Static Obstacles Research Articles

Глобальное планирование маршрута мобильного робота на основе графовых методов

The problem of global route planning for a mobile robot between two given points in a known area with static obstacles is considered. To solve the problem of constructing a route in an area with a large number of obstacles of complex shape, an integrated approach based on graph theory methods is proposed. It includes the Voronoi diagram, visibility graph and the Dijkstra's algorithm. At the first stage, the study area is represented as a polygonal object, the space outside the object is considered as obstacles. Next, to get a safe distance from obstacles, an internal buffer of the polygonal object is built using the Minkowski difference. Then the vertices of the polygon are compacted, and the Voronoi polygons are constructed from the resulting vertices. The median axis of the polygon is calculated from the Voronoi polygons. Then the Dijkstra's algorithm is applied to calculate the shortest path. The resulting path is used to construct a visibility graph, and the Dijkstra's algorithm is reapplied to the resulting graph. The proposed approach allows to build a route that is optimal in terms of length and distance to obstacles. It significantly reduces the computational complexity of constructing a visibility graph. The approach was implemented in the freely distributed QGIS geographic information system for planning the route of a mobile robot in an aquatic environment. The results of the experiment showed that the Voronoi diagram reduced the number of vertices required to construct the visibility graph by 8.3 times, while the visibility graph improved the path obtained from the Voronoi diagram by 8%. The proposed approach can be used for global planning of routes for mobile robots in various environments.

A Gaussian-Process-Based Model Predictive Control Approach for Trajectory Tracking and Obstacle Avoidance in Autonomous Underwater Vehicles

To achieve the efficient and precise control of autonomous underwater vehicles (AUVs) in dynamic ocean environments, this paper proposes an innovative Gaussian-Process-based Model Predictive Control (GP-MPC) method. This method combines the advantages of Gaussian process regression in modeling uncertainties in nonlinear systems, and MPC’s constraint optimization and real-time control abilities. To validate the effectiveness of the proposed GP-MPC method, its performance is first evaluated for trajectory tracking control tasks through numerical simulations based on a 6-degrees-of-freedom, fully actuated, AUV dynamics model. Subsequently, for 3D scenarios involving static and dynamic obstacles, an AUV horizontal plane decoupled motion model is constructed to verify the method’s obstacle avoidance capability. Extensive simulation studies demonstrate that the proposed GP-MPC method can effectively manage the nonlinear motion constraints faced by AUVs, significantly enhancing their intelligent obstacle avoidance performance in complex dynamic environments. By effectively handling model uncertainties and satisfying motion constraints, the GP-MPC method provides an innovative and efficient solution for the design of AUV control systems, substantially improving the control performance of AUVs.

Research on model predictive control of autonomous underwater vehicle based on physics informed neural network modeling

In the rapidly evolving field of Autonomous Underwater Vehicles (AUVs), achieving precise control remains a critical endeavor. This study presents a pioneering integration of Model Predictive Control (MPC) with a Physics-Informed Neural Network (PINN), aiming to enhance control system precision and operational efficiency in AUVs. The efficacy of MPC lies in its adept handling of the intricate constraints and inherent nonlinear dynamics intrinsic to AUV systems. Concurrently, the PINN architecture incorporates the fundamental physical laws represented by Partial Differential Equations (PDEs), augmenting the predictive fidelity of the system. Firstly, this research implements the novel PINN-enhanced MPC framework for trajectory tracking and conducts a comparative evaluation against adaptive proportional-integral-derivative (PID) and Gaussian-process-based MPC controllers. This comparative analysis elucidates the advancements in control mechanisms attributable to the PINN integration. Furthermore, this study meticulously assesses the PINN-MPC's proficiency in navigating through static and dynamic obstacles within three-dimensional marine environments, a critical capability for AUV operations. Through extensive and meticulous simulations, the proposed approach demonstrates notable progress in overcoming environmental challenges and executing intricate operational tasks, such as obstacle avoidance, with heightened efficiency and dexterity. This research constitutes a substantial contribution to the theoretical advancement and elucidation of control systems in the AUV domain, bearing profound practical implications. It lays the foundation for the development of increasingly sophisticated, advanced, and reliable AUV missions, signifying a crucial advancement in the realms of underwater exploration and operational technology.

Obstacle avoidance and trajectory optimisation for an autonomous vessel utilising MILP path planning, computer vision based perception and feedback control

In this study, we investigated autonomous vessel obstacle avoidance using advanced techniques within the Guidance, Navigation, and Control (GNC) framework. We propose a Mixed Integer Linear Programming (MILP) based Guidance system for robust path planning avoiding static and dynamic obstacles. For Navigation, we suggest a multi-modal neural network for perception, demonstrating the identification of obstacle type, position, and orientation using imaging sensors. Additionally, the paper compares an error-based PID control strategy and a Model Predictive Control (MPC) scheme as well. This evaluation aids in better evaluating their performance and determining their applicability within the GNC scheme. We detail the implementation of these systems, present simulation results, and offer a performance evaluation using an experimental dataset. Our findings, analysed through qualitative discussion and quantitative performance indicators, contribute to advancements in autonomous navigation and the control strategies to achieve it.

Low-Cost Small Scale Autonomous Vehicle

A low-cost small-scale autonomous vehicle refers to a self-driving vehicle that is affordable and designed for smaller applications or purposes. The firefly algorithm was used to solve obstacle-avoiding problems due to dynamic or static uncertain positioned obstacles. The autonomous vehicle reached the determined position, which could be considered accurate. Regardless of the starting point, it arrived at the defined destination in an area with a diameter of 5 meters. Considering the costs of the sensors, simple algorithm, not very powerful processor and circuit elements, sufficient success has been achieved.

An IoT Intelligent Approach for Safety and Efficiency of Robotic Medicine Delivery in Hospitals

In this paper, we introduce an IoT-based robotic medicine delivery system designed to boost safety and efficiency in hospital settings. This IoT-embedded robotic system integrates advanced sensors such as proximity, temperature, pressure, pulse rate, etc., sensors for ensuring real-time health and environmental monitoring behind this system. The robot is connected to a centralised controller, enabling healthcare workers to monitor patients using a cloud-based system. . Our robotic system moves about with the support of both line follower and LiDAR scanning technology for environmental safety and proximity detection. Experimental results show that the robotic system was able to navigate static obstacles and dynamically move away from the mobile entities within its reach without touching them. Besides, the proposed robotic system was able to reach the bed at the right time under normal operating conditions, which shows the efficiency of this approach in real-time settings. Patient feedback suggests that patients are very happy about the system, in terms of its usefulness, trustworthiness, and to their suprise to be taken care of by a robot. Overall, our study shows the potential of the proposed robotic system in streamlining the existing medicine delivery process in hospitals. It can potentially improve various aspects including safety, efficiency, patient compliance, and quality of care delivery. The promising results suggest further studies for incorporating advanced features and for ensuring compliance with regulatory requirements. Additional studies are to be conducted to further improve the proposed sensor-based robotic medicine delivery system, to facilitate its adoption in hospitals.

Prototype Model of Forklift with Mecanum Wheel Controlled Using Mobile

Industrial forklifts are used to load and unload goods. Electrical forklifts consume less power to drive the vehicle. In crowded spaces with static and/or dynamic obstacles and small corridors, such as industrial floors, warehouses, offices, and hospitals, multidirectional cars could carry out crucial functions. Mecanum wheel-mounted forklifts have seen several designs developed recently to enhance their multidirectional portability and usefulness. In this project, the center of gravity of the forklift is 67mm from the front axle and mecanum wheel diameter is 60mm. The direction of the mecanum wheel is determined by the direction of the leading edge of the roller, if the roller is pointed left then it is a left wheel and if the roller is pointed right then it is a right wheel. The mecanum wheel is a device that can move a vehicle in all directions, including forward, backward, left, right, diagonal, and more. This design has empowered us to create mecanum wheel-based forklift prototype, showcasing the potential for engineering solution. Key Words: Forklift, Mecanum wheel, multidirectional,

Research on the Application of Computer Big Data Technology in Smart Travel

This paper mainly focuses on the algorithms related to local path planning and path tracking control of unmanned vehicles in the process of obstacle avoidance. By introducing the temporal dimension as a reference, the perceptual results are projected onto the 3D spatio-temporal navigation map by combining the multi-target behavior prediction and other means; by increasing the temporal dimension, the static obstacles and dynamic obstacles are unified into the same parameter space. Under this parameter space, the front-end A* path search initializes the unified B spline curve control points, designs the trajectory cost function and performs nonlinear optimization to generate a spatio-temporal trajectory that satisfies the safety collision-free and vehicle motion constraints (speed and acceleration limits), thus transforming the decision and planning problem under the two-dimensional fence dynamic physical space into a static scene decision and planning problem under the three-dimensional spatio-temporal space. Through simulation verification, the whole process of the proposed trajectory planning method takes 51.27ms on average, which meets the driving requirements of driverless cars. In addition, by adjusting the search conditions of the A* algorithm, its overall planning efficiency is improved by 27.86% compared with the search speed of the traditional algorithm. The actual feeling and data results from the real vehicle experiments show its good tracking effect, which verifies the effectiveness and practicality of the algorithm proposed in this paper.

Robust Decision-Making for the Reactive Collision Avoidance of Autonomous Ships against Various Perception Sensor Noise Levels

Autonomous ships are expected to extensively rely on perception sensors for situation awareness and safety during challenging operations, such as reactive collision avoidance. However, sensor noise is inevitable and its impact on end-to-end decision-making has not been addressed yet. This study aims to develop a methodology to enhance the robustness of decision-making for the reactive collision avoidance of autonomous ships against various perception sensor noise levels. A Gaussian-based noisy perception sensor is employed, where its noisy measurements and noise variance are incorporated into the decision-making as observations. A deep reinforcement learning agent is employed, which is trained in different noise variances. Robustness metrics that quantify the robustness of the agent’s decision-making are defined. A case study of a container ship using a LIDAR in a single static obstacle environment is investigated. Simulation results indicate sophisticated decision-making of the trained agent prioritising safety over efficiency when the noise variance is higher by conducting larger evasive manoeuvres. Sensitivity analysis indicates the criticality of the noise variance observation on the agent’s decision-making. Robustness is verified against noise variance up to 132% from its maximum trained value. Robustness is verified only up to 76% when the agent is trained without the noise variance observation with lack of its prior sophisticated decision-making. This study contributes towards the development of autonomous systems that can make safe and robust decisions under uncertainty.

Shortest Path Planning and Efficient Fuzzy Logic Control of Mobile Robots in Indoor Static and Dynamic Environments

Efficient navigation in dynamic environments is a critical skill for of mobile robots, where obstacles can stochastically appear. This paper presents a complete navigation and control system that integrates effective path optimization and motion control capabilities for mobile robots evolving in indoor static and dynamic environments. This system consists primarily of two layers. In the Optimization Layer (Global planner), a Deterministic Constructive Algorithm (DCA) quickly generates the shortest path, as a sequence of nodes, to get to the goal position while avoiding the static obstacles. The Control layer (Local planner) employs an Efficient Fuzzy Logic Controller (EFLC) to continuously guide the robot around the detected dynamic obstacles and drive safely the robot along the intended path. Simulations conducted on various maps with different complexities demonstrate the effectiveness of the DCA planner. Finally, validations using V-REP software show the strength of the proposed EFLC that mimics human reasoning for mobile robots navigating in dynamic environments.

Multi-robot consensus formation based on virtual spring obstacle avoidance

Abstract. A systematic improvement of the multi-robot formation control algorithm has been developed to address multi-robot formation instability. First, a static obstacle avoidance model based on spring force mapping is proposed, followed by an analysis of the influence of static and dynamic obstacles on the processing of multi-robot cooperative motion. Second, a leader is introduced to the formation to save computational costs. Third, the Velocity Obstacle (VO) algorithm is improved to resolve robot collisions during the dynamic mobility process caused by the increased number of multi-robot formations. Simultaneously, the dynamic speed limit function based on the position error for formation keeping is established. Finally, simulation experiments are carried out. Results show that when 5-robot and 20-robot formations were compared in the environment without dynamic conflict, the average value of the position error of 20-robot formations only increased by 39.47 %, and the average value of the path length did not differ significantly. In the dynamic conflict environment, the maximum position error of 20-robot formations increases by 73.03 % and the path length average value increases by 7.69 %. Our proposed method can control the motion of multiple robots in both conflict-free and conflict-filled environments, resulting in an effective motion planning scheme.

Global Dynamic Path Planning of AGV Based on Fusion of Improved A* Algorithm and Dynamic Window Method.

Designed to meet the demands of AGV global optimal path planning and dynamic obstacle avoidance, this paper proposes a combination of an improved A* algorithm and dynamic window method fusion algorithm. Firstly, the heuristic function is dynamically weighted to reduce the search scope and improve the planning efficiency; secondly, a path-optimization method is introduced to eliminate redundant nodes and redundant turning points in the path; thirdly, combined with the improved A* algorithm and dynamic window method, the local dynamic obstacle avoidance in the global optimal path is realized. Finally, the effectiveness of the proposed method is verified by simulation experiments. According to the results of simulation analysis, the path-planning time of the improved A* algorithm is 26.3% shorter than the traditional A* algorithm, the search scope is 57.9% less, the path length is 7.2% shorter, the number of path nodes is 85.7% less, and the number of turning points is 71.4% less. The fusion algorithm can evade moving obstacles and unknown static obstacles in different map environments in real time along the global optimal path.

Dynamic path planning via Dueling Double Deep Q-Network (D3QN) with prioritized experience replay

Path planning is a key requirement for mobile robots employed for different tasks such as rescue or transport missions. Conventional methods such as A* or Dijkstra to tackle path planning problem need a premise map of the robot's environment. Nowadays, dynamic path planning is a popular research topic, which drives mobile robots without prior static requirements. Deep reinforcement learning (DRL), which is another popular research area, is being harnessed to solve dynamic path planning problem by the researchers. In this study, Deep Q-Networks, which is a subdomain of DRL are opted to solve dynamic path planning problem. We first employ well known techniques Double Deep Q-Networks (D2QN) and Dueling Double Deep Q-Networks (D3QN) to train a model which can drive a mobile robot in environments with static and dynamic obstacles within 3 different configurations. Then we propose D3QN with Prioritized Experience Replay (PER) extension in order to further optimize the DRL model. We created a test bed to measure the performance of the DRL models against 99 randomly generated goal locations. According to our experiments, D3QN-PER method performs better than D2QN and D3QN in terms of path length and travel time to the goal without any collisions. Robot Operating System and Gazebo simulation environment is utilized to realize the training and testing environments, thus, the trained DRL models can be deployed to any ROS compatible robot seamlessly.

Collision-free automatic berthing of maritime autonomous surface ships via safety-certified active disturbance rejection control

This paper addresses the automatic berthing of a maritime autonomous surface ship operating in a confined water environment subject to static obstacles, dynamic obstacles, thruster constraints, and space constraints due to shorelines. A safety-certified active disturbance rejection control (ADRC) method is proposed for achieving the automatic berthing task of an MASS in the presence of model uncertainties and ocean disturbances. An extended state observer (ESO) based on a second-order robust exact differentiator (RED) is employed to estimate an extended state vector consisting of internal model uncertainties and external ocean disturbances. With the aid of the RED-based ESO, a nominal ADRC law is designed to achieve the position and heading stabilization. To avoid collisions with static obstacles, dynamic obstacles, and shorelines, input-to-state safe high-order control barrier functions are used to guarantee safety. Optimized control signals are obtained based on a constrained quadratic programming (QP) problem within safety constraints. In order to translate the control signals into the individual thruster command, a constrained QP problem is further used to search for optimized commands in real time. It is proven that the closed-loop automatic berthing system is input-to-state stable. By using the proposed method, the MASS is able to reach the desired position and heading with collision avoidance. Simulation results verify the effectiveness of the proposed safety-certified ADRC method for automatic berthing.

Autonomous Behavior Selection For Self-driving Cars Using Probabilistic Logic Factored Markov Decision Processes

ABSTRACT We propose probabilistic logic factored Markov decision processes (PL-fMDPs) as a behavior selection scheme for self-driving cars. Probabilistic logic combines logic programming with probability theory to achieve clear, rule-based knowledge descriptions of multivariate probability distributions, and a flexible mixture of deductive and probabilistic inferences. Factored Markov decision processes (fMDPs) are widely used to generate reward-optimal action policies for stochastic sequential decision problems. For evaluation, we developed a simulated self-driving car with reliable modules for behavior selection, perception, and control. The behavior selection module is composed of a two-level structure of four action policies obtained from PL-fMDPs. Three main tests were conducted focused on the selection of the appropriate actions in specific driving scenarios, and the overtaking of static obstacle vehicles and dynamic obstacle vehicles. We performed 520 repetitions of these tests. The self-driving car completed its task without collisions in 99.2% of the repetitions. Results show the suitability of the overall self-driving strategy and PL-fMDPs to construct safe action policies for self-driving cars.

V2X assisted co‐design of motion planning and control for connected automated vehicle

AbstractThe rapid development of vehicle‐to‐everything (V2X) communication technologies significantly promotes the revolution of intelligent transportation systems. V2X communication is expected to play a critical role in enhancing the safety and efficiency of connected and automated vehicles (CAVs), especially for mixed traffic scenarios. Additionally, the computational and storage capabilities of roadside units (RSUs) will be harnessed to effectively enhance the motion planning and control performance of CAVs within the constraints of limited on‐board computational resources. Thus, a V2X assisted co‐design of motion planning and control algorithm for CAVs to improve their situational awareness and computational efficiency is proposed. Under this architecture, a pre‐planning algorithm is proposed first to utilize the computational and storage capabilities of RSUs and generate feasible trajectories for different driving tasks. By analysing the relationship between driving risk index and motion planning performance, an online‐planning algorithm is derived to modify the pre‐planned trajectories in real‐time with static or dynamic obstacles. Furthermore, the lateral and longitudinal control of the vehicle using the Frenet coordinate system is decoupled. The lateral control employs an offline linear quadratic regulator (LQR) from RSUs to control the steering angle of the vehicle. The longitudinal control employs a dual‐loop PID to control the throttle opening of the vehicle. The performance of the proposed framework is evaluated and demonstrated by a Carsim‐Prescan simulation study in different mixed traffic scenarios. Compared with conventional methods, the proposed method improves the computational efficiency by 23% and reduces the collision rate by 13%.

Real-time navigation of mecanum wheel-based mobile robot in a dynamic environment

Path planning and control of a mobile robot, in a dynamic environment, has been an important research topic for many years. In this paper an algorithm for autonomous motion of a mobile robot is proposed, with mecanum wheels, to reach a goal while avoiding obstacles through the shortest path in a dynamic environment. The proposed method uses a hybrid A⁎ and a velocity obstacle algorithms for path planning and obstacle avoidance. The A⁎ algorithm is implemented to explore the shortest path from starting position to the goal while avoiding all the static obstacles. However, in real time applications the dynamic obstacles need to be avoided, therefore, for such a case velocity obstacle algorithm is unified with the A⁎ algorithm. Initially, the proposed algorithm is verified through simulations. Then it is implemented using experimental setup in real time environment using single and multiple static obstacles as well as on a dynamic obstacle. It can be observed that the robot reaches the goal, effectively by avoiding static and dynamic obstacles. Moreover, the performance of the proposed work is evaluated through qualitative comparison between proposed method and recently published work, showing that the proposed algorithm is gives better features than existing work. In the end, the possible application of mobile robot having mecanum wheels with proposed path planning method is also given in the paper.

Predictive Dead Reckoning for Online Peer-to-Peer Games

In online peer-to-peer games, players send periodic updates to each other and each player must locally reconstruct the position of their opponents in between these updates. In scenarios where players are driving cars, high speeds produce more pronounced errors in local replication of online opponents. In this work, we propose a new method of replicating opponents with less data sent and up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$45\%$</tex-math></inline-formula> less error compared to the state-of-the-art. We use a neural network based approach to predict an opponent's position, combined with a path tracking controller from the field of mobile robotics, to produce smooth, believable trajectories for opponents' vehicles. We also propose a neural network based approach to predict a replicated opponent's trajectory following a collision with a static obstacle.

A Herd-Foraging-Based Approach to Adaptive Coverage Path Planning in Dual Environments.

Coverage path planning (CPP) is essential for robotic tasks, such as environmental monitoring and terrain surveying, which require covering all surface areas of interest. As the pioneering approach to CPP, inspired by the concept of predation risk in predator-prey relations, the predator-prey CPP (PPCPP) has the benefit of adaptively covering arbitrary bent 2-D manifolds and can handle unexpected changes in an environment, such as the sudden introduction of dynamic obstacles. However, it can only work in bounded environment and cannot handle tasks in unbounded one, e.g., search and rescue tasks where the search boundary is unknown. Sometimes, robots are required to handle both bounded and unbounded environments, i.e., dual environments, such as capturing criminals in a city. Once encountering a building, the robot enters it to cover the bounded environment, then continues to cover the unbounded one when leaving the building. Therefore, the capability of swarm robots for the coverage tasks both in bounded and unbounded environments is important. In nature, herbivores live in groups to find more food and reduce the risk of predation. Especially the juvenile ones prefer to forage near the herd to protect themselves. Inspired by the foraging behavior of animals in a herd, this article proposes an online adaptive CPP approach that enables swarm robots to handle both bounded and unbounded environments without knowing the environmental information in advance, called dual-environmental herd-foraging-based CPP (DH-CPP). It's performance is evaluated in dual environments with stationary and dynamic obstacles of different shapes and quantity, and compared with three state-of-the-art approaches. Simulation results demonstrate that it is highly effective to handle dual environments.

Beyond the stable handling limits: nonlinear model predictive control for highly transient autonomous drifting

Autonomous vehicles that can reliably operate outside the stable handling limits would have access to a wider range of maneuvers in emergencies, improving overall safety. To that end, this paper presents a novel Nonlinear MPC approach for vehicle control with deeply saturated rear tires. Longitudinal slip management is elevated from the chassis control layer into the optimisation problem by using a coupled-slip tire model, and explicitly including wheelspeed dynamics. Terminal costs on sideslip stability help compensate for the finite horizon, while road bounds and static obstacles are encoded using slack constraints. Experiments on a racetrack with a modified Toyota GR Supra validate the controller's ability to smoothly transition from dynamic, non-equilibrium drifting to grip driving. Further experiments demonstrate robustness to significant longitudinal force and wheelspeed disturbances, and showcase the controller flexibly transitioning in and out of the sliding tire regime to balance slack constraints with tracking objectives.