space. This increases the importance of meeting safety requirements of autonomous robots. Simple mechanisms, such as emergency braking, alone do not suffice in these highly dynamic situations. Moreover, actual robotic control approaches in literature and practice do not take safety particularly into account. A more sophisticated situational approach for assessment and planning is needed as part of the high-level process control. This paper presents the concept of a safety-critical Robot Control Architecture for mobile robots based on microservices and a Hierarchical Finite State Machine. It expands already existing architectures by drastically reducing the amount of centralized logic and thus increasing the overall system’s level of concurrency, interruptibility and fail-safety. Furthermore, it introduces new potential for code reuse that allows for straightforward implementation of safety mechanisms such as internal diagnostics systems. In doing so, this concept presents the template of a new type of state machine implementation. It is demonstrated with the application of a delivery robot, which was implemented and operated in real public during a broader research project.

An agent-based modeling framework for the multi-UAV rendezvous recharging problem

In this work, we aim to model the multi-UAV rendezvous recharging problem, which consists of energy-limited aerial vehicles that rendezvous with a mobile or fixed charging station. The motivation for such a problem is to tackle persistent surveillance missions, where the modeling of related problems often rely on heavy mathematical formulations, such as mixed integer linear programming (MILP). The major drawback of such approaches is great difficulty in capturing constraints and adjusting the model for changes. Additionally, MILP solvers are not guaranteed to yield a feasible solution in a timely manner. As a result, we chose to create an agent-based model (ABM). To the best of our knowledge, the presented problem has not been modeled before using ABM. Additionally, we sought to use a custom framework incorporating Behavior Trees (BTs) and Hierarchical Finite State Machines (HFSMs), two commonly used tools in the video game and robotics industry. We verify the model’s correctness through numerical simulations and show that it is highly modular and extensible.

A Novel Method of Digital Twin-Based Manufacturing Process State Modeling and Incremental Anomaly Detection

In the manufacturing process, digital twin technology can provide real-time mapping, prediction, and optimization of the physical manufacturing process in the information world. In order to realize the complete expression and accurate identification of and changes in the real-time state of the manufacturing process, a digital twin framework of incremental learning driven by stream data is proposed. Additionally, a novel method of stream data-driven equipment operation state modeling and incremental anomaly detection is proposed based on the digital twin. Firstly, a hierarchical finite state machine (HFSM) for the manufacturing process was proposed to completely express the manufacturing process state. Secondly, the incremental learning detection method driven by stream data was used to detect the anomaly of the job process data, so as to change the job status in real time. Furthermore, the F1 value and time consumption of the proposed algorithm were compared and analyzed using a general dataset. Finally, the method was applied to the practical case development of a welding manufacturer’s digital twin system. The flexibility of the proposed model is calculated by the quantitative method. The results show that the proposed state modeling and anomaly detection method can help the system realize job state mapping and state change quickly, effectively, and flexibly.

Modeling and TOPSIS-GRA Algorithm for Autonomous Driving Decision-Making Under 5G-V2X Infrastructure

This paper is to explore the problems of intelligent connected vehicles (ICVs) autonomous driving decision-making under a 5G-V2X structured road environment. Through literature review and interviews with autonomous driving practitioners, this paper firstly puts forward a logical framework for designing a cerebrum-like autonomous driving system. Secondly, situated on this framework, it builds a hierarchical finite state machine (HFSM) model as well as a TOPSIS-GRA algorithm for making ICV autonomous driving decisions by employing a data fusion approach between the entropy weight method (EWM) and analytic hierarchy process method (AHP) and by employing a model fusion approach between the technique for order preference by similarity to an ideal solution (TOPSIS) and grey relational analysis (GRA). The HFSM model is composed of two layers: the global FSM model and the local FSM model. The decision of the former acts as partial input information of the latter and the result of the latter is sent forward to the local path-planning module, meanwhile pulsating feedback to the former as real-time refresh data. To identify different traffic scenarios in a cerebrum-like way, the global FSM model is designed as 7 driving behavior states and 17 driving characteristic events, and the local FSM model is designed as 16 states and 8 characteristic events. In respect to designing a cerebrum-like algorithm for state transition, this paper firstly fuses AHP weight and EWM weight at their output layer to generate a synthetic weight coefficient for each characteristic event; then, it further fuses TOPSIS method and GRA method at the model building layer to obtain the implementable order of state transition. To verify the feasibility, reliability, and safety of the HFSM model as well as its TOPSIS-GRA state transition algorithm, this paper elaborates on a series of simulative experiments conducted on the PreScan8.50 platform. The results display that the accuracy of obstacle detection gets 98%, lane line prediction is beyond 70 m, the speed of collision avoidance is higher than 45 km/h, the distance of collision avoidance is less than 5 m, path planning time for obstacle avoidance is averagely less than 50 ms, and brake deceleration is controlled under 6 m/s2. These technical indexes support that the driving states set and characteristic events set for the HFSM model as well as its TOPSIS-GRA algorithm may bring about cerebrum-like decision-making effectiveness for ICV autonomous driving under 5G-V2X intelligent road infrastructure.

Events detection and handling based on hierarchical finite state machines in EAST PCS

Experimental Advanced Superconducting Tokamak (EAST) is committed to long pulse high performance operation where plasma parameters will necessarily approach stability limits, which sets a higher demand on real-time events detection and handling (EDH). In order to enhance the current EAST plasma control system (PCS) events handling ability and explore a new intelligent scheduling mode for China Fusion Engineering Testing Reactor (CFTER) PCS, the EDH algorithm based on hierarchical finite state machines (HFSM) is designed in EAST plasma control system (PCS). The events and states in PCS were designed, and we successfully validated the state transition and algorithm scheduling. Moreover, a new event detection and processing for controlling hot spots of in-vessel components from hot spots is developed, and a simulation experiment is carried out in the closed-loop test environment between PCS and MATLAB/Simulink. The simulation results show that the EDH algorithm could capture the exception in time and implement effective strategies with the change of hot spots temperature. The temperature of hot spots were prevented from reaching a drastic situation, which proved the effectiveness of the EDH to protect the internal components of the device.

Serious game design for soil tillage based on plowing forces model using neural network

Soil Tillage serious game designed as a training media has been researched based on the plowing forces using polynomial functions. However, the learning process is rare; hence the players in Serious Games (SG) are less engaged and tend to be more static in their games. The effects of vertical cutting angle, plowshare depth, and motor speed affect the soil plowing force in soil tillage. Therefore it is expected that a plow force model with a learning function will generate more actual conditions, engage the player and eventually affect the player’s behavior. The serious game design uses a Hierarchical Finite State Machine (HFSM) in this study. HFSM state is motor speed, vertical cutting angle, and plowing depth. The learning function is based on Neural Network (NN), with a multilayer feed-forward neural network (FFNN) is chosen to estimate plowing forces. The Levenberg-Marquardt algorithm is used by NN to approach second-order training speed without computing the Hessian matrix and is the fastest backpropagation algorithm. The result of the research is a plowing force model values closer to the actual by giving players feedback as they learn. In the transition, HFSM has a feedback value to the initial state, which is helpful as part of measuring one game cycle that is run, thus providing a learning experience in a serious game.

An event-triggered real-time motion planning strategy for autonomous vehicles

Motion planning is an essential part of autonomous vehicles. The planning process should respond to environmental changes in real time to ensure safety. This paper proposes an event-triggered real-time motion planning strategy to achieve a more real-time planning effect and a scenario-based planning process. The path planning process is discretized into several parts and integrated into the behavioral planning process. A hierarchical finite state machine (HFSM) based integrated motion planning process is proposed to trigger the discrete path planning parts according to environmental events. Thus, the output reference path can be obtained. Experiment and simulation results show the efficiency of our strategy.

Finite State Machine in Game Development

Finite State Machine is one of the oldest techniques in gaming where it was used in old games like PACMAN and new games like TOM RAIDER also. In all these games one major goal was to make non player characters more intelligent. There are some advance types also available but FSM still is one of the most used technique for non-player characters. The main goal of this paper is to explain how FSM works, how to create FSM and implement it in games using scripting or visual scripting. Hierarchical Finite State Machine is also discussed in this paper as it overcomes the limitations of older simple FSM. Using FSM, we can create intelligent AI agents. We can implement FSM and HFSM in games to make NPS’s behave like AI.

An Automatic Scenario Control in Serious Game to Visualize Tourism Destinations Recommendation

In the field of tourism, serious games are a pedagogical media application that helps players develop travel knowledge and expertise based on game content. A tourism serious game requires a scenario control system to visualize an attractive travel scenario. This paper proposes an Automatic Scenario Control in the serious game to visualize travel recommendation scenarios choice according to the player's expectations of potential tourism destinations criteria. There are two stages in system development, namely scenario design and scenario selection. In the scenario design stage, we use the Hierarchical Finite State Machine to translate challenge-based stories according to the type of attraction. While at the scenario selection stage, Dynamic Weight Topsis is a method for selecting one of the player's recommended scenarios. This study uses tourism destinations recommendations as to alternative variables, characteristics of tourism destinations as criteria, and players' expectations of tourism destinations' characteristics as weight criteria. In the implementation phase, the tourism serious game uses the content of tourism destinations in Mojokerto Indonesia. The test results show that Automatic Scenario Control generates a preference value for each alternative as a reference for choosing tourism destination scenarios for the player. Three things affect the scenario choice results, including the choice of month of tourist visits, player expectations of tourist destinations, and alternative input from the recommender system.

Top-Down Nested Supervisory Control of State-Tree Structures Based on State Aggregations

With a structured state space, state-tree structures (STS) are a powerful framework to model hierarchical finite state machines (HFSM). The boundary consistency property of STS endows them a compact and neatly representation. In this study, by naturally decomposing an STS into a set of STS nests in a top-down nested approach and finding a supervisor for each, the boundary consistency property is extended to the supervisory control of STS. As a consequence, the state spaces for both the system model and optimal supervisor are significantly reduced. Two examples are provided, in which the state space of a large scale HFSM example is reduced from 1024 to 2 × 1018.

Defense behavior of real time strategy games: comparison between HFSM and FSM

<span>RTS Game is one of the popular genre in PC gaming, which has been played by various type of players frequently. In RTS game, NPC Defense Building (Tower) has attacking behavior to the closest enemy without considering certain enemy parameters. This causes the NPC Tower to be more predictable by the opponent and easily defeated if NPC attacked by enemies in the group. Thus, this research simulates NPC Tower using Hierarchical Finite State Machine (HFSM) method compared with Finite State Machine (FSM). In this study, NPC Tower detects enemies by seeing at four parameters namely NPC Tower Health, Enemy's Health, Enemy Type, and Tower Distance to enemies. NPC Tower will attack the most dangerous enemy according to the ‘Degree of Danger’ parameter. Then use the decision-making logic of the rule-based system. The output of NPC Tower are three type of behaviors namely Aggressive Attacking, Regular Attacking, and Attack with Special Skill. From the test results of 3 NPC Tower, Kamandaka NPC Tower with HFSM method is winning 8.92% compare to Kamandaka Tower with FSM method. For Gayatri Tower NPC obtained equal results using both HFSM and FSM. Meanwhile, Adikara NPC with HFSM method is 4.62% superior to Adikara Tower with FSM method.</span>

Robot Soccer Strategy Based on Hierarchical Finite State Machine to Centralized Architectures

Robot soccer is frequently used to validate coordination strategies in multi-robot systems. This is because coordination among the robots allows a robot soccer team to perform better through coordinated behaviors like passing the ball between teammates, intercepting the ball when opponent players pass it between them, or taking possession of the ball. This requires the coordination strategies focused on robot soccer teams to be designed in line with the conditions of the game like the position of the ball, of teammates or of opponent players. This paper presents the architecture for robot soccer team coordination, involving the dynamic assignment of roles among the players. This strategy is divided into tactics, which are selected by a hierarchical state machine. Once a tactic has been selected, it is assigned roles to players, depending on the game conditions. Each role performs defined behaviors selected by the hierarchical state machine. To carry out the behaviors, robots are controlled by the lowest level of the hierarchical state machine. The architecture proposed is designed for robot soccer teams with a central decision-making body, with a global perception. The strategy presented is validated by simulation.

Path Planning under Interface-Based Constraints for Assistive Robotics

We present a heuristic-based search method for path planning in shared human-robot control scenarios in which the robot should adhere to specific motion constraints imposed by the human's control interface. This approach to path planning gives special consideration to kinematic and dynamic constraints introduced to reconcile discrepancies between the control space of the user and the control space of the robot. The resulting paths more closely mirror paths produced by users of the same interface; which is helpful, for example, when inferring human intent or for control sharing. Our first insight is to develop a hierarchical finite state machine describing the constrained state space, state transitions and associated costs. We then use this definition to embed the constraints of the interface into our heuristic planning algorithm, named C*, with simple modifications to the A*/D* family of graph search algorithms. This approach allows us to maintain powerful theoretical guarantees such as complexity and completeness. In this paper, we ground our augmented path planning algorithm with an implementation on a robotic wheelchair system and a Sip-and-Puff interface. We demonstrate that the new approach produces paths and control signals that more closely resemble user-generated data and can easily be incorporated into real hardware systems.

Intent Recognition in a Generalized Framework for Collaboration

For a collaborative assistive device, human intent recognition (IR) is one of the first and foremost requirements. Formalizing the complex process of human IR in a compact yet expressive mathematical model holds promise. We put forward a Hierarchical Finite State Machine (H-FSM) for human IR within a generalized framework for collaborative assistive devices. Visual and contextual observations drive the H-FSM to different levels of granularity.

Accurate abandoned and removed object classification using hierarchical finite state machine

The ability of most existing approaches to classify abandoned and removed objects (AROs) in images is affected by external environmental conditions such as illumination and traffic volume because the approaches use several pre-defined threshold values and generate many falsely-classified static regions. To reduce these effects, we propose an accurate ARO classification method using a hierarchical finite state machine (FSM) that consists of pixel-layer, region-layer, and event-layer FSMs, where the result of the lower-layer FSM is used as the input of the higher-layer FSM. Each FSM is defined by a Mealy state machine with three states and several state transitions, where a support vector machine (SVM) determines the state transition based on the current state and input features such as area, intensity, motion, shape, time duration, color and edge. Because it uses the hierarchical FSM (H-FSM) structure with features that are optimally trained by SVM classifiers, the proposed ARO classification method does not require threshold values and guarantees better classification accuracy under severe environmental changes. In experiments, the proposed ARO classification method provided much higher classification accuracy and lower false alarm rate than the state-of-the-art methods in both public databases and a commercial database. The proposed ARO classification method can be applied to many practical applications such as detection of littering, illegal parking, theft, and camouflaged soldiers.

Internal‐to‐internal transition method for consecutive hierarchical template matching

This study proposes a method reducing the tree traversal cost by first investigating the most probable node instead of the root node when a hierarchical template matching is consecutively applied to the object. In particular, this study gives a novel viewpoint that a consecutive hierarchical template matching could be regarded as a transition of a hierarchical finite state machine, and then it proposes a novel method considering the transitions between the internal nodes of the hierarchical template tree. The proposed method is verified by applying it to pedestrian silhouette detection.

Computer-Aided Formalization of Requirements Based on Patterns

Formalizing requirements in formal specifications is an effective way to deepen the understanding of the envisioned system and reduce ambiguities in the original requirements. However, it requires mathematical sophistication and considerable experience in using formal notations, which remains a challenge to many practitioners. To handle this challenge, this paper describes a pattern-based approach to facilitate the formalization of requirements. In this approach, a pattern system is pre-defined to guide requirements formalization where each pattern provides a specific solution for formalizing one kind of function into a formal expression. All of the patterns are classified and organized into a hierarchical structure according to the functions they can be used to formalize. The distinct characteristic of our approach is that all of the patterns are stored on computer as knowledge for creating effective guidance to facilitate the developer in requirements formalization; they are “understood” only by the computer but transparent to the developer. We also describe a prototype tool that supports the approach. It adopts Hierarchical Finite State Machine (HFSM) to represent the pattern knowledge and implements an algorithm for applying it to assist requirements formalization. Two experiments on the tool are presented to demonstrate the effectiveness of the approach.

Concurrent Hierarchical Finite State Machines for Modeling Pedestrian Behavioral Tendencies

A detailed and realistic simulation of pedestrian behavior requires a precise modeling of human decision making processes regarding action prioritization and selection. This paper presents a novel strategic pedestrian decision making model based on concurrent hierarchical finite state machines. The model is capable to create goal directed behavioral tendencies, which are operational guardrails for tactical models. The decision model is inherently flexible and scalable, being adaptable to different application scenarios, behavioral demands and input parameters. The applicability of the model is shown by means of an example. Furthermore, we discuss a validation and calibration approach for the decision model.

Hardware implementations of software programs based on hierarchical finite state machine models

Advances in microelectronic devices have dissolved the boundary between software and hardware. Faster hardware circuits that enable significantly greater parallelism to be achieved have encouraged recent research efforts into high-performance computation in electronic systems without the direct use of processing cores. Standard multi-core processors undoubtedly introduce a number of constraints, such as pre-defined operand sizes and instruction sets, and limits on concurrency and parallelism. This paper suggests a way to convert methods and functions that are defined in a general-purpose programming language into hardware implementations. Thus, conventional programming techniques such as function hierarchy, recursion, passing arguments and returning values can be entirely implemented in hardware modules that execute within a hierarchical finite state machine with extended capabilities. The resulting circuits have been found to be faster than their software alternatives and this conclusion is confirmed by numerous experiments in a variety of application areas.

Hierarchical finite state machines for autonomous mobile systems

This paper proposes a system architecture, related design approaches for autonomous mobile systems and guidelines for self-sufficient autonomy. Development of a tiered layout for a hybrid-state control in a series of stages as well as the integration of such a controller in the overall autonomy structure are proposed and demonstrated as part of multiple examples, including The Ohio State University participation in DARPA Urban Challenge 2007. The hierarchical layout and the iterative design methodology enable a certain level of design flexibility for the overall system and preparation for various contingencies, as illustrated on specific development cycles.