Robot path planner based on deep reinforcement learning and the seeker optimization algorithm

Xiangrui, Xing; Ding, Hongwei; Liang, Zhen; Li, Bo; Yang, Zhijun

doi:10.1016/j.mechatronics.2022.102918

Cited by 10 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, novel strategies for resolving robot path planning issues have been proposed [19,20]. The authors Ntakolia et al [19] present a new algorithm for path construction using chaotic ant colony optimization with fuzzy logic (CACOF), obstacle avoidance using a bug-like algorithm enhanced with fuzzy rules, and powerful and lightweight deep convolutional neural networks for obstacle detection.…”

Section: Introductionmentioning

confidence: 99%

“…The algorithm was tested in a simulated environment and demonstrated computational efficiency. Using the advantage actor-critic (A2C) algorithm as a local planner and the seeker optimization algorithm (SOA) as a global planner, Xing et al [20] present a novel robot path planner, seeker optimization algorithm (SOA+A2C), which outperforms the Dijkstra and dynamic window approaches.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimal path planning using bidirectional rapidly-exploring random tree star-dynamic window approach (BRRT*-DWA) with adaptive Monte Carlo localization (AMCL) for mobile robot

Ayalew,

Menebo,

Merga

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

Path planning is an important task for mobile service robots. Most of theavailable path-planning algorithms are applicable only in static environments. Achievingpath planning becomes a difficult task in an unknown dynamic environment. To solve theproblem of path planning in an unknown dynamic environment, this paper proposes a BRRT*-DWA algorithm with Adaptive Monte Carlo Localization. Bidirectional Rapidly-exploringRandom Tree Star(BRRT*) is used to generate an optimal global path plan, Dynamic WindowApproach(DWA) is a local planner and Adaptive Monte Carlo Localization(AMCL) is usedas a localization technique. By using the map file of the unknown environment created bySLAM and LiDAR sensor, the robot can navigate while avoiding dynamic as well as staticobstacles. In addition, the object identification algorithm YOLO was adopted, trained, andused for the robot to recognize objects and people. Results obtained from both simulationand experiment show the proposed method can achieve better performance in a dynamicenvironment compared with other state-of-the-art algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Optimal path planning using bidirectional rapidly-exploring random tree star-dynamic window approach (BRRT*-DWA) with adaptive Monte Carlo localization (AMCL) for mobile robot

Ayalew,

Menebo,

Merga

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…For example, Yang et al (2020) improved the deep Q-network (DQN) algorithm in deep reinforcement learning to solve the multirobot path-planning problem in a nonmanned warehouse. Xing et al (2022) designed a new type of path planner for mobile robots, which integrates the seeker optimization algorithm (SOA) and the deep reinforcement learning algorithm advantage actor-critic to achieve global and local path planning. Sonny et al (2023) solved the path-planning and dynamic obstacle avoidance problem of UAVs using the Q-learning approach.…”

mentioning

confidence: 99%

Dynamic path planning for mobile robots based on artificial potential field enhanced improved multiobjective snake optimization (APF‐IMOSO)

Li,

Ma,

Weng

2024

Journal of Field Robotics

View full text Add to dashboard Cite

With the widespread adoption of mobile robots, effective path planning has become increasingly critical. Although traditional search methods have been extensively utilized, meta‐heuristic algorithms have gained popularity owing to their efficiency and problem‐specific heuristics. However, challenges remain in terms of premature convergence and lack of solution diversity. To address these issues, this paper proposes a novel artificial potential field enhanced improved multiobjective snake optimization algorithm (APF‐IMOSO). This paper presents four key enhancements to the snake optimizer to significantly improve its performance. Additionally, it introduces four fitness functions focused on optimizing path length, safety (evaluated via artificial potential field method), energy consumption, and time efficiency. The results of simulation and experiment in four scenarios including static and dynamic highlight APF‐IMOSO's advantages, delivering improvements of 8.02%, 7.61%, 50.71%, and 12.74% in path length, safety, energy efficiency, and time‐savings, respectively, over the original snake optimization algorithm. Compared with other advanced meta‐heuristics, APF‐IMOSO also excels in these indexes. Real robot experiments show an average path length error of 1.19% across four scenarios. The results reveal that APF‐IMOSO can generate multiple viable collision‐free paths in complex environments under various constraints, showcasing its potential for use in dynamic path planning within the realm of robot navigation.

show abstract

Path planning of manure-robot cleaners using grid-based reinforcement learning

Sun,

van der Tol,

Melenhorst

et al. 2024

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

Robot path planner based on deep reinforcement learning and the seeker optimization algorithm

Cited by 10 publications

References 31 publications

Optimal path planning using bidirectional rapidly-exploring random tree star-dynamic window approach (BRRT*-DWA) with adaptive Monte Carlo localization (AMCL) for mobile robot

Optimal path planning using bidirectional rapidly-exploring random tree star-dynamic window approach (BRRT*-DWA) with adaptive Monte Carlo localization (AMCL) for mobile robot

Dynamic path planning for mobile robots based on artificial potential field enhanced improved multiobjective snake optimization (APF‐IMOSO)

Path planning of manure-robot cleaners using grid-based reinforcement learning

Contact Info

Product

Resources

About