Local Path Planning of Mobile Robot Based on Long Short-Term Memory Neural Network

Guo, Na; Li, Caihong; Wang, Di; Song, Yong; Liu, Guoming; Gao, Tengteng

doi:10.3103/s014641162101003x

Cited by 14 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7 (a), otherwise, when the obstacle is on the left side of the trajectory direction, ℓ 𝐴𝐵𝐶 = 1, as shown in Fig. 7 (b), and the value of ℓ 𝐴𝐵𝐶 is given by equation (8).…”

Section: (I) Arc Treatment Of Trajectory Corner Pointsmentioning

confidence: 99%

“…They require grid-based map processing, which can lead to a dramatic increase in computation time and memory consumption as the map size grows and grid sizes cannot be increased accordingly. Consequently, in recent years, researchers have turned their focus to more efficient and intelligent path planning algorithms, including those based on ant colony optimization 4 , particle swarm optimization (PSO) 5 , genetic algorithms (GA) 6 , simulated annealing 7 , neural network algorithms 8 , and the Rapidly-exploring Random Trees (RRT) algorithm 9 . Some of these intelligent algorithms require initial parameter settings and are sensitive to these parameters.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Research on Path Planning and Smoothing Based on Obstacle Corner Points

Di,

Sun,

et al. 2024

Preprint

View full text Add to dashboard Cite

In response to the challenges of path planning in complex scenarios, where grid map algorithms are susceptible to the influence of grid size and intelligent algorithms exhibit uncertainty, this paper proposes a method for finding the shortest path based on obstacle corner points using the Dijkstra algorithm. To address obstacles composed of curves without corner points, we suggest a preliminary linearization fitting process followed by pathfinding. To enhance the applicability of the trajectory, we introduce the constraint of minimum turning radius and conduct smoothing research based on circular arcs, providing smoothing solutions for various scenarios. Finally, considering the practical requirement that the trajectory should maintain a safe distance from obstacle edges, we perform an expansion analysis on the obstacles, linearize the resulting arcs, obtain the trajectory based on obstacle corner points, and apply smoothing treatment. Each step has been validated through simulations, demonstrating the rationality of the proposed approach.

show abstract

Section: (I) Arc Treatment Of Trajectory Corner Pointsmentioning

confidence: 99%

mentioning

confidence: 99%

Research on Path Planning and Smoothing Based on Obstacle Corner Points

Di,

Sun,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…A local path planning method for mobile robots based on long short-term memory (LSTM) networks and reinforcement learning was implemented in [30]. The method combines LSTM network with reinforcement learning algorithms to solve the problem of local deadlock and path redundancy in the robot's planning process in unknown and complex environments, and the method is also able to improve the success rate of path planning and optimize the path length.…”

Section: Related Workmentioning

confidence: 99%

Real-Time UAV Path Planning Based on LSTM Network

Zhang,

Guo,

Zheng

et al. 2024

J. of Syst. Eng. Electron.

View full text Add to dashboard Cite

To address the shortcomings of single-step decision making in the existing deep reinforcement learning based unmanned aerial vehicle (UAV) real-time path planning problem, a real-time UAV path planning algorithm based on long shortterm memory (RPP-LSTM) network is proposed, which combines the memory characteristics of recurrent neural network (RNN) and the deep reinforcement learning algorithm. LSTM networks are used in this algorithm as Q-value networks for the deep Q network (DQN) algorithm, which makes the decision of the Q-value network has some memory. Thanks to LSTM network, the Q-value network can use the previous environmental information and action information which effectively avoids the problem of single-step decision considering only the current environment. Besides, the algorithm proposes a hierarchical reward and punishment function for the specific problem of UAV real-time path planning, so that the UAV can more reasonably perform path planning. Simulation verification shows that compared with the traditional feed-forward neural network (FNN) based UAV autonomous path planning algorithm, the RPP-LSTM proposed in this paper can adapt to more complex environments and has significantly improved robustness and accuracy when performing UAV real-time path planning.

show abstract

“…A local pathplanning algorithm is a method to plan a path for a robot in a dynamic environment. It guides the robot for dynamic-obstacle avoidance based on the robot's kinematic model, realtime environment information, obstacle distribution and other factors [27,28]. Currently, common local path-planning algorithms for mobile robots include the Dynamic Window Approach (DWA) [29], Temporal Elastic Band (TEB) [30] and Model Predictive Control (MPC) [31].…”

Section: Related Workmentioning

confidence: 99%

Mobile Robot Path Planning Based on Kinematically Constrained A-Star Algorithm and DWA Fusion Algorithm

Liu,

Wang,

et al. 2023

Mathematics

View full text Add to dashboard Cite

Path-planning research has been the key to mobile-robot-navigation technology. However, traditional path-planning algorithms have some shortcomings. To solve these problems, this paper proposes a fusion algorithm that combines the kinematical constrained A* algorithm with the Dynamic Window Approach (DWA) algorithm. The kinematical constrained A* algorithm can plan the global path, and then the DWA algorithm can plan the local path under the global path’s guidance. Firstly, combined with robot kinematics, we improve the node-expansion method and heuristic-function model of the A* algorithm, which improves the search efficiency, reduces the number of path bends and lowers the computational cost so that the path generated by the A* algorithm better meets the needs of robot motion. Secondly, we optimize the trajectory-evaluation function of the DWA algorithm so that the local paths planned by the DWA algorithm are smoother and more coherent, which is easier for robot-motion execution. Finally, we extract the key nodes from the global path planned by the A* algorithm to guide the DWA algorithm for local path planning and dynamic-obstacle avoidance and to make the local path closer to the global path. Through simulation and practical experiments, the effectiveness of the fusion algorithm proposed in this paper is verified.

show abstract

Local Path Planning of Mobile Robot Based on Long Short-Term Memory Neural Network

Cited by 14 publications

References 13 publications

Research on Path Planning and Smoothing Based on Obstacle Corner Points

Research on Path Planning and Smoothing Based on Obstacle Corner Points

Real-Time UAV Path Planning Based on LSTM Network

Mobile Robot Path Planning Based on Kinematically Constrained A-Star Algorithm and DWA Fusion Algorithm

Contact Info

Product

Resources

About