Learning-Based End-to-End Path Planning for Lunar Rovers with Safety Constraints

Yu, Xiaoqiang; Wang, Ping; Zhang, Zexu

doi:10.3390/s21030796

Cited by 42 publications

(22 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further insights and a more extensive surveys on related hybrid methods are provided in Mac et al [ 8 ]. Furthermore, the use of Reinforcement Learning (RL) has also been studied to control the motion of a robot [ 156 , 157 ]. Faust et al [ 158 ] combined RL with the Probabilistic Roadmap Method (PRM), which is one of the algorithms detailed next.…”

Section: Soft-computing-based Path Planning Algorithmsmentioning

confidence: 99%

Path Planning for Autonomous Mobile Robots: A Review

Sánchez‐Ibáñez

Pérez-del-Pulgar

García-Cerezo

2021

Sensors

198

View full text Add to dashboard Cite

Providing mobile robots with autonomous capabilities is advantageous. It allows one to dispense with the intervention of human operators, which may prove beneficial in economic and safety terms. Autonomy requires, in most cases, the use of path planners that enable the robot to deliberate about how to move from its location at one moment to another. Looking for the most appropriate path planning algorithm according to the requirements imposed by users can be challenging, given the overwhelming number of approaches that exist in the literature. Moreover, the past review works analyzed here cover only some of these approaches, missing important ones. For this reason, our paper aims to serve as a starting point for a clear and comprehensive overview of the research to date. It introduces a global classification of path planning algorithms, with a focus on those approaches used along with autonomous ground vehicles, but is also extendable to other robots moving on surfaces, such as autonomous boats. Moreover, the models used to represent the environment, together with the robot mobility and dynamics, are also addressed from the perspective of path planning. Each of the path planning categories presented in the classification is disclosed and analyzed, and a discussion about their applicability is added at the end.

show abstract

Section: Soft-computing-based Path Planning Algorithmsmentioning

confidence: 99%

Path Planning for Autonomous Mobile Robots: A Review

Sánchez‐Ibáñez

Pérez-del-Pulgar

García-Cerezo

2021

Sensors

198

View full text Add to dashboard Cite

show abstract

“…Yu et al. [19] propose a deep learning path planning algorithm applied to a lunar rover. It has higher security compared with the traditional path‐planning algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…It is through the analysis of a large amount of sample data, discovering the intrinsic laws of it, and then performing autonomous learning and planning the optimal path to avoid obstacles. Yu et al [19] propose a deep learning path planning algorithm applied to a lunar rover. It has higher security compared with the traditional path-planning algorithm.…”

Section: Introductionmentioning

confidence: 99%

Optimisation of collaborative supply transportation based on traffic road network topology

Wang

Han

Liao

et al. 2023

IET Collab Intel Manufact

View full text Add to dashboard Cite

With the rapid development of China's economy, enterprises need to plan their logistics transportation routes reasonably in advance. This will make the transportation service more efficient. For the supplier's transportation service problem, an analysis method of critical path nodes is provided and a multi‐supplier collaborative transportation strategy is designed in this article. First, a model for minimising the transportation cost was established, then a path diagram was simulated and the optimal and alternative transportation paths of suppliers based on the k‐shortest path algorithm were calculated. In addition, path node availability during COVID‐19 is used as a research context in this article. A multi‐stage path analysis method was provided by discussing different cases of critical path nodes, which can make a reasonable selection of paths in a timely and effective manner. Finally, simulations of collaborative transportation for suppliers were performed in three scenarios and the results verified the effectiveness of the collaborative transportation strategy. The proposed collaborative transportation strategy of suppliers not only strengthened the synergistic cooperation among suppliers, but also cultivated the potential customer for suppliers in this article. Furthermore, the strategy could improve the flexibility of the supply chain, maximise the overall efficiency and also provide a new solution for the development of logistics and transportation services.

show abstract

“…Xu proposed a good convergence algorithm based on deep reinforcement learning, and designed a reward function including process rewards, such as a speed tracking reward, which solved the problem of sparse rewards [18]. Yu proposed a learning-based, end-to-end path-planning algorithm with security constraints, which included a security reward function, and used it as the reward feedback of the current state to improve the safety guarantee of autonomous exploration process [19]. Wang proposed an online learning method, DDPG, combined with a particle swarm optimization algorithm to improve the speed control performance [20].…”

Section: Introductionmentioning

confidence: 99%

A Deep Reinforcement Learning Strategy Combining Expert Experience Guidance for a Fruit-Picking Manipulator

et al. 2022

View full text Add to dashboard Cite

When using deep reinforcement learning algorithms for path planning of a multi-DOF fruit-picking manipulator in unstructured environments, it is much too difficult for the multi-DOF manipulator to obtain high-value samples at the beginning of training, resulting in low learning and convergence efficiency. Aiming to reduce the inefficient exploration in unstructured environments, a reinforcement learning strategy combining expert experience guidance was first proposed in this paper. The ratios of expert experience to newly generated samples and the frequency of return visits to expert experience were studied by the simulation experiments. Some conclusions were that the ratio of expert experience, which declined from 0.45 to 0.35, was more effective in improving learning efficiency of the model than the constant ratio. Compared to an expert experience ratio of 0.35, the success rate increased by 1.26%, and compared to an expert experience ratio of 0.45, the success rate increased by 20.37%. The highest success rate was achieved when the frequency of return visits was 15 in 50 episodes, an improvement of 31.77%. The results showed that the proposed method can effectively improve the model performance and enhance the learning efficiency at the beginning of training in unstructured environments. This training method has implications for the training process of reinforcement learning in other domains.

show abstract

Learning-Based End-to-End Path Planning for Lunar Rovers with Safety Constraints

Cited by 42 publications

References 25 publications

Path Planning for Autonomous Mobile Robots: A Review

Path Planning for Autonomous Mobile Robots: A Review

Optimisation of collaborative supply transportation based on traffic road network topology

A Deep Reinforcement Learning Strategy Combining Expert Experience Guidance for a Fruit-Picking Manipulator

Contact Info

Product

Resources

About