Dynamic Window Approach Research Articles

Model-based and machine learning-based high-level controller for autonomous vehicle navigation: lane centering and obstacles avoidance

<p>Researchers have been attempting to make the car drive autonomously. The environment perception together with safe guidance and control is an important task and are one of the big challenges when developing this kind of system. Geometrical or physical based models, machine learning based models and those based on a mixture of both models, are the three types of navigation methods used to resolve this problem. The last method takes advantage of the learning capability of machine learning models and uses the safeness of geometric models in order to better perform the navigation task. This paper presents a hybrid autonomous navigation methodology, which takes advantage of the learning capability of machine learning and uses the safeness of the dynamic window approach geometric method. Using a single camera and a 2D lidar sensor, this method actuates as a high-level controller, where optimal vehicle velocities are found, then applied by a low-level controller. The final algorithm is validated on CARLA Simulator environment, where the system proved to be capable to guide the vehicle in order to achieve the following tasks: lane keeping and obstacle avoidance.</p>

Research on Autonomous Navigation of Showroom Service Robot Based on ROS and Laser SLAM

As an important tool for guiding and introducing visitors to the exhibition hall, the robot needs to confront the complex environment that may exist and the constantly moving visitors. First of all, it is needed to have the ability to enable accurate positioning and navigation as well as dynamic obstacle avoidance. In recent years, simultaneous localization and mapping (SLAM) technology has been widely used to address localization and navigation issues in unknown indoor environments. Based on the robot operating system (ROS), this study collects environmental information by 2D LiDAR, and then combines the service robot's Inertial measurement unit (IMU), odometer, and other sensors to map the exhibition hall environment by the Cartographer SLAM algorithm. Path planning and dynamic obstacle avoidance functions are also implemented, in path planning, the algorithm is selected for global path planning and the Dynamic Window Approach (DWA) algorithm for local path planning. The environment map construction, path planning and dynamic obstacle avoidance functions are verified by simulation and in real environment. The average position deviation and standard deviation (SD) of the robot from the target point were less than 7 cm and less than 3 cm, respectively, when the robot was set to move at 0.5 m/s for the positioning test. The average heading deviation was less than 9° and SD was less than 3°. The robot's positioning and navigation can well meet the working requirements of the pavilion service robot.

A Data-Driven Approach to Motion Planning and Optimal Control of Medical Nanorobots with Dynamic Window Approach⋆

Targeted drug delivery via nanorobots has become an area of prominent research. However, since such robots are microns in size (and in the future, nanometers in size), implementing control laws to make sure the nanorobot does not deviate from a desired trajectory becomes exceedingly difficult. Building upon the existing nonlinear dynamic models of a nanorobot, this work proposes a data-driven method for optimal path planning and control of nanorobots. Specifically, the collision avoidance strategy, Dynamic Window Approach (DWA) implemented with linear quadratic regulator (LQR) control, is employed to simulate a randomly chosen nanorobot moving through the pulmonary artery against blood flow. The nanorobot is simulated as though it is being guided from the initial site to the target site via an induced magnetic field gradient generated by an MRI. It is shown that when full-state feedback control is implemented for nanorobot control, the LQR controller is able to quickly bring the nanorobot to desired states.

Local Path Planning: Dynamic Window Approach With Q-Learning Considering Congestion Environments for Mobile Robot

Local Path Planning: Dynamic Window Approach With Q-Learning Considering Congestion Environments for Mobile Robot

An energy-efficient hierarchical algorithm of dynamic obstacle avoidance for unmanned surface vehicle

Most of the existing studies developed and improved local path planning algorithms independently of global planning, i.e., ignoring the global optimal constrains. To meet the requirements of practical applications, this paper presented an energy-efficient hierarchical collision avoidance algorithm for unmanned surface vehicle operating in clustered dynamic environments. For the global level, genetic algorithm was modified by strategies of greedy-inspired population initialization, penalty-based multi-objective fitness function, and joint crossover. For the local level, velocity obstacle was combined with dynamic window approach to provide the kinematic constraints of the vehicle to its admissible velocities and simplified collision avoidance rules to guide the evasive maneuvers. Simulations showed that the proposed global algorithm was superior to three other algorithms in terms of path length, path smoothness, and convergence speed regardless of the environment size. The performance of the local algorithm was also verified for various encounter scenarios and speed ratios. In addition, the combination of the global and local planning can effectively solve the path optimization and dynamic obstacle avoidance in a designed offshore environment of fish cage culture.

Continuous shared control of a mobile robot with brain–computer interface and autonomous navigation for daily assistance

Although the electroencephalography (EEG) based brain–computer interface (BCI) has been successfully developed for rehabilitation and assistance, it is still challenging to achieve continuous control of a brain-actuated mobile robot system. In this study, we propose a continuous shared control strategy combining continuous BCI and autonomous navigation for a mobile robot system. The weight of shared control is designed to dynamically adjust the fusion of continuous BCI control and autonomous navigation. During this process, the system uses the visual-based simultaneous localization and mapping (SLAM) method to construct environmental maps. After obtaining the global optimal path, the system utilizes the brain-based shared control dynamic window approach (BSC-DWA) to evaluate safe and reachable trajectories while considering shared control velocity. Eight subjects participated in two-stage training, and six of these eight subjects participated in online shared control experiments. The training results demonstrated that naïve subjects could achieve continuous control performance with an average percent valid correct rate of approximately 97 % and an average total correct rate of over 80 %. The results of online shared control experiments showed that all of the subjects could complete navigation tasks in an unknown corridor with continuous shared control. Therefore, our experiments verified the feasibility and effectiveness of the proposed system combining continuous BCI, shared control, autonomous navigation, and visual SLAM. The proposed continuous shared control framework shows great promise in BCI-driven tasks, especially navigation tasks for brain-driven assistive mobile robots and wheelchairs in daily applications.

Towards Path Planning Algorithm Combining with A-Star Algorithm and Dynamic Window Approach Algorithm

Towards Path Planning Algorithm Combining with A-Star Algorithm and Dynamic Window Approach Algorithm

Mobile robot path planning using improved mayfly optimization algorithm and dynamic window approach

Mobile robot path planning using improved mayfly optimization algorithm and dynamic window approach

A Study on the Formation Control Algorithm of Multi-USVs According to COLREGs

In this paper, we propose a formation control algorithm for multi-USVs according to COLREGs. First, we applied the Dynamic Window Approach algorithm that can reflect the kinematic characteristics for the path movement of USVs. Then, we propose a virtual structure-based virtual leader-follower method that applies the advantages of leader-follower and virtual structure methods among conventional formation control algorithms for stability. Next, we proposed a collision avoidance algorithm according to all COLREGs when encountering an opposing ship by adding COLREGs situational conditions to the virtual leader, and finally confirmed the feasibility of the proposed method through simulation.

Collision avoidance control for unmanned surface vehicle with COLREGs compliance

In this paper, a collision avoidance control algorithm for unmanned surface vehicle (USV) with COLREGs is studied. To solve the constraints of actuator and dynamics in the maneuvering characteristics and the estimation of velocity window parameters in dynamic window approach (DWA), a real-time collision avoidance control algorithm based on dynamic constraints is proposed according to the principle of DWA, which mainly includes the design of candidate control behavior space, feasible trajectory prediction, collision risk assessment, acquisition of optimal control quantities and so on. The candidate control behavior space designed according to DWA meets the actuator constraints; The feasible trajectory prediction method can meet the dynamic constraints and avoid the problem of velocity window parameters estimation in DWA; The optimal control quantity method constructs the collision avoidance control evaluation function according to the collision risk evaluation principle, and obtain the feasible dynamic trajectory and collision avoidance control quantities at the same time. In addition, the collision avoidance rule function is introduced into the collision avoidance control evaluation function to enable the USV to comply with the COLREGs. Finally, simulation results are provided to illustrate the efficacy of collision avoidance control algorithm.

Distributed Model Predictive Contouring Control for Real-Time Multi-Robot Motion Planning

Existing motion planning algorithms for multi-robot systems must be improved to address poor coordination and increase low real-time performance. This paper proposes a new distributed real-time motion planning method for a multi-robot system using Model Predictive Contouring Control (MPCC). MPCC allows separating the tracking accuracy and productivity, to improve productivity better than the traditional Model Predictive Control (MPC) which follows a time-dependent reference. In the proposed distributed MPCC, each robot exchanges the predicted paths of the other robots and generates the collision-free motion in a parallel manner. The proposed distributed MPCC method is tested in industrial operation scenarios in the robot simulation platform Gazebo. The simulation results show that the proposed distributed MPCC method realizes real-time multi-robot motion planning and performs better than three commonly-used planning methods (dynamic window approach, MPC, and prioritized planning).

Robot path planner based on deep reinforcement learning and the seeker optimization algorithm

Path planning is one of the key technologies for mobile robot applications. However, the traditional robot path planner has a slow planning response, which leads to a long navigation completion time. In this paper, we propose a novel robot path planner (SOA+A2C) that produces global and local path planners with the seeker optimization algorithm (SOA) and the advantage actor-critic (A2C) algorithm, respectively. In addition, to solve the problems of poor convergence performance when training deep reinforcement learning (DRL) agents in complex path planning tasks and path redundancy when metaheuristic algorithms, such as SOA, are used for path planning, we propose the incremental map training method and path de-redundancy method. Simulation results show that first, the incremental map training method can improve the convergence performance of the DRL agent in complex path planning tasks. Second, the path de-redundancy method can effectively alleviate path redundancy without sacrificing the search capability of the metaheuristic algorithm. Third, the SOA+A2C path planner is superior to the Dijkstra & dynamic window approach (Dijkstra+DWA) and the Dijkstra & timed elastic band (Dijkstra+TEB) path planners provided by the robot operating system (ROS) in terms of path length, path planning response time, and navigation completion time. Therefore, the developed SOA+A2C path planner can serve as an effective tool for mobile robot path planning.

Control optimisation of automated guided vehicles in container terminal based on Petri network and dynamic path planning

• The task optimization and path planning of vehicles considering dynamic obstacle avoidance remain to be the urgent problems to be solved, so as to realize intelligence of container handling in container terminals. • The scheduling framework model of automated guided vehicle is established based on heuristic rules and OOTCSPN with vehicle behavior pattern as the top-level object, which can direct the traffic order and position sequence of the automated guided vehicle fleet. • Based on A* fusion DWA, path planning algorithm of automated guided vehicles is designed. Experiments show that the improved algorithm can improve vehicle operation efficiency, plan the route more smoothly and achieve random obstacle avoidance. To solve the problem of path optimisation and obstacle avoidance of automated guided vehicles (AGV) in the horizontal transportation of container terminals, this study proposed three operation modes of terminal vehicles and summarised four vehicle behaviour modes. Considering the vehicle behaviour pattern as the top-level object, based on heuristic rules and an object-oriented timed coloured stochastic Petri network (OOTCSPN) algorithm, a scheduling framework model of the AGV was established to optimise vehicle scheduling. A path planning model for three vehicle operation modes was designed for AGV path planning and real-time random obstacle avoidance based on the A-star(A*) algorithm fusion dynamic window approach (DWA). The simulation results indicate that the container handling efficiency increased by 13.2% using the improved algorithm. The scaled-down experiment confirms that the proposed method makes the planned path smoother and can also achieve real-time obstacle avoidance.

An Intelligent Inspection Robot for Underground Cable Trenches Based on Adaptive 2D-SLAM

With the rapid growth of underground cable trenches, the corresponding inspections become a heavy burden, and an intelligent inspection robot for automatic examinations in underground cable trenches would be a suitable solution. To achieve this, this paper establishes one new navigation methodology for intelligent inspection robots, especially when applied in complex scenarios and the corresponding hardware. Firstly, to map the underground trenches with higher precision, an improved graph optimization cartographer-SLAM algorithm is proposed, which is based on the combination of depth camera and LIDAR. The depth image is converted into pseudo laser data, and fused with LIDAR data for calibration. Secondly, to overcome the low precision of the Laser odometer due to the uneven ground, an adaptive keyframe selection method is designed. Thirdly, the forward A* model is presented, which has been adjusted in three aspects, including the convergence of node searching, the cost function, and the path smoothness, to adapt to the narrow underground environment for global path planning. Fourthly, to realize dynamic obstacle avoidance, an improved fusion scheme is built to integrate the proposed global path planning algorithm and the dynamic window approach (DWA). In the case study, the simulation experiments showed the advantage of the forward A* algorithm over the state-of-the-art algorithm in both time consumption and the number of inflection points generated, the field tests illustrated the effect of the fusion of depth camera images and LIDAR. Hence, the feasibility of this navigation methodology can be verified, and the average length of path and time consumption decreased by 6.5% and 17.8%, respectively, compared with the traditional methods.

A potential field-based trajectory planning and tracking approach for automatic berthing and COLREGs-compliant collision avoidance

A potential field-based Extended Dynamic Window Approach (EDWA) is proposed to fulfill the real-time trajectory planning for automatic berthing. To avoid falling into a local minimum, an nonuniform Theta* (NT*) is introduced to search the global path considering the risk of obstacles. Three potential fields are established: the attractive potential field guides the unmanned surface vehicle (USV) along its global path; the grid-based repulsive potential field is designed to keep the USV away from shores; and the COLREGs-compliant repulsive potential field is to avoid collision from other USVs. Taking the dynamic constraints of the USV into account, EDWA generates predicted trajectories of both constant force and deceleration phases. The objective function is subsequently produced to select them optimally according to the established potential fields. Finally, a linear MPC is presented to track the designed berthing trajectory considering the real-time requirement. The whole automatic berthing scheme is simulated on the Dalian port. The results indicate that the USVs avoid the potential collisions in accordance with COLREGs, and successfully reach their desired berthing spots with reasonable small deviations.

Deep Learning-Based NMPC for Local Motion Planning of Last-Mile Delivery Robot.

Feasible local motion planning for autonomous mobile robots in dynamic environments requires predicting how the scene evolves. Conventional navigation stakes rely on a local map to represent how a dynamic scene changes over time. However, these navigation stakes depend highly on the accuracy of the environmental map and the number of obstacles. This study uses semantic segmentation-based drivable area estimation as an alternative representation to assist with local motion planning. Notably, a realistic 3D simulator based on an Unreal Engine was created to generate a synthetic dataset under different weather conditions. A transfer learning technique was used to train the encoder-decoder model to segment free space from the occupied sidewalk environment. The local planner uses a nonlinear model predictive control (NMPC) scheme that inputs the estimated drivable space, the state of the robot, and a global plan to produce safe velocity commands that minimize the tracking cost and actuator effort while avoiding collisions with dynamic and static obstacles. The proposed approach achieves zero-shot transfer from a simulation to real-world environments that have never been experienced during training. Several intensive experiments were conducted and compared with the dynamic window approach (DWA) to demonstrate the effectiveness of our system in dynamic sidewalk environments.

Robot Path Planning Navigation for Dense Planting Red Jujube Orchards Based on the Joint Improved A* and DWA Algorithms under Laser SLAM

High precision navigation along specific paths is required for plant protection operations in dwarf and densely planted jujube orchards in southern Xinjiang. This study proposes a robotic path planning and navigation method for dense planting of red jujube orchards based on the improved A* and dynamic window approach (DWA) algorithms using Laser Radar to build maps. First, kinematic and physical robot simulation models are established; a map of the densely planted jujube orchard is constructed using Laser Radar. The robot’s position on the constructed map is described using an adaptive Monte Carlo positioning algorithm. Second, a combination of the improved A* and DWA algorithms is used to implement global and real-time local path planning; an evaluation function is used for path optimisation. The proposed path planning algorithm can accurately determine the robot’s navigation paths, with the average error U, average linear path displacement error, and L-shaped navigation being 2.69, 2.47, and 2.68 cm, respectively. A comparison experiment is set up in the specific path navigation section. The experimental results show that the improved fusion algorithm reduces the average navigation positioning deviation by 0.91cm and 0.54 cm when navigating L and U-shaped specific paths. The improved fusion algorithm is superior to the traditional fusion algorithm in navigation accuracy and navigation stability. It can improve the navigation accuracy of the dense planting jujube garden and provide a reference method for the navigation of the plant protection operation in the densely planted jujube orchards.

Cryptocurrency policy uncertainty and gold return forecasting: A dynamic Occam's window approach

The inherent relationship between gold and cryptocurrency has been verified for a long time. However, no research has explored the possible predictive ability of cryptocurrency market information on the gold market returns. Using a newly developed cryptocurrency policy uncertainty index (UCRY Policy) and an efficient forecasting method, named Dynamic Occam's Window (DOW), this paper identifies and compares the predictive power of UCRY Policy with many traditional predictors for the gold market. Our empirical results show that UCRY Policy does have good predictive power in forecasting weekly gold returns, and it is superior to many commonly used predictors throughout a data sample from 2014 to 2022. Moreover, the DOW method with various thresholds can outperform dynamic model averaging/selection (DMA/DMS) and many other conventional econometric models in forecasting weekly gold returns.

Improvement of Dynamic Window Approach Using Reinforcement Learning in Dynamic Environments

Improvement of Dynamic Window Approach Using Reinforcement Learning in Dynamic Environments

Improved Dynamic Window Approach for Unmanned Surface Vehicles' Local Path Planning Considering the Impact of Environmental Factors.

The aim of local path planning for unmanned surface vehicles (USVs) is to avoid unknown dynamic or static obstacles. However, current relative studies have not fully considered the impact of ocean environmental factors which significantly increase the control difficulty and collision risk of USVs. Therefore, this work studies two ocean environmental factors, namely, wave and current, given that they both have a significant impact on USVs. Furthermore, we redesign a kinematic model of an USV and the evaluation function of a classical and practical local path planning method based on the dynamic window approach (DWA). As shown by the results of the simulations, the path length was impacted mainly by the intensity of the environmental load and slightly by the direction of the environmental load, but the navigation time was significantly influenced by both. Taking the situation in still water as a benchmark in terms of the intensity and direction of the environmental factors, the maximum change rates of the path length were 8.6% and 0.6%, respectively, but the maximum change rates of the navigating time were 17.9% and 25.6%, separately. In addition, the average calculation time of each cycle was only 0.0418 s, and the longest time did not exceed the simulation time corresponding to a single cycle of 0.1 s. This method has proven to be a good candidate for real-time local path planning of USVs since it systematically considers the impact of waves and currents on the navigation of USVs, and thus ensures that USVs can adjust to the planned path in time and avoid obstacles when navigating in the real ocean environment.