Planning Module Research Articles

Deep reinforcement learning augmented decision model for intelligent driving cars

In view of the fact that the state machine decision model cannot effectively handle the rich contextual information and the influence of uncertain factors in ice and snow environments, a deep reinforcement learning agent based on the deep Q network algorithm (DQN) was constructed. The motion planner was used to augment the agent, and the rule-based decision planning module and the deep reinforcement learning model were integrated to establish the DQN-planner model, thereby improving the convergence speed and driving ability of the reinforcement learning agent. Finally, based on the CARLA simulation platform, a comparative experiment was conducted on the driving ability of the DQN model and the DQN-planner model on low-adhesion ice and snow roads, and the training process and verification results were analyzed respectively.

Energy-Aware Hierarchical Control of Joint Velocities

Nowadays, robots are applied in dynamic environments. For a robust operation, the motion planning module must consider other tasks besides reaching a specified pose: (self) collision avoidance, joint limit avoidance, keeping an advantageous configuration, etc. Each task demands different joint control commands, which may counteract each other. We present a hierarchical control that, depending on the robot and environment state, determines online a suitable priority among those tasks. Thereby, the control command of a lower-prioritized task never hinders the control command of a higher-prioritized task. We ensure smooth control signals also during priority rearrangement. Our hierarchical control computes reference joint velocities. However, the underlying concepts of hierarchical control differ when using joint accelerations or joint torques as control signals instead. So, as a further contribution, we provide a comprehensive discussion on how joint velocity control, joint acceleration control, and joint torque control differ in hierarchical task control. We validate our formulation in an experiment on hardware.

A real time data-driven dynamic glasius bionic neural network path planning algorithm for polar under-ice feature scanning by “Xinghai 1000” AUV

Using Autonomous Underwater Vehicle (AUV) to survey polar under-ice feature is crucial for studying polar marine environment and global climate change. Compared with seafloor terrain scanning, it faces several challenges, such as uncertain under-ice environment, lack of reliable positioning methods, and stringent constraints on recovery location. Thus, taking “Xinghai 1000” as analysis object, this paper proposes a real time data-driven dynamic glasius bionic neural network path planning algorithm (RDGPP), which consists of an online bi-level path planning module. In global planning module, dynamically hierarchical strategy is used to realize task area layering. On this basis, global coverage path is planned by combining neuron activity value updated which utilize real-time environmental information obtained by FLS sonar with multivariant strategy. Moreover, due to AUV recovery mode limitation, return strategy has been devised in multivariant strategy to ensure AUV automatic return to launch point, thereby reducing energy usage. In local planning module, Flagged bit and GBNN-driven A-star algorithm (FGA) is introduced to minimize deadlock escape time for AUV. Simulation experiments verify RDGPP algorithm advancement in key indicators such as turning times, running time, etc., and effectiveness is verified by “Xinghai 1000” under-ice experiment.

Development of a digital module for planning and installation of the audio system subject in audio video engineering skills competency

Development of a digital module for planning and installation of the audio system subject in audio video engineering skills competency

Generative design for complex floorplans in high-rise residential buildings: A Monte Carlo tree search-based self-organizing multi-agent system (MCTS-MAS) solution

This research aims to develop an innovative generative design algorithm for complex floorplan layout designs in high-rise residential buildings. Unlike conventional methods, which treat such a task as an optimization problem, we approach it as an adaption problem to be solved by combining a self-organized multi-agent system (MAS) and Monte Carlo tree search (MCTS) algorithm. The approach involves two steps. The first is design constraints pre-processing, which comprises (a) initial user input, and (b) pre-processing for initial setup. The second is building plan generation, involving (a) perception, (b) planning, and (c) action modules. Multiple illustrative examples are explored to verify the proposed generative design algorithm in terms of robustness, efficiency, and scale. We discover that the algorithm can handle complex combinations of input constraints (e.g., number of rooms, room areas, adjacency connections, and building boundaries) and generate plausible floorplans in a robust, efficient way that can be scaled up to bigger, more complex floorplan generative design problems. With proper adaptation, the algorithm can potentially be applied to other building types, such as office or hospital buildings.

Competing with autonomous model vehicles: a software stack for driving in smart city environments

This article introduces an open-source software stack designed for autonomous 1:10 scale model vehicles. Initially developed for the Bosch Future Mobility Challenge (BFMC) student competition, this versatile software stack is applicable to a variety of autonomous driving competitions. The stack comprises perception, planning, and control modules, each essential for precise and reliable scene understanding in complex environments such as a miniature smart city in the context of BFMC. Given the limited computing power of model vehicles and the necessity for low-latency real-time applications, the stack is implemented in C++, employs YOLO Version 5 s for environmental perception, and leverages the state-of-the-art Robot Operating System (ROS) for inter-process communication. We believe that this article and the accompanying open-source software will be a valuable resource for future teams participating in autonomous driving student competitions. Our work can serve as a foundational tool for novice teams and a reference for more experienced participants. The code and data are publicly available on GitHub.

Probabilistic Path Planning for UAVs in Forest Fire Monitoring: Enhancing Patrol Efficiency through Risk Assessment

Forest fire is a significant global natural disaster, and unmanned aerial vehicles (UAVs) have gained attention in wildfire prevention for their efficient and flexible monitoring capabilities. Proper UAV patrol path planning can enhance fire-monitoring accuracy and response speed. This paper proposes a probabilistic path planning (PPP) module that plans UAV patrol paths by combining real-time fire occurrence probabilities at different points. Initially, a forest fire risk logistic regression model is established to compute the fire probabilities at different patrol points. Subsequently, a patrol point filter is applied to remove points with low fire probabilities. Finally, combining fire probabilities with distances between patrol points, a dynamic programming (DP) algorithm is employed to generate an optimal UAV patrol route. Compared with conventional approaches, the experimental results demonstrate that the PPP module effectively improves the timeliness of fire monitoring and containment, and the introduction of DP, considering that the fire probabilities and the patrol point filter both contribute positively to the experimental outcomes. Different combinations of patrol point coordinates and their fire probabilities are further studied to summarize the applicability of this method, contributing to UAV applications in forest fire monitoring and prevention.

Multi-institutional investigation into the robustness of intra-cranial multi-target stereotactic radiosurgery plans to patient setup errors

PurposeThis study aimed to analyse correlations between planning factors including plan geometry and plan complexity with robustness to patient setup errors. MethodsMultiple-target brain stereotactic radiosurgery (SRS) plans were obtained through the Trans-Tasman Radiation Oncology Group (TROG) international treatment planning challenge (2018). The challenge dataset consisted of five intra-cranial targets with a 20 Gy prescription. Setup error was simulated using an in-house tool. Dose to targets was assessed via dose covering 99 % (D99 %) of gross tumour volume (GTV) and 98 % of planning target volume (PTV). Dose to organs at risk was assessed using volume of normal brain receiving 12 Gy and maximum dose covering 0.03 cc of brainstem. Plan complexity was assessed via edge metric, modulation complexity score, mean multi-leaf collimator (MLC) gap, mean MLC speed and plan modulation. ResultsEven for small (0.5 mm/°) errors, GTV D99 % was reduced by up to 20 %. The strongest correlation was found between lower complexity plans (larger mean MLC gap and lower edge metric) and higher robustness to setup error. Lower complexity plans had 1 %–20 % fewer targets/scenarios with GTV D99 % falling below the specified tolerance threshold. These complexity metrics correlated with 100 % isodose volume sphericity and dose conformity, though similar conformity was achievable with a range of complexities. ConclusionsA higher level of importance should be directed towards plan complexity when considering plan robustness. It is recommended when planning multi-target SRS, larger MLC gaps and lower MLC aperture irregularity be considered during plan optimisation due to higher robustness should patient positioning errors occur.

A novel query execution time prediction approach based on operator iterate-aware of the execution plan on the graph database

Query execution time prediction is essential for database query optimization tasks, such as query scheduling, progress monitoring, and resource allocation. In the query execution time prediction tasks, the query plan is often used as the modeling object of a prediction model. Although the learning-based prediction models have been proposed to capture plan features, there are two limitations need to be considered more. First, the parent–child dependencies between plan operators can be captured, but the operator’s branch independence cannot be distinguished. Second, each operator’s output row is its following operator input, but the data iterate transfer operations between operators are ignored. In this study, we propose a graph query execution time prediction model containing a plan module, a query module, a plan-query module, and a prediction module to improve prediction effectiveness. Specifically, the plan module is used to capture the data iterate transfer operations and distinguish independent of branch operators; the query module is used to learn features of query terms that have an influence on the composition of operators; the plan-query interaction module is used to learn the logical correlations of plan and query. The experiment on datasets proves the effectiveness of the operator iterate-aware and query-plan interaction method in our proposed graph query execution prediction model.

The impact of plan complexity on calculation and measurement-based pre-treatment verifications for sliding-window intensity-modulated radiotherapy

Background and purposeIn sliding-window intensity-modulated radiotherapy, increased plan modulation often leads to increased plan complexities and dose uncertainties. Dose calculation and/or measurement checks are usually adopted for pre-treatment verification. This study aims to evaluate the relationship among plan complexities, calculated doses and measured doses. Materials and methodsA total of 53 plan complexity metrics (PCMs) were selected, emphasizing small field characteristics and leaf speed/acceleration. Doses were retrieved from two beam-matched treatment devices. The intended dose was computed employing the Anisotropic Analytical Algorithm and validated through Monte Carlo (MC) and Collapsed Cone Convolution (CCC) algorithms. To measure the delivered dose, 3D diode arrays of various geometries, encompassing helical, cross, and oblique cross shapes, were utilized. Their interrelation was assessed via Spearman correlation analysis and principal component linear regression (PCR). ResultsThe correlation coefficients between calculation-based (CQA) and measurement-based verification quality assurance (MQA) were below 0.53. Most PCMs showed higher correlation rpcm-QA with CQA (max: 0.84) than MQA (max: 0.65). The proportion of rpcm-QA ≥ 0.5 was the largest in the pelvis compared to head-and-neck and chest-and-abdomen, and the highest rpcm-QA occurred at 1 %/1mm. Some modulation indices for the MLC speed and acceleration were significantly correlated with CQA and MQA. PCR’s determination coefficients (R2) indicated PCMs had higher accuracy in predicting CQA (max: 0.75) than MQA (max: 0.42). ConclusionsCQA and MQA demonstrated a weak correlation. Compared to MQA, CQA exhibited a stronger correlation with PCMs. Certain PCMs related to MLC movement effectively indicated variations in both quality assurances.

Sparing the Hippocampus in Prophylactic Cranial Irradiation Using Three Different Linear Accelerators: A Comparative Study.

Hippocampus protection, as an organ at risk in brain radiotherapy, might protect patients' quality of life. Prophylactic cranial irradiation (PCI) has been used traditionally in small cell lung cancer (SCLC) patients as it increases survival. This study aimed to discover the contributing parameters for a successful PCI with simultaneous protection of the hippocampus by using three different treatment machines. For this purpose, treatment plans were generated for 45 SCLC patients using three half-arcs in three linear accelerators (LINACs; Elekta Infinity, Synergy, and Axesse; Elekta Ltd, Stockholm, Sweden) with different radiation field sizes and multileaf collimator (MLC) leaf thickness characteristics. The prescribed dose was 25 Gy in 10 fractions. Thresholds for the hippocampus were calculated based on the Radiation Therapy Oncology Group 0933 dose constraints. The planning and treatment system templates were common to all three LINACs. Plan evaluation was based on the dosimetric target coverage by the 95% isodose, the maximum dose of the plan, the conformity index (CI), the degree of plan modulation (MOD), and the patient-specific quality assurance (QA) pass rate. The mean target coverage was highest for Infinity (97.3%), followed by Axesse (96.6%) and Synergy (95.5%). The mean maximum dose was higher for Synergy (27.5 Gy), followed by Infinity (27.0 Gy) and Axesse (26.9 Gy). Axesse plans had the highest CI (0.93), followed by Infinity (0.91) and Synergy (0.88). Plan MOD was lower for Synergy (2.88) compared with Infinity (3.07) and Axesse (3.69). Finally, patient-specific QA was successful in all Infinity plans, in all but one Synergy plan, and in 17/45 Axesse plans, as was expected from the field size in that treatment unit. Based on overall performance, the most favorable combination of target coverage, hippocampus sparing, and plan deliverability was obtained with the LINAC, which has the largest field opening and thinnest MLC leaves.

6-DOF UAV Path planning and tracking control for obstacle avoidance: a deep learning-based integrated approach

Path planning is crucial for achieving autonomous and safe flight of fixed-wing unmanned aerial vehicles (UAVs). The existing methods generally cannot simultaneously balance real-time performance, near optimality, and feasibility in three-dimensional obstacle environments. To this end, this paper proposes a deep learning-based integrated path planning and tracking control framework for obstacle avoidance. First, a fundamental framework, including an interfered fluid dynamical system (IFDS)-based path planning module and a backstepping control-based path tracking module, is established. Then, to satisfy high real-time requirements, a long short-term memory (LSTM)-based fast online decision-making network matched with the IFDS is developed. Extensive training samples are generated by the fundamental framework, and receding horizon control is employed to optimize these samples so that the LSTM can provide near-optimal coefficients for the IFDS. Furthermore, the dynamic characteristics of an actual UAV system and the performance of the tracking controller are fully considered during sample generation, enabling that the paths planned by the LSTM-assisted IFDS are highly feasible. Finally, the results of numerical simulations and hardware-in-the-loop experiments show that our method can plan near-optimal obstacle-free paths with high feasibility in real-time.

Synthesis and Verification of Mission Plans for Multiple Autonomous Agents under Complex Road Conditions

Mission planning for multi-agent autonomous systems aims to generate feasible and optimal mission plans that satisfy given requirements. In this article, we propose a tool-supported mission-planning methodology that combines (i) a path-planning algorithm for synthesizing path plans that are safe in environments with complex road conditions, and (ii) a task-scheduling method for synthesizing task plans that schedule the tasks in the right and fastest order, taking into account the planned paths. The task-scheduling method is based on model checking, which provides means of automatically generating task execution orders that satisfy the requirements and ensure the correctness and efficiency of the plans by construction. We implement our approach in a tool named MALTA, which offers a user-friendly GUI for configuring mission requirements, a module for path planning, an integration with the model checker UPPAAL, and functions for automatic generation of formal models, and parsing of the execution traces of models. Experiments with the tool demonstrate its applicability and performance in various configurations of an industrial case study of an autonomous quarry. We also show the adaptability of our tool by employing it in a special case of an industrial case study.

A domain-independent agent architecture for adaptive operation in evolving open worlds

1Angry Birds Competition. Model-based reasoning agents are ill-equipped to act in novel situations in which their model of the environment no longer sufficiently represents the world. We propose HYDRA, a framework for designing model-based agents operating in mixed discrete-continuous worlds that can autonomously detect when the environment has evolved from its canonical setup, understand how it has evolved, and adapt the agents' models to perform effectively. HYDRA is based upon PDDL+, a rich modeling language for planning in mixed, discrete-continuous environments. It augments the planning module with visual reasoning, task selection, and action execution modules for closed-loop interaction with complex environments. HYDRA implements a novel meta-reasoning process that enables the agent to monitor its own behavior from a variety of aspects. The process employs a diverse set of computational methods to maintain expectations about the agent's own behavior in an environment. Divergences from those expectations are useful in detecting when the environment has evolved and identifying opportunities to adapt the underlying models. HYDRA builds upon ideas from diagnosis and repair and uses a heuristics-guided search over model changes such that they become competent in novel conditions. The HYDRA framework has been used to implement novelty-aware agents for three diverse domains - CartPole++ (a higher dimension variant of a classic control problem), Science Birds (an IJCAI competition problem1), and PogoStick (a specific problem domain in Minecraft). We report empirical observations from these domains to demonstrate the efficacy of various components in the novelty meta-reasoning process.

Experimental validation of the accuracy of robotic-assisted radioactive seed implantation for tumor treatment.

An experimental validation of a robotic system for radioactive iodine-125 seed implantation (RISI) in tumor treatment was conducted using customized phantom models and animal models simulating liver and lung lesions. The robotic system, consisting of planning, navigation, and implantation modules, was employed to implant dummy radioactive seeds into the models. Fiducial markers were used for target localization. In phantom experiments across 40 cases, the mean errors between planned and actual seed positions were 0.98±1.05mm, 1.14±0.62mm, and 0.90±1.05mm in the x, y, and z directions, respectively. The x, y, and z directions correspond to the left-right, anterior-posterior, and superior-inferior anatomical planes. Silicone phantoms exhibiting significantly smaller x-axis errors compared to liver and lung phantoms (p<0.05). Template assistance significantly reduced errors in all axes (p<0.05). No significant dosimetric deviations were observed in parameters such as D90, V100, and V150 between plans and post-implant doses (p>0.05). In animal experiments across 23 liver and lung cases, the mean implantation errors were 1.28±0.77mm, 1.66±0.69mm, and 1.86±0.93mm in the x, y, and z directions, slightly higher than in phantoms (p<0.05), with no significant differences between liver and lung models. The dosimetric results closely matched planned values, confirming the accuracy of the robotic system for RISI, offering new possibilities in clinical tumor treatment.

Path planning of micromanipulators inside an SEM and 3D nanomanipulation of CNTs for nanodevice construction

The concept of a nano-laboratory inside an SEM involves performing a sequence of tasks in a continuous pattern. Robotic systems with nanoscale motion resolution facilitate in-situ manipulation and characterization of nanomaterials to assemble nanodevices inside SEMs. Precise motion control of micromanipulators is required at both macro and micro-nano scales to effectively execute multiple sequential experimental tasks in nanofabrication. However, managing the entire nanomanipulation setup is challenging due to the constricted workspace inside an SEM and the lack of proper process feedback information at that scale. This study explores the application of path planning algorithms to generate a collision-free motion path for the micromanipulators operating within the confined space of an SEM. A MATLAB-based computational tool is first developed using PRM and Dijkstra's path planning algorithms. Considering environmental constraints, the program generates an optimal motion path for the micromanipulators, facilitating automatic configuration changes within the SEM chamber. It ensures a seamless workflow and facilitates the smooth integration of additional experimental tools within the existing setup. Manipulation strategies using the nanorobotic setup are established based on the application of the developed path planning module. A pick-and-place 3D nanomanipulation technique of CNTs using cooperative control of dual micromanipulators has been demonstrated for nanodevice construction. Additionally, the electrical response of individually manipulated CNTs is recorded using a two-probe measurement technique.

Optimal Parking Space Selection and Vehicle Driving Decision for Autonomous Parking System Based on Multi-Attribute Decision

Autonomous parking systems (APSs) can help drivers complete the task of finding a parking space and the parking operation, which improves driving comfort. Current research on APSs focus on the perception, localization, planning, and control modules, while few pay attention to the decision modules. This paper proposes a method for optimal parking space selection and vehicle driving decisions. In terms of selecting the optimal parking space, a multi-attribute decision method is designed considering the type of parking space, walking distance, and other factors. In terms of vehicle driving decisions, we first predict the behavior and trajectory of the target vehicle in a specific scenario, and then use a combination of rule-based and learning-based decision methods for safe and comfortable vehicle driving behavior decisions. Simulation results show that the proposed methods can find the optimal parking space according to the parking lot map and improve the efficiency and smoothness of vehicle driving while ensuring driving safety.

Rapid Plan Module Applying to Optimize the Planning Process for Treatment of Head and Neck and Rectal Cancer

In situations where the number of patients is large, it may be necessary to quickly create dosimetry plan without compromising the quality of the final plan. With the help of the modern technologies, it is possible to optimize and standardize the dosimetry planning process. The Varian Eclipse planning system has a Rapid Plan module, which is an automated system for creating plans based on the database of clinical plans (1-4). Knowledge-based planning is a promising method that can improve plan quality and speed up treatment planning. In this study the performance of volume modulated radiotherapy planning optimization (VMAT) for head and neck and rectal cancer was examined. Plans were compared based on dose statistics for critical organs and planning target volume using dose-volume histograms. Each model is configured on more than 50 real plans. The plans made using the RapidPlan had dose distributions no worse than the dose distributions of clinical plans. No statistically significant differences were found regarding planning target volume (PTV) coverage. The model was used for already treated patients with different types of localizations. The results indicate that automation of dosimetry planning is possible using the Rapid Plan module, and this may facilitate its use in clinical practice.

Determining the library size for the optimal output plan in the RapidPlan knowledge-based planning system using multicriteria optimization.

The aim of this study was to determine the number of trade-off explored (TO) library plans required for building a RapidPlan (RP) library that would generate the optimal clinical treatment plan. We developed 2 RP models, 1 each for the 2 clinical sites, head and neck (HN) and cervix. The models were created using 100 plans and were validated using 70 plans (VP) for each site respectively. Each of the 2 libraries comprising 100 TO plans was divided into 5 different subsets of library plans comprising 20, 40, 60, 80, and 100 plans, leading to 5 different RP models for each site. For every validation patient, a TO plan (TO_VP) was created. For every patient, 5 RP plans were automatically generated using RP models. The dosimetric parameters of the 6 plans (TO_VP + 5 RP plans) were compared using Pearson correlation and Greenhouse-Geisser analysis. Planning target volume (PTV) dose volume parameters PTVD95% in 6 competing plans varied between 97.6 ± 0.7% and 98.1 ± 0.6% in HN cases and 98.8 ± 0.3% and 99.0 ± 0.4% in cervix cases. Overall, for both sites, the mean variations in organ at risk (OAR) doses or volumes were within 50 cGy, 0.5%, and 0.2 cc between library plans, and if TO_VP was included the variations deteriorated to 180 cGy, 0.4%, and 15 cc. All OARs in both sites, except D0.1 ccspine, showed a statistically insignificant variation between all plans. Dosimetric variation among various output plans generated from 5 RP libraries is minimal and clinically insignificant. The optimal output plan can be derived from the least-weighted library consisting of 20 plans. This article shows that, when the constituent plans are subjected to trade-off exploration, the number of constituent plans for a knowledge-based planning module is not relevant in terms of its dosimetric output.

Research on Obstacle Avoidance Replanning and Trajectory Tracking Control Driverless Ferry Vehicles

This study aimed to solve the problem that is the frequent switching between the acceleration and braking modes of the driverless ferry vehicle, affecting the comfort and stability of speed control. The driverless ferry vehicle encounters unknown obstacles on the road that affect the normal planning and tracking control of the ferry vehicle and finally lead to the problem that the driverless ferry vehicle cannot drive normally. First of all, in the longitudinal control, the fuzzy PID control algorithm was utilized to produce the fuzzy PID acceleration controller by taking into account the difference between the actual and expected speeds and choosing the triangular membership function. According to the relationship between the brake oil pressure and brake torque, the brake controller was designed. The acceleration/braking switching module with acceleration tolerance zone was added to the longitudinal controller, and the acceleration/braking mode-switching controller was designed. Secondly, in the lateral control, the tire cornering stiffness was analyzed, an MPC controller with a planning module was designed, and a lateral motion controller with an obstacle avoidance replanning function was proposed. Finally, according to the prediction time domain of different planning modules corresponding to different speeds, a coordinated control strategy of horizontal and longitudinal motion was proposed by using a real-time speed adjustment planning module to predict the time domain. Through the joint simulation analysis of MATLAB and CarSim, the results show that the driving stability of the ferry vehicle was significantly improved, and the longitudinal speed error of the ferry vehicle was reduced by 43.59%. The ferry’s avoidance of obstacles and tracking of reference trajectories were significantly improved, so that the tracking error can be reduced by 61.11%.