Reinforcement learning path planning algorithm based on obstacle area expansion strategy

Chen, Haiyang; Yebiao, Ji; Longhui, Niu

doi:10.1007/s11370-020-00313-y

Cited by 22 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been some researches processing the concave regions before the path planning. Chen et al 28 proposed an improved OAE-Q(λ)-learning path planning method by introducing the concave area expansion strategy to avoid repeated invalid actions when the agent falls into the obstacle area. This method fills the concave area in the map before the path planning.…”

Section: Solution To the Concave Regionmentioning

confidence: 99%

One Way to Fill All the Concave Region in Grid-Based Map

Zhang

et al. 2020

Robotica

View full text Add to dashboard Cite

SUMMARY The search space of the path planning problem can greatly affect the running time and memory consumption, for example, the concave obstacle in grid-based map usually leads to the invalid search space. In this paper, the filling container algorithm is proposed to alleviate the concave area problem in 2D map space, which is inspired from the scenario of pouring water into a cup. With this method, concave areas can be largely excluded by scanning the map repeatedly. And the effectiveness has been proved in our experiments.

show abstract

Section: Solution To the Concave Regionmentioning

confidence: 99%

One Way to Fill All the Concave Region in Grid-Based Map

Zhang

et al. 2020

Robotica

View full text Add to dashboard Cite

show abstract

“…With the rapid development of machine learning [7][8][9][10], using reinforcement learning-based methods to solve path planning problems has attracted more and more attention. Reinforcement learning can realize online learning without a tutor, so it fully meets the needs of mobile robot path planning.…”

Section: Introductionmentioning

confidence: 99%

Robot Path Planning Based on Improved Reinforcement Learning

Fang

Yin

Wang

et al. 2022

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

With the continuous progress and development of robotics, mobile robots have been widely used in many different fields. In the power grid, mobile robots are used to inspect electrical equipment, which greatly reduce the investment of manpower and material resources. However, in many cases, mobile robots need to work in a constantly changing and complex environment. Because they cannot obtain environmental information in time, it is often difficult to make path planning. In response to this problem, this paper proposes a path planning method for mobile robots based on improved reinforcement learning. This method establishes a grid environment model, defines the return value through the number of steps of the robot, and then proposes a changing action selection strategy for the balance between the robot’s exploration and utilization of the environment in reinforcement learning, so that the exploration factor dynamically change with the increase of the robot’s exploration degree of the environment, thus speeding up the convergence speed of the learning algorithm. Simulation results show that this method can realize autonomous navigation and path planning of mobile robots in complex environments. Compared with traditional algorithms, it greatly reduces the number of iterations.

show abstract

“…Based on the traditional Q‐learning algorithm, Wang et al 9 combined greedy search and Boltzmann search to balance the randomness and purpose of the search, reducing the possibility of falling into local optimal. Chen et al 10 proposed OAE‐Q( λ )‐learning and applied it to the path planning in the complex environment, improving the traditional Q( λ )‐learning algorithm by adding the obstacle area expansion strategy.…”

Section: Introductionmentioning

confidence: 99%

“…Chen et al 10 proposed OAE-Q(𝜆)-learning and applied it to the path planning in the complex environment, improving the traditional Q(𝜆)-learning algorithm by adding the obstacle area expansion strategy.…”

Section: Introductionmentioning

confidence: 99%

Path planning of mobile robot in unknown dynamic continuous environment using reward‐modified deep Q‐network

Huang

Qin

et al. 2021

Optim Control Appl Methods

View full text Add to dashboard Cite

The path planning problem of mobile robot in unknown dynamic environment (UDE) is discussed in this article by building a continuous dynamic simulation environment. To achieve a collision-free path in UDE, the reinforcement learning theory with deep Q-network (DQN) is applied for the mobile robot to learn optimal decisions. A reward function is designed with weight to balance the obstacle avoidance and the approach to the goal. Moreover, it is found that the relative motion between moving obstacles and robots may cause abnormal rewards and further lead to a collision between robot and obstacle. To address this problem, two reward thresholds are set to modify the abnormal rewards, and the experiments shows that the robot can avoid all obstacles and reach the goal successfully. Finally, double DQN (DDQN) and dueling DQN are applied in this article. This article compares the results of reward-modified DQN (RMDQN), reward-modified DDQN (RMDDQN), dueling RMDQN, and dueling RMDDQN and concludes that the result of RMDDQN is the best.

show abstract

Reinforcement learning path planning algorithm based on obstacle area expansion strategy

Cited by 22 publications

References 15 publications

One Way to Fill All the Concave Region in Grid-Based Map

One Way to Fill All the Concave Region in Grid-Based Map

Robot Path Planning Based on Improved Reinforcement Learning

Path planning of mobile robot in unknown dynamic continuous environment using reward‐modified deep Q‐network

Contact Info

Product

Resources

About