A softmin-based adaptive blending mechanism that automatically selects the most suitable path from the champion solutions on the Pareto front according to regional environmental conditions, thereby eliminating the need for manual user intervention is introduced.
Abstract
The autonomous execution of routine sequential tasks by mobile robots in obstacle-dense environments poses substantial challenges for long-duration operations, as it simultaneously demands energy efficiency, kinematically feasible trajectory generation, and collision-free maneuvering. Although genetic algorithms (GAs) have been successfully applied to such problems, they often struggle to converge toward a feasible solution space when initialized with random coordinates in complex multi-goal maps. To address these limitations, we propose a hierarchical path planning framework for multi-goal navigation. Population initialization is accelerated by integrating the deterministic seed path planning of A* with the multi-objective optimization capabilities of the Non-dominated Sorting GA II (NSGA-II). Subsequently, the following five conflicting criteria are simultaneously optimized over a B-Spline curve representation to ensure that the planned paths comply with the robot’s physical constraints: path length, cumulative wheel effort (energy consumption), trajectory curvature (smoothness), obstacle clearance (centering), and collision risk. We further introduce a softmin-based adaptive blending mechanism that automatically selects the most suitable path from the champion solutions on the Pareto front according to regional environmental conditions, thereby eliminating the need for manual user intervention. Extensive simulation results across five difficulty levels involving multiple segments demonstrate that the proposed adaptive NSGA-II method achieves path length improvements of 22%–42%, 8%–27%, and 16%–34% compared with Standard GA, ant-based whale optimization algorithm-artificial potential field, and HWPSO, respectively. The adaptive blending mechanism also attains the shortest mean path length in all five tested environments.
Robotic manipulators operating in cluttered environments require collision-free trajectories that remain executable under kinematic and dynamic constraints. This paper proposes a reinforcement learning (RL)-guided multi-objective trajectory planning framework, termed RL-MOP-HNE, for a 6-DOF UR5 manipulator. The planning model simultaneously minimizes path length, energy consumption, and execution time while satisfying collision-avoidance, kinematic, and dynamic constraints. A tabular SARSA agent is embedded into the evolutionary search to adaptively select search behaviours according to the current optimization state. To improve the balance between exploration and exploitation, a Gaussian-perturbation adaptive hybrid crossover operator is integrated with a hierarchical neighborhood evolution (HNE) strategy, enabling progressive population refinement throughout the search process. The proposed method is evaluated in three representative environments with increasing planning complexity, including single-obstacle, narrow three-obstacle, and irregular five-obstacle scenarios, and is compared with MOEA/D, MOPSO, MSCLPSO, NSGA-II, and RL-NSGA-II. Experimental results show that RL-MOP-HNE generates feasible trajectories in all test cases and achieves the lowest dynamic-stability-prioritized composite scores among the compared algorithms. The planned trajectories exhibit smoother joint motion and lower velocity fluctuations, although these improvements are generally accompanied by longer execution times. Complementary analyses, including time scaling, manipulability, clearance evaluation, statistical significance tests, and ablation studies, further explain the performance characteristics of the proposed framework and quantify the contribution of its key components. The proposed framework is therefore well suited to robotic applications where motion stability and dynamic executability are of greater importance than minimum-time operation.
Zhen-Long Zhao, Shu-Tao Hao, Bi-Hao Jin et al.· Scientific Reports· 0 citations
Sampling-based motion planning algorithms have been extensively adopted for the global path planning of mobile robots and industrial manipulators in complex static environments, owing to their probabilistic completeness and computational scalability in high-dimensional configuration space. However, most existing variants predominantly rely on single optimization strategy and multi-strategy fusion approaches often suffer from insufficient collaborative design among modules. These limitations hinder the ability to simultaneously balance exploration, convergence speed, and path quality, particularly in cluttered scenes with narrow passages. To address these challenges, this study proposes a novel multi-strategy integrated RRT* (M-RRT*) path planning framework that enables coordinated optimization across all modules. First, a three-layer hybrid sampling strategy is designed, combining goal-biased sampling, obstacle Gaussian sampling, and uniform global sampling to adaptively balance global exploration and local convergence efficiency. Second, an adaptive bidirectional tree expansion mechanism can dynamically adjust the two trees expansion state. Third, a three-point local shortcut optimization serves as the post-processing module to further refine the path quality. Extensive comparative experiments are conducted across three typical 2D environments: cluttered obstacles, maze, and narrow passages environments. The results demonstrate that, compared to RRT*, the M-RRT* reduces average path length by 24.1%, sampling nodes by 84.2%, average planning time by 83.0%, and maintains a 100% success rate across all test environments—notably enhancing planning reliability in complex constrained environments. When benchmarked against Informed-RRT* and B-RRT*, M-RRT* achieves a superior equilibrium between efficiency, success rate, and path quality, exhibiting more pronounced comprehensive advantages in complex maze and narrow passage scenarios. These quantitative results validate that the M-RRT* surpasses existing baselines in overall performance and holds application potential for AGVs, inspection robots, and industrial logistics equipment.
jian liu, Bo Tao, Du Jiang et al.· Engineering Research Express· 0 citations
A node detection strategy grounded in the safe workspace effectively prevents collisions between the generated path and surrounding obstacles, and a two-stage heuristic search strategy is designed, incorporating an intermediate node mechanism to substantially enhance search efficiency.
Xin-Guang Li, Shilong Zhao, Xiao-Qi Guo· Proceedings of the Instituti...· 0 citations
This work presents a prioritized Safe Interval Path Planning algorithm (SIPP-PP) with a novel limited goal reservation strategy to prevent goal-blocking conflicts while allowing shared goal regions, and demonstrates a multi-robot planner capable of real-time operation in dense scenarios, satisfying the stringent requirements of industrial applications such as drive units in fulfillment centers.
Rajat Kumar, Kristin Predeck, Ken Meszaros et al.· 0 citations
To address the challenge that single algorithms struggle to balance global exploration and local obstacle avoidance, and are prone to falling into local optima in complex environments, this paper proposes a Strategic Hierarchical Path Planning (SHPP) framework. This framework decouples the 3D navigation task into three synergistic layers. The top layer employs a reinforcement learning network equipped with a Credit Alignment Mechanism (CAM) to provide macroscopic guidance, eliminating credit assignment pollution and escaping local minima. The middle layer introduces a Dual-Guided Particle Swarm Optimization (DG-PSO) algorithm to map discrete commands into continuous smooth trajectories. The bottom layer executes physical collision avoidance and tracking based on the Artificial Potential Field (APF) method. Simulations indicate that the system can establish a stable policy in approximately 625 episodes, achieving an average reward of 95.6. Furthermore, benefiting from the hierarchical architecture's smooth optimization in continuous space, the average flight path length is 138.3 meters, a reduction of approximately 19% compared to traditional discrete decision-making models. These quantitative results fully validate the superior performance of the proposed architecture in complex 3D environments.
Fei Wang, Jun-Yong Shi, Zhao-Kun Chen et al.· International Conference on...· 0 citations
Path planning is a core technology in robotics, autonomous driving systems, and unmanned aerial vehicle navigation. However, in complex environments with multiple constraints, existing intelligent optimization methods are still susceptible to factors such as uneven initial distribution, insufficient environmental feedback, and premature convergence, making it difficult to stably obtain high-quality feasible paths. To address the above problems, this paper proposes an Enhanced Competition of Tribes and Cooperation of Members Method (ECTCM) based on the competition-cooperation search framework of the Competition of Tribes and Cooperation of Members Method (CTCM), aiming to improve the global exploration capability, environmental adaptability, and local exploitation capability in complex path planning tasks. Specifically, this paper designs a double-trigonometric coupled chaotic map and combines it with opposition-based learning to construct a chaotic opposition-based initialization strategy, aiming to improve the distribution uniformity of the initial population and the coverage of the search space. An environmental quality assessment mechanism is proposed to dynamically adjust the intensity of inter-tribal competition and migration according to the environmental quality of different search regions, thereby enhancing the adaptiveness of the search direction. An improved adaptive mutation strategy is introduced to adjust the perturbation intensity based on historical memory and individual ranking information, so as to alleviate population stagnation and premature convergence. Meanwhile, an elite-guided learning evolution strategy is designed to guide inferior individuals using a weighted elite center, thereby strengthening late-stage local exploitation capability. To verify the effectiveness of the proposed method, this paper compares ECTCM with 11 mainstream optimization algorithms on the CEC2020 (D = 50, 100) and CEC2022 (D = 10, 20) benchmark test functions, and further applies it to two-dimensional (2D) grid and three-dimensional (3D) UAV path planning tasks. The experimental results show that ECTCM achieves the lowest Friedman average rank in all benchmark test scenarios, and its average win rates based on the Wilcoxon rank-sum test reach 89.1%, 92.7%, 79.5%, and 83.3%, respectively. In the path planning experiments, compared with the original CTCM, ECTCM achieves comprehensive improvement rates of 6.84% and 21.36% in the 2D grid map and 3D UAV path planning scenarios, respectively. The above results indicate that, while introducing additional computational overhead, ECTCM can improve path quality, convergence accuracy, and search stability, providing a competitive optimization method for agent path planning in complex simulation environments.
Xiao-Yuan Li, Guang-Hui Li, Tai-Hua Zhang et al.· Journal of King Saud Univers...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
