Dynamic Planning Research Articles

Reinforcement learning-based dynamic planning of cut and fill operations for earthwork optimization

Earthwork allocation planning aims to minimize earthwork costs by optimizing cut–fill pairs and their sequences. However, previous optimization approaches are limited in their ability to respond to dynamic changes in earthworks in computational processes. This paper proposes a reinforcement learning model with an attention mechanism that can address such dynamics by learning a strategy of selecting the cut–fill pairs with the shortest travel time in a given environment state through trial-and-error processes. For validation, the proposed model was compared with benchmarking models through four experiments: one-dimensional problems, two-dimensional problems, a constraint-change scenario, and a case study. The benchmarking results showed that the differences in total travel times were 4.845%, 5.183%, −0.068%, and 18.577%, respectively, implying that the travel time can be better optimized by incorporating the changing environments into the learning process. Hence, the proposed model can contribute to reducing earthwork costs by enhancing earthwork planning in practice.

Energy Consumption Analysis and Efficiency Enhancement in Manufacturing Companies Using Decision Support Method for Dynamic Production Planning (DSM DPP) for Solar PV Integration

Energy Consumption Analysis and Efficiency Enhancement in Manufacturing Companies Using Decision Support Method for Dynamic Production Planning (DSM DPP) for Solar PV Integration

Dynamic Path Planning and Motion Control of Microrobotic Swarms for Mobile Target Tracking

Magnetic field-driven microrobotic swarms have drawn extensive attention, especially in the field of automatic control. Realizing dynamic path planning and motion control of microrobotic swarms for mobile target tracking is one of the important tasks that still remains unsolved. In this paper, we firstly present an enhanced bidirectional rapidly-exploring random tree star (EB-RRT*) algorithm considering the physical size of the swarm to dynamically plan the optimal path for obstacle avoidance. An image-guided motion controller, which consists of a direction controller and a Genetic Algorithm based Linear Quadratic Regulator (GA-LQR) velocity controller, is then proposed to realize mobile target tracking using microrobotic swarms. Targeted bursting algorithm is subsequently developed to meet the requirement of tracking high-speed ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , 20 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mu m/s$</tex-math> </inline-formula> ) mobile targets. Simulations are performed to validate the proposed methods and obtain the proper ranges of the input parameters for the controllers. Finally, the control effectiveness of mobile target tracking in different conditions and environments is validated by experimental results. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The motivation of this work is to develop an effective control scheme for mobile target tracking using microrobotic swarms. Conventional control schemes mainly focus on the control of single microrobots to reach static targets, and thus the desired path is fixed once planned. In addition, the motion of single monolithic microrobots can be modelled precisely. However, in mobile target tracking using microrobotic swarms, dynamic planning algorithms are demanded to frequently update the desired path. Swarms consisting of millions of micro-agents are also difficult to be modelled due to the complex agent-agent interactions. In this work, an effective control scheme consisting of a dynamic path planner, a motion controller and a targeted bursting unit is developed. Real-time dynamic paths will be planned even though the positions of the swarm and the target change rapidly. The precise control of the swarm direction and velocity are achieved, and moreover, using the targeted bursting algorithm, the swarm can be accelerated to approach mobile targets accurately with higher efficiency. Experimental results validates the proposed tracking strategy in different environments with virtual obstacles. The proposed control scheme paves the way for a better understanding of advanced motion control methods for microrobotic swarms.

Research on Dynamic Path Planning and Tracking Control for Ship Collision Avoidance

Ship collisions are prevalent every year, leading to significant maritime traffic accidents. This paper presents research on dynamic path planning and tracking control for ship collision avoidance by integrating ship automatic avoidance technology to address this issue. We conducted a comprehensive study on artificial potential fields, trajectory tracking, and route trajectory tracking in response to the current state of ship collision avoidance and trajectory tracking. The study employed vector decomposition and slider control as research methods to analyze, optimize, and modify ship collision avoidance methods. Additionally, we carried out collision avoidance simulations using MATLAB to verify the stability and safety of ship trajectory tracking under various methods to advance the research on ship collision avoidance and trajectory. The proposed approach has the potential to significantly reduce ship collisions and enhance ship trajectory safety.

Perceptive Locomotion Through Nonlinear Model-Predictive Control

Dynamic locomotion in rough terrain requires accurate foot placement, collision avoidance, and planning of the underactuated dynamics of the system. Reliably optimizing for such motions and interactions in the presence of imperfect and often incomplete perceptive information is challenging. We present a complete perception, planning, and control pipeline, which can optimize motions for all degrees of freedom of the robot in real time. To mitigate the numerical challenges posed by the terrain, a sequence of convex inequality constraints is extracted as local approximations of foothold feasibility and embedded into an online model-predictive controller. Steppability classification, plane segmentation, and a signed distance field are precomputed per elevation map to minimize the computational effort during the optimization. A combination of multiple-shooting, real-time iteration, and a filter-based line search is used to solve the formulated problem reliably and at high rate. We validate the proposed method in scenarios with gaps, slopes, and stepping stones in simulation and experimentally on the ANYmal quadruped platform, resulting in state-of-the-art dynamic climbing.

Dynamic modeling, trajectory planning and prototyping of an ice-skating robot

Dynamic modeling, trajectory planning and prototyping of an ice-skating robot

The Potential Ability of Plan Complexity Metrics on the Dose Calculation and Plans Delivery in Intensity Modulated Radiotherapy.

The excessive modulation of treatment plan during radiotherapy (RT) increases the complexity. Evaluation of the multidimensional relationship between program complexity metrics, computation-based patient-specific quality assurance (PSQA), and conventional measurement-based PSQA could assist in enhancing the robustness of treatment planning, guide the allocation of clinical QA resources, and ultimately lessen QA workload. The fifty-five metrics affecting RT planning and delivery accuracy were calculated by a house-built program to describe the complexity of 404 dynamic IMRT plans, with sensitivity to the small field, aperture position, MLC edge, low MUs, MLC leaf motion, leaf speed/acceleration, etc. The calculation-based PSQA was performed using Monte Carlo (MC) method and Collapsed Cone Convolution (CCC) algorithm, implemented in SciMoCa and Mobius 3D, respectively. The measurement-based PSQA was performed using 3D diode arrays with different geometries covering "O", "+" and " × " shapes which exist in ArcCheck, Delta4 phantom+ (Delta4) and Delta4PT phantom (Delta4PT), respectively. Gamma passing rates (GPRs) were recorded to measure the results of each QA system. This multidimensional relationship was evaluated using correlation analysis and principal component linear regression (PCR) analysis. A total of 4448 GPRs for various QA systems corresponding to two Linacs were counted. The modulation index for speed (MIs) and modulation index for acceleration (MIa) were consistently located at the high points of the radarplots of the Spearman correlation coefficient |rs| between metrics and GPRs of the four QA systems, just except Delta4. Besides, the rs between SciMoCa and ArcCheck were 0.275-0.531 (P ≤ 0.001), SciMoCa and Delta4 were 0.32-0.418 (P ≤ 0.001), and Mobius 3Dand Delta4PT were 0.124-0.226 (P ≤ 0.05). The PCR model's coefficients determination (R2) for SciMoCa were 0.461-0.756 (P ≤ 0.001), ArcCheck were 0.243-0.440 (P ≤ 0.001), Delta4 were 0.268-0.402 (P ≤ 0.001), Mobius 3D were 0.299-0.407 (P ≤ 0.001), and Delta4PT were 0.087-0.141 (P ≤ 0.05). This study is the first overall assessment of the impact of various complexity metrics on the accuracy of TPS calculation and Linac delivery. Of the metrics studied, MIs and MIa metrics have a standout impact on the ability of the TPS calculation and delivery system, extra attention should be paid during the planning process. It is inappropriate to utilize calculation-based QA to predict the results of measurement-based QA since there is a poor correlation between the two. Furthermore, calculation-based QA outperforms measurement-based QA in identifying highly complex plans, which can further guide clinical QA process optimization and save limited clinical resources.

Dynamic Three-Dimensional Lift Planning for Intelligent Boom Cranes

Manually planning a crane's lifting path is complicated and laborious since it typically depends on the planner's experience. We examined dynamic three-dimensional lift planning, including problem formulation for multiobjective planning and problem-solving with an improved A* algorithm. First, we quantified various feasible movements by introducing energy and time consumption models to determine the most efficient and quickest path. Second, we examined a new method for determining the visible lifting path in Configuration space (C-space) and derived an obstacle enveloping method for collision detection in C-space. Our method is both safe and feasible. Finally, we proposed an improved A* algorithm for lift planning considering multiple objectives and featuring better computational efficiency. The experimental and simulation results demonstrate that the proposed lift planning method can comprehensively consider multiple objectives, thus providing a high-quality path for actual lifting. Furthermore, compared with the ordinary A* algorithm, the improved A* algorithm had better computational efficiency and consumed less energy and time. To our best knowledge, this is the first novel algorithm for planning crane lifts considering energy consumption and visibility in C-space.

Control of Fuel Lithium Battery Hybrid Vehicle Power Supply System and Vehicle Energy Management Strategy

&lt;p&gt;The main research object of this article is the increasing number of new energy vehicles, focusing on the energy management issues of new energy vehicles. Firstly, a real car model was established: an engine mathematical model, an electric motor mathematical model, and a power battery mathematical model. Then, in order to achieve optimal management of vehicle energy management, an algorithm model for vehicle energy dynamic planning was established with the goal of minimizing energy consumption. Finally, simulation experiments were conducted to verify the performance improvement of the proposed algorithm in vehicle energy management.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt;

An Efficient Maritime Route Planning Method Based on an Improved A* with an Adaptive Heuristic Function and Parallel Computing Structure

Maritime route planning under minimal-risk conditions plays an important part in the development and utilization of marine resources. High-resolution weather forecasting data places higher demands on the algorithms’ ability to optimize and compute, and existing algorithms are significantly deficient in these aspects. Therefore, we propose a parallel computing-based planning method, segment parallel A* (SPA*), which splits the path into small segments and runs A* separately on CPU cores through a control algorithm. In segment planning, we propose an adaptive heuristic function on A*. It automatically balances the order of magnitude difference between the risk assessment value and the estimated distance, thus significantly reducing the A* expansion useless grid to improve the performance and running speed of the algorithm. Finally, the complete route is obtained by splicing the above segments. In the static planning experiments, the time of SPA* is reduced by about 5~12,425 times compared with 6 traditional and swarm intelligence-based algorithms, i.e., Dijkstra, A*, bidirectional A* (BA*), ant colony optimization (ACO), Harris hawks optimization (HHO), and sparrow search algorithm (SSA). And the abilities to control the risk caused by wind and waves and the comprehensive risk are improved by 7.68%~25.14% and 8.44%~14.38%, respectively; in the dynamic planning experiments, the above results are 4.8~1262.9 times, 3.87%~9.47% and 7.21%~10.36%, respectively. By setting the recommended range of the number of segments for each case, SPA* shows stable performance in terms of the calculation and risk control. SPA* demonstrates a unique structure for using parallel computing in route planning, which is representative and general in both reducing time and improving efficiency.

Uncertainties in data processing, forecasting and decision making

Forecasting, dynamic planning, and current statistical data processing are defined as the process of estimating an enterprise’s current state on the market compared to other competing enterprises and determining further goals as well as sequences of actions and resources necessary for reaching the goals stated. In order to perform high-quality forecasting, it is proposed to identify and consider possible uncertainties associated with data and expert estimates. This is one of the system analysis principles to be hired for achieving high-quality final results. A review of some uncertainties is given, and an illustrative example showing improvement of the final result after considering possible stochastic uncertainty is provided.

Integrating existing data to assess the risk of an expanding land use change on mammals

ContextLand-use change, including agricultural expansion, is one of the major drivers of biodiversity loss globally. Given the rapid pace of land-use change, data-driven, strategic, and dynamic conservation planning is imperative.ObjectivesWe present an exemplar application of using existing data to inform conservation planning. Specifically, we developed a systematic approach for identifying areas of conservation concern due to cannabis cultivation in California, USA.MethodsWe used three existing datasets: (1) camera trap data from ten projects (n = 1186); (2) the locations of cannabis cultivation sites eradicated by law enforcement (n = 834); and (3) the locations of cultivation licenses (n = 4366). We analyzed this data using multi-species occupancy models to estimate the occupancy and richness of 30 species, and maximum entropy models to estimate the risk of unlicensed and trespass cultivation. We then identified areas of overlap and determined the percent of suitable habitat potentially impacted by cannabis cultivation.ResultsCannabis cultivation was estimated to overlap 39–74% of suitable habitat for special status species. Private land cultivation tended to have a larger influence on generalist species whereas trespass cultivation had the largest potential influence on fisher (Pekania pennanti), a special status species.ConclusionsOur results can be used to prioritize eradication, restoration, and remediation activities; to target mitigation efforts; and to guide the placement of new, licensed cultivation. Our approach demonstrates the utility of aggregating existing biological and socioeconomic data to inform conservation planning and is broadly applicable to other data sources and ecological stressors.

Deep reinforcement learning approach for dynamic capacity planning in decentralised regenerative medicine supply chains

Decentralized manufacturing has the benefits of fast fulfillment, reducing risks of distant delivery, and improving patient access to personalised regenerative medicine (PRM). Implementing the decentralised PRM manufacturing system successfully needs a capacity planning strategy involving inventory replenishment, capacity allocation, and demand sharing to mitigate the impacts of supplier disruption and satisfy demand with a high service level. However, existing methods for generating optimal capacity planning policies for such PRM systems require knowing the distributions of the supplier disruption and demand uncertainty, which is usually unknown for PRM supply chains. This study proposes a data-driven approach that can learn effective capacity planning policy under various manufacturing circumstances without knowing the exact distributions. The proposed approach utilises a production simulation model and a deep reinforcement learning method. Case study results demonstrate that the proposed method can outperform existing methods when ground-truth demand forecasts differ from priori estimations. The results also support that the proposed method not only can be applied in regenerative medicine but also in many other sectors.

Impact of the gradient in gantry-table rotation on dynamic trajectory radiotherapy plan quality.

To improve organ at risk (OAR) sparing, dynamic trajectory radiotherapy (DTRT) extends VMAT by dynamic table and collimator rotation during beam-on. However, comprehensive investigations regarding the impact of the gantry-table (GT) rotation gradient on the DTRT plan quality have not been conducted. To investigate the impact of a user-defined GT rotation gradient on plan quality of DTRT plans in terms of dosimetric plan quality, dosimetric robustness, deliverability, and delivery time. The dynamic trajectories of DTRT are described by GT and gantry-collimator paths. The GT path is determined by minimizing the overlap of OARs with planning target volume (PTV). This approach is extended to consider a GT rotation gradient by means of a maximum gradient of the path ( ) between two adjacent control points ( ) and maximum absolute change of G ( ). Four DTRT plans are created with different maximum G&∆G: & =0.5&0.125 (DTRT-1), 1&0.125 (DTRT-2), 3&0.125 (DTRT-3) and 3&1‍(DTRT-4), including 3-4 dynamic trajectories, for three clinically motivated cases in the head and neck and brain region (A, B, and C). A reference VMAT plan for each case is created. For all plans, plan quality is assessed and compared. Dosimetric plan quality is evaluated by target coverage, conformity, and OAR sparing. Dosimetric robustness is evaluated against systematic and random patient-setup uncertainties between in the lateral, longitudinal, and vertical directions, and machine uncertainties between in the dynamically rotating machine components (gantry, table, collimator rotation). Delivery time is recorded. Deliverability and delivery accuracy on a TrueBeam are assessed by logfile analysis for all plans and additionally verified by film measurements for one case. All dose calculations are Monte Carlo based. The extension of the DTRT planning process with user-defined to investigate the impact of the GT rotation gradient on plan quality is successfully demonstrated. With increasing , slight (case C, : up to‍-1‍Gy) and substantial (case A, : up to -9.3Gy, case‍B, : up to -4.7‍Gy) improvements in OAR sparing are observed compared to VMAT, while maintaining similar target coverage. All plans are delivered on the TrueBeam. Expected and actual machine position values recorded in the logfiles deviated by <0.2° for gantry, table and collimator rotation. The film measurements agreed by >96% (2%‍global/2mm Gamma passing rate) with the dose calculation. With increasing , delivery time is prolonged by <2min/trajectory (DTRT-4) compared to VMAT and DTRT-1. The DTRT plans for case A and B and the VMAT plan for case C plan reveal the best dosimetric robustness for the considered uncertainties. The impact of the GT rotation gradient on DTRT plan quality is comprehensively investigated for three cases in the head and neck and brain region. Increasing freedom in this gradient improves dosimetric plan quality at the cost of increased delivery time for the investigated cases. No clear dependency of GT rotation gradient on dosimetric robustness is observed.

Controlling of Unmanned Underwater Vehicles Using the Dynamic Planning of Symmetric Trajectory Based on Machine Learning for Marine Resources Exploration

Unmanned underwater vehicles (UUV) are widely used tools in ocean development, which can be applied in areas such as marine scientific research, ocean resources exploration, and ocean security. However, as ocean exploration advances, UUVs face increasingly challenging operational environments with weaker communication signals. Consequently, autonomous obstacle avoidance planning for UUVs becomes increasingly important. With the deepening of ocean exploration, the operational environment of UUVs has become increasingly difficult to access, and the communication signals in the environment have become weaker. Therefore, autonomous obstacle avoidance planning of UUVs has become increasingly important. Traditional dynamic programming methods face challenges in terms of accuracy and real-time performance, requiring the design of auxiliary strategies to achieve ideal avoidance and requiring cumbersome perception equipment to support them. Therefore, exploring an efficient and easy-to-implement dynamic programming method has significant theoretical and practical value. In this study, an LSTM-RNN network structure suitable for UUVs was designed to learn the dynamic programming mode of UUVs in an unknown environment. The research was divided into three main aspects: collecting the required sample dataset for training deep networks, designing the LSTM-RNN network structure, and utilizing LSTM-RNN to achieve dynamic programming. Experimental results demonstrated that LSTM-RNN can learn planning patterns in unknown environments without the need for constructing an environment model or complex perception devices, thus providing significant theoretical and practical value. Consequently, this approach offers an effective solution for autonomous obstacle avoidance planning for UUVs.

An integrated optimization model for planning supply chains' resilience and business continuity under interrelated disruptions: a case study

PurposeThe adverse interactions between disruptions can increase the supply chain's vulnerability. Accordingly, establishing supply chain resilience to deal with disruptions and employing business continuity planning to preserve risk management achievements is of considerable importance. The aforementioned idea is discussed in this study.Design/methodology/approachThis study proposes a multi-objective optimization model for employing business continuity management and organizational resilience in a supply chain for responding to multiple interrelated disruptions. The improved augmented e-constraint and the scenario-based robust optimization methods are adopted for multi-objective programming and dealing with uncertainty, respectively. A case study of the automotive battery manufacturing industry is also considered to ensure real-world conformity of the model.FindingsThe results indicate that interactions between disruptions remarkably increase the supply chain's vulnerability. Choosing a higher fortification level for the supply chain and foreign suppliers reduces disruption impacts on resources and improves the supply chain's resilience and business continuity. Facilities dispersion, fortification of facilities, lateral transshipment, order deferral policy, dynamic capacity planning and direct transportation of products to markets are the most efficient resilience strategies in the under-study industry.Originality/valueApplying resource allocation planning and portfolio selection to adopt preventive and reactive resilience strategies simultaneously to manage multiple interrelated disruptions in a real-world automotive battery manufacturing industry, maintaining the long-term achievements of supply chain resilience using business continuity management and dynamic capacity planning are the main contributions of the presented paper.

Cooperative Dynamic Motion Planning for Dual Manipulator Arms Based on RRT*Smart-AD Algorithm.

Intelligent manufacturing requires robots to adapt to increasingly complex tasks, and dual-arm cooperative operation can provide a more flexible and effective solution. Motion planning serves as a crucial foundation for dual-arm cooperative operation. The rapidly exploring random tree (RRT) algorithm based on random sampling has been widely used in high-dimensional manipulator path planning due to its probability completeness, handling of high-dimensional problems, scalability, and faster exploration speed compared with other planning methods. As a variant of RRT, the RRT*Smart algorithm introduces asymptotic optimality, improved sampling techniques, and better path optimization. However, existing research does not adequately address the cooperative motion planning requirements for dual manipulator arms in terms of sampling methods, path optimization, and dynamic adaptability. It also cannot handle dual-manipulator collaborative motion planning in dynamic scenarios. Therefore, in this paper, a novel motion planner named RRT*Smart-AD is proposed to ensure that the dual-arm robot satisfies obstacle avoidance constraints and dynamic characteristics in dynamic environments. This planner is capable of generating smooth motion trajectories that comply with differential constraints and physical collision constraints for a dual-arm robot. The proposed method includes several key components. First, a dynamic A* cost function sampling method, combined with an intelligent beacon sampling method, is introduced for sampling. A path-pruning strategy is employed to improve the computational efficiency. Strategies for dynamic region path repair and regrowth are also proposed to enhance adaptability in dynamic scenarios. Additionally, practical constraints such as maximum velocity, maximum acceleration, and collision constraints in robotic arm applications are analyzed. Particle swarm optimization (PSO) is utilized to optimize the motion trajectories by optimizing the parameters of quintic non-uniform rational B-splines (NURBSs). Static and dynamic simulation experiments verified that the RRT*Smart-AD algorithm for cooperative dynamic path planning of dual robotic arms outperformed biased RRT* and RRT*Smart. This method not only holds significant practical engineering significance for obstacle avoidance in dual-arm manipulators in intelligent factories but also provides a theoretical reference value for the path planning of other types of robots.

Hierarchical Optimization Based on Deep Reinforcement Learning for Connected Fuel Cell Hybrid Vehicles through Signalized Intersections

With the advantages of non-pollution and energy-saving, hydrogen fuel cell hybrid vehicles (HFCHVs) are regarded as one of the potential traveling ways in the future. The energy management of FCHVs has a huge energy-efficient potential which is combined with the Internet of Things (IOT) and auto-driving technologies. In this paper, a hierarchical joint optimization method that combines deep deterministic policy gradient and dynamic planning (DDPG-DP) for speed planning and energy management of the HFCHV is proposed for urban road driving scenarios. The results demonstrate that when the HFCHV is operating in driving scenario 1, the traveling efficiency of the DDPG-DP algorithm is 17.8% higher than that of the IDM-DP algorithm, and the hydrogen fuel consumption is reduced by 2.7%. In contrast, the difference in the traveling efficiency and fuel economy is small among the three algorithms in driving scenario 2, the number of idling/stop situations of the DDPG-DP algorithm is reduced compared with that of the IDM-DP algorithm. This will support further research for multi-objective eco-driving optimization of fuel cell hybrid vehicles.

MANAGING UNCERTAINTIES IN URBAN DEVELOPMENT AND CLIMATE CHANGE ADAPTATION: A CASE STUDY IN ADAPTATION IN A COMPLEX COASTAL ENVIRONMENT USING DYNAMIC ADAPTIVE PATHWAYS IN SKIVE, DENMARK

The city of Skive, located in West Jutland Denmark, is looking to develop a long term strategic urban development plan integrated with supporting climate adaptation pathways keeping Skive climate-proof for future conditions. In this study a Dynamic Adaptive Pathway Plan (DAPP) was used to investigate uncertainties with regards to future climate change and urban development. Similarly to uncertainties regarding climate change (e.g. Sea-level rise) and the associated change in risk, there is great uncertainty in the future development of the system (Skive) through a range of socio-economic variables. This will directly affect the solution space for climate adaptation. NIRAS, LYTT Architecture and Skive Municipality have developed a strategic urban development plan and investigated the implications and possibilities for climate change adaptation in Skive. It is one of the first fully developed DAPP processes in Denmark. The project illustrated the need for supporting uptake of dynamic decision making, the necessity of multi-disciplinary collaboration within the municipality, and the integration of land use considerations within the adaptation pathway development.

Online Indoor Fire Evacuation System

Many methods for indoor fire escape evacuation have been proposed to assist victims in escaping. Greedy approaches focus on finding the closest exit and providing victims with the shortest evacuation path. However, they are time consuming to respond to a dynamic fire spread. Optimal approaches determine evacuation exits and routes based on the characteristics of indoor fires using probabilistic or gravitational algorithms. However, their disadvantage is the excessive amount of computation required. Compared with previous methods, this article provides a lightweight exit decision formulation paired with dynamic path planning. The experimental results indicate that our approach accelerates the computation time by approximately 1.5 times and achieves a victim survival rate higher than 90%.