Dynamic Motion Planning Model for Multirobot Using Graph Neural Network and Historical Information

Li, Jinpeng; Su, Zhiyuan; Qiu, Yuxuan

doi:10.1002/aisy.202300036

Cited by 7 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work is later extended in [42], and an attention-like mechanism [24] is inserted in the graph neural network to model the intra-robot communication, where the weights on edges between nodes are proportional to the importance of the received message. A similar structure is exploited by [149], where an history of past paths is stored within the graph neural network to perform motion planning.…”

Section: A Task and Motion Planningmentioning

confidence: 99%

Graph Learning in Robotics: A Survey

Pistilli,

Averta

2023

IEEE Access

View full text Add to dashboard Cite

Deep neural networks for graphs have emerged as a powerful tool for learning on complex non-euclidean data, which is becoming increasingly common for a variety of different applications. Yet, although their potential has been widely recognised in the machine learning community, graph learning is largely unexplored for downstream tasks such as robotics applications. To fully unlock their potential, hence, we propose a review of graph neural architectures from a robotics perspective. The paper covers the fundamentals of graph-based models, including their architecture, training procedures, and applications. It also discusses recent advancements and challenges that arise in applied settings, related for example to the integration of perception, decision-making, and control. Finally, the paper provides an extensive review of various robotic applications that benefit from learning on graph structures, such as bodies and contacts modelling, robotic manipulation, action recognition, fleet motion planning, and many more. This survey aims to provide readers with a thorough understanding of the capabilities and limitations of graph neural architectures in robotics, and to highlight potential avenues for future research.

show abstract

Section: A Task and Motion Planningmentioning

confidence: 99%

Graph Learning in Robotics: A Survey

Pistilli,

Averta

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the field of intelligent driving, behavior cloning (BC) has been studied for driver imitation without prior reference trajectory. [ 24,25 ] BC dates back to the ALVINN system, [ 26 ] which aims to match the learned policy to human demonstrations. With the development of deep neural networks (DNN), DNN‐based planning methods have been proposed.…”

Section: Introductionmentioning

confidence: 99%

Safe and Human‐Like Trajectory Planning of Self‐Driving Cars: A Constraint Imitative Method

Cui,

Hu,

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Safe and human‐like trajectory planning is crucial for self‐driving cars. While model‐based planning has demonstrated reliability, it is beneficial to incorporate human demonstrations and align the results with human behaviors. This work aims at bridging the gap between model‐based planning and driver imitation by proposing a constraint imitative trajectory planning method (CITP). CITP integrates artificial potential field and dynamic movement primitives, which have achieved both the ability to imitate human demonstrations as well as ensure safety constraints. During the planning process, CITP first encodes human demonstrations, local driving target, and traffic obstacles as attractive or repulsive effects, and then the trajectory planning problem is solved through model predictive optimization. To address the dynamics of traffic scenarios, a hierarchical planning strategy is proposed based on the division of planning process. CITP is designed with five modules, including LSTM‐based target generation, encoding attractive and repulsive effects with target, demonstrations and obstacles, and trajectory planning with model predictive optimization. Data collection and experiments are carried out based on CARLA driving simulator, and the effectiveness in terms of both safety and consistency with human behavior are reported.

show abstract

An Algorithm of Complete Coverage Path Planning for Deep‐Sea Mining Vehicle Clusters Based on Reinforcement Learning

Xing,

Wang,

Liu

2024

Advcd Theory and Sims

View full text Add to dashboard Cite

This paper proposes a deep reinforcement learning algorithm to achieve complete coverage path planning for deep‐sea mining vehicle clusters. First, the mining vehicles and the deep‐sea mining environment are modeled. Then, this paper implements a series of algorithm designs and optimizations based on Deep Q Networks (DQN). The map fusion mechanism can integrate the grid matrix data from multiple mining vehicles to get the state matrix of the complete environment. In this paper, a preprocessing method for the state matrix is also designed to provide suitable training data for the neural network. The reward function and action selection mechanism of the algorithm are also optimized according to the requirements of cluster cooperative operation. Furthermore, the algorithm uses distance constraints to prevent the entanglement of underwater hoses. To improve the training efficiency of the neural network, the algorithm filters and extracts training samples for training through the sample quality score. Considering the requirement of cluster complete coverage mission, this paper introduces Long Short‐Term Memory (LSTM) based on the neural network to achieve a better training effect. After completing the above optimization and design, the algorithm proposed in this paper is verified through simulation experiments.

show abstract

Dynamic Motion Planning Model for Multirobot Using Graph Neural Network and Historical Information

Cited by 7 publications

References 46 publications

Graph Learning in Robotics: A Survey

Graph Learning in Robotics: A Survey

Safe and Human‐Like Trajectory Planning of Self‐Driving Cars: A Constraint Imitative Method

An Algorithm of Complete Coverage Path Planning for Deep‐Sea Mining Vehicle Clusters Based on Reinforcement Learning

Contact Info

Product

Resources

About