UGV Navigation Optimization Aided by Reinforcement Learning-Based Path Tracking

Wei, Minggao; Wang, Song; Zheng, Jieyun; Chen, Dan

doi:10.1109/access.2018.2872751

Cited by 15 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is particle means that robot 1 delivers package 1 and package 3 since the first and third elements are 1.2 and 1.1, whose integer parts are 1. Package 3 should be delivered before package 1 because 1.1 is smaller than 1.2. us, the IDs of packages delivered by robot 1 are elements [3,1], and they are delivered following this order. Similarly, robot 2 is in charge of delivering elements [4,2,5] with the corresponding order.…”

Section: Problem Formulation Considering Multiplementioning

confidence: 99%

See 1 more Smart Citation

Autonomous Last-Mile Delivery Based on the Cooperation of Multiple Heterogeneous Unmanned Ground Vehicles

Ding

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

With the development of e-commerce, the last-mile delivery has become a significant part of customers’ shopping experience. In this paper, an autonomous last-mile delivery method using multiple unmanned ground vehicles is investigated. Being a smart logistics service, it provides a promising solution to reduce the delivery cost, improve efficiency, and avoid the spread of airborne diseases, such as SARS and COVID-19. By using a cooperation strategy with multiple heterogeneous robots, contactless parcel delivery can be carried out within apartment complexes efficiently. In this paper, the last-mile delivery with heterogeneous UGVs is formulated as an optimization problem aimed at minimizing the maximum makespan to complete all tasks. Then, a heuristic algorithm combining the Floyd’s algorithm and PSO algorithm is proposed for task assignment and path planning. This algorithm is further realized in a distributed scheme, with all robots in a swarm working together to obtain the best task schedule. A good solution with an optimized makespan is achieved by considering the constraints of various robots in terms of speed and payload. Simulations and experiments are carried out and the obtained results confirm the validity and applicability of the developed approaches.

show abstract

Section: Problem Formulation Considering Multiplementioning

confidence: 99%

“…Unmanned ground vehicles (UGVs) have been successfully applied in diverse applications, such as planet exploration on the Moon and Mars [1,2]. In recent years, UGVs have also been used for logistic services to reduce delivery costs [3].…”

Section: Introductionmentioning

confidence: 99%

Autonomous Last-Mile Delivery Based on the Cooperation of Multiple Heterogeneous Unmanned Ground Vehicles

Ding

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Wei et al train a deterministic policy gradient algorithm on an abstracted structure to imitate the deformation of the path under the external force. This method allows unmanned ground vehicle autonomously to find collisionfree paths to mobile goals in complicated environments [34]. Tai et al build the environment that regards the coordinate of the agent as input and outputs the continuous steering operation.…”

Section: Literature Reviewmentioning

confidence: 99%

Path Planning Method With Improved Artificial Potential Field—A Reinforcement Learning Perspective

et al. 2020

View full text Add to dashboard Cite

The artificial potential field approach is an efficient path planning method. However, to deal with the local-stable-point problem in complex environments, it needs to modify the potential field and increases the complexity of the algorithm. This study combines improved black-hole potential field and reinforcement learning to solve the problems which are scenarios of local-stable-points. The blackhole potential field is used as the environment in a reinforcement learning algorithm. Agents automatically adapt to the environment and learn how to utilize basic environmental information to find targets. Moreover, trained agents adopt variable environments with the curriculum learning method. Meanwhile, the visualization of the avoidance process demonstrates how agents avoid obstacles and reach the target. Our method is evaluated under static and dynamic experiments. The results show that agents automatically learn how to jump out of local stability points without prior knowledge.

show abstract

“…RL has made a number of significant breakthroughs over the passage of time. Two kinds of method for solving RL problems have been divided as follows: on-policy and off-policy methods [ 32 ]. On-policy methods make decisions and evaluate the policy.…”

Section: Problem Formulationmentioning

confidence: 99%

Reinforcement Learning-Based Data Association for Multiple Target Tracking in Clutter

Zhang

et al. 2020

Sensors

View full text Add to dashboard Cite

Data association is a crucial component of multiple target tracking, in which each measurement obtained by the sensor can be determined whether it belongs to the target. However, many methods reported in the literature may not be able to ensure the accuracy and low computational complexity during the association process, especially in the presence of dense clutters. In this paper, a novel data association method based on reinforcement learning (RL), i.e., the so-called RL-JPDA method, has been proposed for solving the aforementioned problem. In the presented method, the RL is leveraged to acquire available information of measurements. In addition, the motion characteristics of the targets are utilized to ensure the accuracy of the association results. Experiments are performed to compare the proposed method with the global nearest neighbor data association method, the joint probabilistic data association method, the fuzzy optimal membership data association method and the intuitionistic fuzzy joint probabilistic data association method. The results show that the proposed method yields a shorter execution time compared to other methods. Furthermore, it can obtain an effective and feasible estimation in the environment with dense clutters.

show abstract

UGV Navigation Optimization Aided by Reinforcement Learning-Based Path Tracking

Cited by 15 publications

References 35 publications

Autonomous Last-Mile Delivery Based on the Cooperation of Multiple Heterogeneous Unmanned Ground Vehicles

Autonomous Last-Mile Delivery Based on the Cooperation of Multiple Heterogeneous Unmanned Ground Vehicles

Path Planning Method With Improved Artificial Potential Field—A Reinforcement Learning Perspective

Reinforcement Learning-Based Data Association for Multiple Target Tracking in Clutter

Contact Info

Product

Resources

About