AUV path planning in complex 3D underwater environments based on an improved TD3 algorithm

This review systematically examines major research advances in AUV path planning over recent years, covering several mainstream methodologies: sample-based path planning (e.g., PRM and RRT along with their asymptotically optimal variants, suitable for high-dimensional space exploration), graph-search-based path planning (e.g., A-series and D-series algorithms, achieving global optimization and dynamic replanning through environmental modeling), optimization-based approaches (including artificial potential field (APF), nonlinear programming (NLP), and model predictive control (MPC), designed to satisfy stringent dynamic constraints on AUV motion), swarm intelligence-based planning methods (such as genetic algorithms and ant colony optimization), and learning-based intelligent methods (such as deep reinforcement learning (DRL) for real-time decision-making in unknown and dynamic environments). Through in-depth analysis of these methods’ principles, improvement strategies, and AUV path planning contexts, this review highlights current research trends toward hybrid cooperative planning, dynamic environmental adaptability, and high-precision trajectory optimization. Finally, the paper outlines future directions for AUV path planning, emphasizing multi-AUV collaboration and higher-level intelligent decision-making as key research priorities.

In the face of a complex three-dimensional environment, the computational complexity of the traditional path planning algorithms is extremely increased. But the performance of path planning results is relatively poor. Deep reinforcement learning (DRL) algorithms don’t rely on accurate environmental models, and its overall efficiency is much higher than traditional algorithms. Aiming at the problem of AUV path planning in a three-dimensional environment, proximal policy optimization algorithm (PPO) is selected. The PPO algorithm with improved network structure is used to train the model based on the established AUV model and gym environment. Through simulation experiments, the accuracy and effectiveness of the algorithm is verified.

AUV path planning and obstacle avoidances in marine environment based on enhanced ECUO technique

For multi-Autonomous Underwater Vehicle (multi-AUV) system task assignment and path planning, a novel Glasius Bio-inspired Self-Organising Map (GBSOM) neural networks algorithm is proposed to solve relevant problems in a Three-Dimensional (3D) grid map. Firstly, a 3D Glasius Bio-inspired Neural Network (GBNN) model is established to represent the 3D underwater working environment. Using this model, the strength of neural activity is calculated at each node within the GBNN. Secondly, a Self-Organising Map (SOM) neural network is used to assign the targets to a set of AUVs and determine the order of the AUVs to access the target point. Finally, according to the magnitude of the neuron activity in the GBNN, the next AUV target point can be autonomously planned when the task assignment is completed. By repeating the above three steps, access to all target points is completed. Simulation and comparison studies are presented to demonstrate that the proposed algorithm can overcome the speed jump problem of SOM algorithms and path planning in the 3D underwater environments with static or dynamic obstacles.

A fusion framework with spatial perception and energy-aware strategies for AUV path planning in uncharted marine environments

Aiming at the problem of large amount of calculation and difficulty in convergence of robot path planning in complex underwater 3D environments, the paper proposes a 3D path planning algorithm based on the sparrow search algorithm with potential field heuristic. First, establish an underwater 3D grid model, and use artificial potential field forces to generate an initial feasible path. Secondly, use the infinite folding chaotic map to expand the sparrow population and increase the diversity of the population.Then use the dynamic adjustment strategy to improve the location update formula of the sparrow search algorithm to adjust the search area range. Finally, the improved algorithm proposed is applied to solve the 3D path planning problem of underwater robots. The simulation results show that the optimization performance of the potential field sparrow search algorithm (PFSSA) proposed in this paper is better than the particle swarm optimization algorithm (PSO) and the sparrow search algorithm (SSA), and it can quickly obtain an optimal and safe feasible path, which proves the effectiveness of the method, and it has application value in the field of path planning of underwater robot.

Path planning in unknown environments is one of the most challenging research areas in robotics. In this class of path planning, the robot acquires the information from its sensory system. Sampling-based path planning is one of the famous approaches with low memory and computational requirements that has been studied by many researchers during the past few decades. We propose a sampling-based algorithm for path planning in unknown environments using Tabu search. The Tabu search component of our method guides the sampling to find the samples in the most promising areas and makes the sampling procedure more intelligent. The simulation results show the efficient performance of the proposed approach in different types of environments. We also compare the performance of the algorithm with some of the well-known path planning approaches, including Bug1, Bug2, SRT, potential fields and the visibility graph. Furthermore, two different sampling strategies were used in the sampling procedure, including uniform and Gaussian distributions.

The rapidly-exploring random trees (RRT) algorithm and its variants have been extensively studied because of their high efficiency and asymptotic optimality in path planning. Yet, they still struggle in complex environments with a dense arrangement of short and closely spaced narrow passages. In terms of the issue, this paper proposes a dynamic RRT* with bridge guidance (DBRRT*) to accelerate feasible path searching by adding a dynamic sampling method and an improved bridge test. To validate the effectiveness of DBRRT*, a series of experiments on a 6-DOF manipulator are conducted in reference to some typical path planning algorithms. Experimental results demonstrate that DBRRT* generally enhances the resolution and optimisation speed, and reduces path planning time in 2D and 3D environments, indicating its capability to address the challenges of path planning in environments with numerous short, dense and narrow passages.

Robust and efficient AUV path planning is a key element for persistence AUV maneuvering in variable underwater environments. To develop such a path planning system, in this study, differential evolution (DE) algorithm is employed. The performance of the DE-based planner in generating time-efficient paths to direct the AUV from its initial conditions to the target of interest is investigated within a complexed 3D underwater environment incorporated with turbulent current vector fields, coastal area, islands, and static/dynamic obstacles. The results of simulations indicate the inherent efficiency of the DE-based path planner as it is capable of extracting feasible areas of a real map to determine the allowed spaces for the vehicle deployment while coping undesired current disturbances, exploiting desirable currents, and avoiding collision boundaries in directing the vehicle to its destination. The results are implementable for a realistic scenario and on-board real AUV as the DE planner satisfies all vehicular and environmental constraints while minimizing the travel time/distance, in a computationally efficient manner.

We present an efficient, anytime method for path planning in dynamic environments. Current approaches to planning in such domains either assume that the environment is static and replan when changes are observed, or assume that the dynamics of the environment are perfectly known a priori. Our approach takes into account all prior information about both the static and dynamic elements of the environment, and efficiently updates the solution when changes to either are observed. As a result, it is well suited to robotic path planning in known or unknown environments in which there are mobile objects, agents or adversaries

A new APF strategy for path planning in environments with obstacles

Ship berthing is a critical and high‐risk phase of navigation that requires highly precise path planning in environments with numerous obstacles. This paper presents a two‐stage hybrid path planning approach designed to improve both safety and manoeuvrability during berthing operations. The first stage involves constructing an accurate environmental model based on berth characteristics. In the second stage, an enhanced A* algorithm is introduced with a directional consistency penalty to generate globally feasible paths with improved continuity. To further enhance local obstacle avoidan ce and edge‐following capabilities, the artificial potential field method is applied. The resulting path is coupled with a ship dynamics model and a dynamic look‐ahead strategy combined with PID control is employed to enable closed‐loop heading and speed tracking. Simulation results show that the proposed method significantly enhances path smoothness and obstacle clearance. Specifically, the average heading change is reduced to 2.51° and the minimum obstacle distance increases from 15.12 to 39.04 m. This approach offers a practical and effective solution for autonomous berthing in constrained port environments.

The problem of three-dimensional path planning in obstacle-crowded environments is a challenge (an NP-hard problem), which becomes even more complex when considering environmental uncertainty and system control. Int this paper, we mainly focused on more challenging problem, that is, path planning in obstacle-crowded environments, and we try to find the relation between contact information and obstacle modeling. We proposed a newactive exploring sampling-based algorithm based on rapidly exploring random tree (RRT), namely, guiding attraction–based random tree (GART). GART introduces bidirectional potential field to redistribute each newly sampled state, such that the in-collision samples can be redistributed for extension. Furthermore, dynamic constraints are deployed to establish forward extending region by GART. Thus, GART can ensure kinodynamic reachability as well as smoothness. Theoretical analysis demonstrate that GART is probabilistic complete, and it obtains faster convergence rate because of its redistribution ability. In addition to theoretical analysis, this article provides comparative simulations as well as experiments under typical situations. Results demonstrate that GART has a much better time-efficiency performance than RRT*, retraction-based RRT, and other referred algorithms when applying redistribution and dynamic constraints on random exploration.

This paper deals with a new approach based on Q-learning for solving the problem of mobile robot path planning in complex unknown static environments. As a computational approach to learning through interaction with the environment, reinforcement learning algorithms have been widely used for intelligent robot control, especially in the field of autonomous mobile robots. However, the learning process is slow and cumbersome. For practical applications, rapid rates of convergence are required. Aiming at the problem of slow convergence and long learning time for Q-learning based mobile robot path planning, a state-chain sequential feedback Q-learning algorithm is proposed for quickly searching for the optimal path of mobile robots in complex unknown static environments. The state chain is built during the searching process. After one action is chosen and the reward is received, the Q-values of the state-action pairs on the previously built state chain are sequentially updated with one-step Q-learning. With the increasing number of Q-values updated after one action, the number of actual steps for convergence decreases and thus, the learning time decreases, where a step is a state transition. Extensive simulations validate the efficiency of the newly proposed approach for mobile robot path planning in complex environments. The results show that the new approach has a high convergence speed and that the robot can find the collision-free optimal path in complex unknown static environments with much shorter time, compared with the one-step Q-learning algorithm and the Q(λ)-learning algorithm.

This paper presents an efficient path planner to identify difficult regions for path planning in changing environments, in which obstacles can move randomly. The difficult regions consist of narrow passages and the boundaries of obstacles in robot Configuration Space (C-space). These regions exert significantly negative influence on finding a valid path in static environments. The problem becomes more complicated in changing environments, because that the regions will change their positions when obstacles move. Besides, it is necessary to identify difficult regions in real time since obstacles may move frequently. To identify difficult regions fast when they change their positions, a dynamic bridge builder is proposed based on a W-C nodes mapping and a Bridge planner method. The W-C nodes mapping is used not only to conserve the validity of nodes in C-space, but also to provide the information about where a "bridge" should be built, i.e. the positions of narrow passages, and where the boundaries of obstacles are. Furthermore, a hierarchy sampling strategy is employed to boost the density of nodes in difficult regions efficiently. In the query phase, a Lazy-edges evaluation method is adopted to validate the edges in a found path. Simulated experiments for a dual-manipulator system show that our method is efficient for path planning in changing environments.