Rescue path planning for urban flood: A deep reinforcement learning-based approach.

Urban flooding is among the costliest natural disasters worldwide. Timely and effective rescue path planning is crucial for minimizing loss of life and property. However, current research on path planning often fails to adequately consider the need to assess area risk uncertainties and bypass complex obstacles in flood rescue scenarios, presenting significant challenges for developing optimal rescue paths. This study proposes a deep reinforcement learning (RL) algorithm incorporating four main mechanisms to address these issues. Dual-priority experience replays and backtrack punishment mechanisms enhance the precise estimation of area risks. Concurrently, random noisy networks and dynamic exploration techniques encourage the agent to explore unknown areas in the environment, thereby improving sampling and optimizing strategies for bypassing complex obstacles. The study constructed multiple grid simulation scenarios based on real-world rescue operations in major urban flood disasters. These scenarios included uncertain risk values for all passable areas and an increased presence of complex elements, such as narrow passages, C-shaped barriers, and jagged paths, significantly raising the challenge of path planning. The comparative analysis demonstrated that only the proposed algorithm could bypass all obstacles and plan the optimal rescue path across nine scenarios. This research advances the theoretical progress for urban flood rescue path planning by extending the scale of scenarios to unprecedented levels. It also develops RL mechanisms adaptable to various extremely complex obstacles in path planning. Additionally, it provides methodological insights into artificial intelligence to enhance real-world risk management.

Obstacle Avoidance and Path Planning Methods for Autonomous Navigation of Mobile Robot.

Path planning creates the shortest path from the source to the destination based on sensory information obtained from the environment. Within path planning, obstacle avoidance is a crucial task in robotics, as the autonomous operation of robots needs to reach their destination without collisions. Obstacle avoidance algorithms play a key role in robotics and autonomous vehicles. These algorithms enable robots to navigate their environment efficiently, minimizing the risk of collisions and safely avoiding obstacles. This article provides an overview of key obstacle avoidance algorithms, including classic techniques such as the Bug algorithm and Dijkstra's algorithm, and newer developments like genetic algorithms and approaches based on neural networks. It analyzes in detail the advantages, limitations, and application areas of these algorithms and highlights current research directions in obstacle avoidance robotics. This article aims to provide comprehensive insight into the current state and prospects of obstacle avoidance algorithms in robotics applications. It also mentions the use of predictive methods and deep learning strategies.

Mobile Sensor Path Planning for Kalman Filter Spatiotemporal Estimation.

The estimation of spatiotemporal data from limited sensor measurements is a required task across many scientific disciplines. In this paper, we consider the use of mobile sensors for estimating spatiotemporal data via Kalman filtering. The sensor selection problem, which aims to optimize the placement of sensors, leverages innovations in greedy algorithms and low-rank subspace projection to provide model-free, data-driven estimates. Alternatively, Kalman filter estimation balances model-based information and sparsely observed measurements to collectively make better estimation with limited sensors. It is especially important with mobile sensors to utilize historical measurements. We show that mobile sensing along dynamic trajectories can achieve the equivalent performance of a larger number of stationary sensors, with performance gains related to three distinct timescales: (i) the timescale of the spatiotemporal dynamics, (ii) the velocity of the sensors, and (iii) the rate of sampling. Taken together, these timescales strongly influence how well-conditioned the estimation task is. We draw connections between the Kalman filter performance and the observability of the state space model and propose a greedy path planning algorithm based on minimizing the condition number of the observability matrix. This approach has better scalability and computational efficiency compared to previous works. Through a series of examples of increasing complexity, we show that mobile sensing along our paths improves Kalman filter performance in terms of better limiting estimation and faster convergence. Moreover, it is particularly effective for spatiotemporal data that contain spatially localized structures, whose features are captured along dynamic trajectories.

A Design of Three-Dimensional Spatial Path Planning Algorithm Based on Vector Field Histogram.

In this paper, we present a novel three-dimensional spatial path planning algorithm based on the Vector Field Histogram* (VFH*) approach, specifically tailored for underwater robotics applications. Our method leverages the strengths of VFH* in obstacle avoidance while enhancing its capability to handle complex three-dimensional environments. Through extensive simulations, we demonstrate the superior performance of our algorithm compared to traditional methods, such as RS-RRT algorithm. Our results show significant improvements in terms of computational efficiency and path optimality, making it a viable solution for real-time path planning in dynamic underwater environments.

Improved A* Algorithm for Mobile Robots under Rough Terrain Based on Ground Trafficability Model and Ground Ruggedness Model.

Considering that the existing path planning algorithms for mobile robots under rugged terrain do not consider the ground flatness and the lack of optimality, which leads to the instability of the center of mass of the mobile robot, this paper proposes an improved A* algorithm for mobile robots under rugged terrain based on the ground accessibility model and the ground ruggedness model. Firstly, the ground accessibility and ruggedness models are established based on the elevation map, expressing the ground flatness. Secondly, the elevation cost function that can obtain the optimal path is designed based on the two types of models combined with the characteristics of the A* algorithm, and the continuous cost function is established by connecting with the original distance cost function, which avoids the center-of-mass instability caused by the non-optimal path. Finally, the effectiveness of the improved algorithm is verified by simulation and experiment. The results show that compared with the existing commonly used path planning algorithms under rugged terrain, the enhanced algorithm improves the smoothness of paths and the optimization degree of paths in the path planning process under rough terrain.

A Context-Aware Navigation Framework for Ground Robots in Horticultural Environments.

Environmental mapping and robot navigation are the basis for realizing robot automation in modern agricultural production. This study proposes a new autonomous mapping and navigation method for gardening scene robots. First, a new LiDAR slam-based semantic mapping algorithm is proposed to enable the robots to analyze structural information from point cloud images and generate roadmaps from them. Secondly, a general robot navigation framework is proposed to enable the robot to generate the shortest global path according to the road map, and consider the local terrain information to find the optimal local path to achieve safe and efficient trajectory tracking; this method is equipped in apple orchards. The LiDAR was evaluated on a differential drive robotic platform. Experimental results show that this method can effectively process orchard environmental information. Compared with vnf and pointnet++, the semantic information extraction efficiency and time are greatly improved. The map feature extraction time can be reduced to 0.1681 s, and its MIoU is 0.812. The resulting global path planning achieved a 100% success rate, with an average run time of 4ms. At the same time, the local path planning algorithm can effectively generate safe and smooth trajectories to execute the global path, with an average running time of 36 ms.

A Deep Learning Approach to Lunar Rover Global Path Planning Using Environmental Constraints and the Rover Internal Resource Status.

This research proposes a novel approach to global path and resource planning for lunar rovers. The proposed method incorporates a range of constraints, including static, time-variant, and path-dependent factors related to environmental conditions and the rover's internal resource status. These constraints are integrated into a grid map as a penalty function, and a reinforcement learning-based framework is employed to address the resource constrained shortest path problem (RCSP). Compared to existing approaches referenced in the literature, our proposed method enables the simultaneous consideration of a broader spectrum of constraints. This enhanced flexibility leads to improved path search optimality. To evaluate the performance of our approach, this research applied the proposed learning architecture to lunar rover path search problems, generated based on real lunar digital elevation data. The simulation results demonstrate that our architecture successfully identifies a rover path while consistently adhering to user-defined environmental and rover resource safety criteria across all positions and time epochs. Furthermore, the simulation results indicate that our approach surpasses conventional methods that solely rely on environmental constraints.

Deep Learning-Enhanced Sampling-Based Path Planning for LTL Mission Specifications.

The presented paper introduces a novel path planning algorithm designed for generating low-cost trajectories that fulfill mission requirements expressed in Linear Temporal Logic (LTL). The proposed algorithm is particularly effective in environments where cost functions encompass the entire configuration space. A core contribution of this paper is the presentation of a refined approach to sampling-based path planning algorithms that aligns with the specified mission objectives. This enhancement is achieved through a multi-layered framework approach, enabling a simplified discrete abstraction without relying on mesh decomposition. This abstraction is especially beneficial in complex or high-dimensional environments where mesh decomposition is challenging. The discrete abstraction effectively guides the sampling process, influencing the selection of vertices for extension and target points for steering in each iteration. To further improve efficiency, the algorithm incorporates a deep learning-based extension, utilizing training data to accurately model the optimal trajectory distribution between two points. The effectiveness of the proposed method is demonstrated through simulated tests, which highlight its ability to identify low-cost trajectories that meet specific mission criteria. Comparative analyses also confirm the superiority of the proposed method compared to existing methods.

Localized Path Planning for Mobile Robots Based on a Subarea-Artificial Potential Field Model.

The artificial potential field method has efficient obstacle avoidance ability, but this traditional method suffers from local minima, unreasonable paths, and sudden changes in heading angles during obstacle avoidance, leading to rough paths and increased energy consumption. To enable autonomous mobile robots (AMR) to escape from local minimum traps and move along reasonable, smooth paths while reducing travel time and energy consumption, in this paper, an artificial potential field method based on subareas is proposed. First, the optimal virtual subgoal was obtained around the obstacles based on the relationship between the AMR, obstacles, and goal points in the local environment. This was done according to the virtual subgoal benefit function to solve the local minima problem and select a reasonable path. Secondly, when AMR encountered an obstacle, the subarea-potential field model was utilized to solve problems such as path zigzagging and increased energy consumption due to excessive changes in the turning angle; this helped to smooth its planning path. Through simulations and actual testing, the algorithm in this paper demonstrated smoother heading angle changes, reduced energy consumption, and a 10.95% average reduction in movement time when facing a complex environment. This proves the feasibility of the algorithm.

Research on Autonomous Vehicle Path Planning Algorithm Based on Improved RRT* Algorithm and Artificial Potential Field Method.

For the RRT* algorithm, there are problems such as greater randomness, longer time consumption, more redundant nodes, and inability to perform local obstacle avoidance when encountering unknown obstacles in the path planning process of autonomous vehicles. And the artificial potential field method (APF) applied to autonomous vehicles is prone to problems such as local optimality, unreachable targets, and inapplicability to global scenarios. A fusion algorithm combining the improved RRT* algorithm and the improved artificial potential field method is proposed. First of all, for the RRT* algorithm, the concept of the artificial potential field and probability sampling optimization strategy are introduced, and the adaptive step size is designed according to the road curvature. The path post-processing of the planned global path is carried out to reduce the redundant nodes of the generated path, enhance the purpose of sampling, solve the problem where oscillation may occur when expanding near the target point, reduce the randomness of RRT* node sampling, and improve the efficiency of path generation. Secondly, for the artificial potential field method, by designing obstacle avoidance constraints, adding a road boundary repulsion potential field, and optimizing the repulsion function and safety ellipse, the problem of unreachable targets can be solved, unnecessary steering in the path can be reduced, and the safety of the planned path can be improved. In the face of U-shaped obstacles, virtual gravity points are generated to solve the local minimum problem and improve the passing performance of the obstacles. Finally, the fusion algorithm, which combines the improved RRT* algorithm and the improved artificial potential field method, is designed. The former first plans the global path, extracts the path node as the temporary target point of the latter, guides the vehicle to drive, and avoids local obstacles through the improved artificial potential field method when encountered with unknown obstacles, and then smooths the path planned by the fusion algorithm, making the path satisfy the vehicle kinematic constraints. The simulation results in the different road scenes show that the method proposed in this paper can quickly plan a smooth path that is more stable, more accurate, and suitable for vehicle driving.

A Study of the Improved A* Algorithm Incorporating Road Factors for Path Planning in Off-Road Emergency Rescue Scenarios.

To address the problem of ignoring unpaved roads when planning off-road emergency rescue paths, an improved A* algorithm that incorporates road factors is developed to create an off-road emergency rescue path planning model in this study. To reduce the number of search nodes and improve the efficiency of path searches, the current node is classified according to the angle between the line connecting the node and the target point and the due east direction. Additionally, the search direction is determined in real time through an optimization method to improve the path search efficiency. To identify the path with the shortest travel time suitable for emergency rescue in wilderness scenarios, a heuristic function based on the fusion of road factors and a path planning model for off-road emergency rescue is developed, and the characteristics of existing roads are weighted in the process of path searching to bias the selection process toward unpaved roads with high accessibility. The experiments show that the improved A* algorithm significantly reduces the travel time of off-road vehicles and that path selection is enhanced compared to that with the traditional A* algorithm; moreover, the improved A* algorithm reduces the number of nodes by 16.784% and improves the search efficiency by 27.18% compared with the traditional 16-direction search method. The simulation results indicate that the improved algorithm reduces the travel time of off-road vehicles by 21.298% and improves the search efficiency by 93.901% compared to the traditional A* algorithm, thus greatly enhancing off-road path planning.

Research on Path Planning Algorithm of Driverless Ferry Vehicles Combining Improved A* and DWA.

In view of the fact that the global planning algorithm cannot avoid unknown dynamic and static obstacles and the local planning algorithm easily falls into local optimization in large-scale environments, an improved path planning algorithm based on the integration of A* and DWA is proposed and applied to driverless ferry vehicles. Aiming at the traditional A* algorithm, the vector angle cosine value is introduced to improve the heuristic function to enhance the search direction; the search neighborhood is expanded and optimized to improve the search efficiency; aiming at the problem that there are many turning points in the A* algorithm, a cubic quasi-uniform B-spline curve is used to smooth the path. At the same time, fuzzy control theory is introduced to improve the traditional DWA so that the weight coefficient of the evaluation function can be dynamically adjusted in different environments, effectively avoiding the problem of a local optimal solution. Through the fusion of the improved DWA and the improved A* algorithm, the key nodes in global planning are used as sub-target punctuation to guide the DWA for local planning, so as to ensure that the ferry vehicle avoids obstacles in real time. Simulation results show that the fusion algorithm can avoid unknown dynamic and static obstacles efficiently and in real time on the basis of obtaining the global optimal path. In different environment maps, the effectiveness and adaptability of the fusion algorithm are verified.

Model Predictive Control with Variational Autoencoders for Signal Temporal Logic Specifications.

This paper presents a control strategy synthesis method for dynamical systems with differential constraints, emphasizing the prioritization of specific rules. Special attention is given to scenarios where not all rules can be simultaneously satisfied to complete a given task, necessitating decisions on the extent to which each rule is satisfied, including which rules must be upheld or disregarded. We propose a learning-based Model Predictive Control (MPC) method designed to address these challenges. Our approach integrates a learning method with a traditional control scheme, enabling the controller to emulate human expert behavior. Rules are represented as Signal Temporal Logic (STL) formulas. A robustness margin, quantifying the degree of rule satisfaction, is learned from expert demonstrations using a Conditional Variational Autoencoder (CVAE). This learned margin is then applied in the MPC process to guide the prioritization or exclusion of rules. In a track driving simulation, our method demonstrates the ability to generate behavior resembling that of human experts and effectively manage rule-based dilemmas.

Global Path Planning for Articulated Steering Tractor Based on Multi-Objective Hybrid Algorithm.

With the development of smart agriculture, autopilot technology is being used more and more widely in agriculture. Because most of the current global path planning only considers the shortest path, it is difficult to meet the articulated steering tractor operation needs in the orchard environment and address other issues, so this paper proposes a hybrid algorithm of an improved bidirectional search A* algorithm and improved differential evolution genetic algorithm(AGADE). First, the integrated priority function and search method of the traditional A* algorithm are improved by adding weight influence to the integrated priority, and the search method is changed to a bidirectional search. Second, the genetic algorithm fitness function and search strategy are improved; the fitness function is set as the path tree row center offset factor; the smoothing factor and safety coefficient are set; and the search strategy adopts differential evolution for cross mutation. Finally, the shortest path obtained by the improved bidirectional search A* algorithm is used as the initial population of an improved differential evolution genetic algorithm, optimized iteratively, and the optimal path is obtained by adding kinematic constraints through a cubic B-spline curve smoothing path. The convergence of the AGADE hybrid algorithm and GA algorithm on four different maps, path length, and trajectory curve are compared and analyzed through simulation tests. The convergence speed of the AGADE hybrid algorithm on four different complexity maps is improved by 92.8%, 64.5%, 50.0%, and 71.2% respectively. The path length is slightly increased compared with the GA algorithm, but the path trajectory curve is located in the center of the tree row, with fewer turns, and it meets the articulated steering tractor operation needs in the orchard environment, proving that the improved hybrid algorithm is effective.

Enhancing Stability and Performance in Mobile Robot Path Planning with PMR-Dueling DQN Algorithm.

Path planning for mobile robots in complex circumstances is still a challenging issue. This work introduces an improved deep reinforcement learning strategy for robot navigation that combines dueling architecture, Prioritized Experience Replay, and shaped Rewards. In a grid world and two Gazebo simulation environments with static and dynamic obstacles, the Dueling Deep Q-Network with Modified Rewards and Prioritized Experience Replay (PMR-Dueling DQN) algorithm is compared against Q-learning, DQN, and DDQN in terms of path optimality, collision avoidance, and learning speed. To encourage the best routes, the shaped Reward function takes into account target direction, obstacle avoidance, and distance. Prioritized replay concentrates training on important events while a dueling architecture separates value and advantage learning. The results show that the PMR-Dueling DQN has greatly increased convergence speed, stability, and overall performance across conditions. In both grid world and Gazebo environments the PMR-Dueling DQN achieved higher cumulative rewards. The combination of deep reinforcement learning with reward design, network architecture, and experience replay enables the PMR-Dueling DQN to surpass traditional approaches for robot path planning in complex environments.

Path Planning for a Wheel-Foot Hybrid Parallel-Leg Walking Robot.

Mobile robots require the ability to plan collision-free paths. This paper introduces a wheel-foot hybrid parallel-leg walking robot based on the 6-Universal-Prismatic-Universal-Revolute and 3-Prismatic (6UPUR + 3P) parallel mechanism model. To enhance path planning efficiency and obstacle avoidance capabilities, an improved artificial potential field (IAPF) method is proposed. The IAPF functions are designed to address the collision problems and issues with goals being unreachable due to a nearby problem, local minima, and dynamic obstacle avoidance in path planning. Using this IAPF method, we conduct path planning and simulation analysis for the wheel-foot hybrid parallel-legged walking robot described in this paper, and compare it with the classic artificial potential field (APF) method. The results demonstrate that the IAPF method outperforms the classic APF method in handling obstacle-rich environments, effectively addresses collision problems, and the IAPF method helps to obtain goals previously unreachable due to nearby obstacles, local minima, and dynamic planning issues.

An Improved A-Star Path Planning Algorithm Based on Mobile Robots in Medical Testing Laboratories.

In the blood sample management pipeline environment, we have innovatively improved the traditional A-star algorithm to enhance the efficiency of mobile robots. This study employs a grid environmental modeling approach to accurately simulate medical testing laboratories. On the grid map, we utilize an 8-neighbor search method for path planning to accommodate the complex structure within the laboratory. By introducing an improved evaluation function and a bidirectional search strategy, we have successfully reduced the number of search nodes and significantly improved path search efficiency. Additionally, we eliminate redundant nodes in the path, smooth the path using cubic uniform B-spline curves, remove unnecessary inflection points, and further optimize the motion trajectory of the robot. The experimental results of the path planning simulation under different scenarios and specifications show that the improved A-star algorithm has higher search efficiency and traverses fewer nodes compared to the traditional A-star algorithm and the bidirectional A-star algorithm. Overall, the simulation experiments verify the feasibility of the improved A-star algorithm, which can better meet the needs of actual mobile robots in real medical testing laboratories.

Integrating Modular Pipelines with End-to-End Learning: A Hybrid Approach for Robust and Reliable Autonomous Driving Systems.

Autonomous driving navigation relies on diverse approaches, each with advantages and limitations depending on various factors. For HD maps, modular systems excel, while end-to-end methods dominate mapless scenarios. However, few leverage the strengths of both. This paper innovates by proposing a hybrid architecture that seamlessly integrates modular perception and control modules with data-driven path planning. This innovative design leverages the strengths of both approaches, enabling a clear understanding and debugging of individual components while simultaneously harnessing the learning power of end-to-end approaches. Our proposed architecture achieved first and second place in the 2023 CARLA Autonomous Driving Challenge's SENSORS and MAP tracks, respectively. These results demonstrate the architecture's effectiveness in both map-based and mapless navigation. We achieved a driving score of 41.56 and the highest route completion of 86.03 in the MAP track of the CARLA Challenge leaderboard 1, and driving scores of 35.36 and 1.23 in the CARLA Challenge SENSOR track with route completions of 85.01 and 9.55, for, respectively, leaderboard 1 and 2. The results of leaderboard 2 raised the hybrid architecture to the first position, winning the edition of the 2023 CARLA Autonomous Driving Competition.

Intelligent Vehicle Path Planning Based on Optimized A* Algorithm.

With the rapid development of the intelligent driving technology, achieving accurate path planning for unmanned vehicles has become increasingly crucial. However, path planning algorithms face challenges when dealing with complex and ever-changing road conditions. In this paper, aiming at improving the accuracy and robustness of the generated path, a global programming algorithm based on optimization is proposed, while maintaining the efficiency of the traditional A* algorithm. Firstly, turning penalty function and obstacle raster coefficient are integrated into the search cost function to increase the adaptability and directionality of the search path to the map. Secondly, an efficient search strategy is proposed to solve the problem that trajectories will pass through sparse obstacles while reducing spatial complexity. Thirdly, a redundant node elimination strategy based on discrete smoothing optimization effectively reduces the total length of control points and paths, and greatly reduces the difficulty of subsequent trajectory optimization. Finally, the simulation results, based on real map rasterization, highlight the advanced performance of the path planning and the comparison among the baselines and the proposed strategy showcases that the optimized A* algorithm significantly enhances the security and rationality of the planned path. Notably, it reduces the number of traversed nodes by 84%, the total turning angle by 39%, and shortens the overall path length to a certain extent.

Research on Multiple-AUVs Collaborative Detection and Surrounding Attack Simulation.

Due to limitations in operational scope and efficiency, a single Autonomous Underwater Vehicle (AUV) falls short of meeting the demands of the contemporary marine working environment. Consequently, there is a growing interest in the coordination of multiple AUVs. To address the requirements of coordinated missions, this paper proposes a comprehensive solution for the coordinated development of multi-AUV formations, encompassing long-range ferrying, coordinated detection, and surrounding attack. In the initial phase, detection devices are deactivated, employing a path planning method based on the Rapidly Exploring Random Tree (RRT) algorithm to ensure collision-free AUV movement. During the coordinated detection phase, an artificial potential field method is applied to maintain AUV formation integrity and avoid obstacles, dynamically updating environmental probability based on formation movement. In the coordinated surroundings attack stage, predictive capabilities are enhanced using Long Short-Term Memory (LSTM) networks and reinforcement learning. Specifically, LSTM forecasts the target's position, while the Deep Deterministic Policy Gradient (DDPG) method controls AUV formation. The effectiveness of this coordinated solution is validated through an integrated simulation trajectory.