Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search

@article{Osanlou2019OptimalSO,
  title={Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search},
  author={Kevin Osanlou and Andrei Bursuc and Christophe Guettier and Tristan Cazenave and {\'E}ric Jacopin},
  journal={2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year={2019},
  pages={3519-3525}
}
Learning-based methods are growing prominence for planning purposes. However, there are very few approaches for learning-assisted constrained path-planning on graphs, while there are multiple downstream practical applications. This is the case for constrained path-planning for Autonomous Unmanned Ground Vehicles (AUGV), typically deployed in disaster relief or search and rescue applications. In off-road environments, the AUGV must dynamically optimize a source-destination path under various… 

Figures and Tables from this paper

Learning Constraint-based Strategies for On-Board Dynamic Planning and Scheduling of Logistics Missions for Autonomous VTOL-UAV

  • Computer Science
  • 2020
A constraint programming model and a learning-based search algorithm approach for path-planning & scheduling and re-planing, using representative topological maps of navigation waypoints and edges is proposed.

UAV Intelligent Coverage Navigation Based on DRL in Complex Geometrical Environments

Experiments show that the trained UAV can find an excellent flight path by intelligent navigation, and able to make effective flight decisions in a complex geometrical environment.

Solving Disjunctive Temporal Networks with Uncertainty under Restricted Time-Based Controllability using Tree Search and Graph Neural Networks

R-TDC is shown to retain significant completeness with regard to DC, while being faster to prove, and GNN tree search guidance leads to substantial performance gains on benchmarks of more complex DTNUs, with up to eleven times more problems solved than the baseline tree search.

Time-based Dynamic Controllability of Disjunctive Temporal Networks with Uncertainty: A Tree Search Approach with Graph Neural Network Guidance

This work introduces a more restricted, stronger form of controllability than DC for DTNUs, time-based dynamic controllable (TDC), and presents a tree search approach to determine whether or not a DTNU is TDC.

Space-Time Graph Neural Networks with Stochastic Graph Perturbations

The stability properties of ST-GNNs are revisited and it is proved that they are stable to stochastic graph perturbations and enables the design of generalized convolutional architectures that jointly process time-varying graphs and time- varying signals.

Smart element aware gate controller for intelligent wheeled robot navigation

The practical results demonstrate that the proposed mechanism is very efficient in terms of providing shortest distance to reach the goal with maximum velocity as compared with the MENN, and is better than MENN in minimizing the error rate.

Planning and Learning: A Review of Methods involving Path-Planning for Autonomous Vehicles

This short review aims to make the reader familiar with state-of-the-art works relating to planning, scheduling and learning and study some successful approaches combining neural networks for path-planning.

References

SHOWING 1-10 OF 116 REFERENCES

Constrained Shortest Path Search with Graph Convolutional Neural Networks

This paper proposes a hybrid model that combines a constraintbased solver and a graph convolutional neural network to improve search performance and focuses on shortest path search with mandatory nodes on a given connected graph.

Adaptive Planner Scheduling with Graph Neural Networks

A graph neural network (GNN) approach to selecting candidate planners is proposed, advantageous over a straightforward alternative, the convolutional neural networks, in that they are invariant to node permutations and that they incorporate node labels for better inference.

Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks

This work proposes a graph neural network architecture for predicting object importance in a single inference pass, thus incurring little overhead while greatly reducing the number of objects that must be considered by the planner.

Motion Planning Networks: Bridging the Gap Between Learning-Based and Classical Motion Planners

This article describes motion planning networks (MPNet), a computationally efficient, learning-based neural planner for solving motion planning problems, and shows that worst-case theoretical guarantees can be proven if this neural network strategy is merged with classical sample-based planners in a hybrid approach.

A Goal-Prioritized Algorithm for Additional Route Deployment on Existing Mass Transportation System

Gaussian mixture model is employed to propose a target-prioritized searching algorithm called Multi-Source Bidirectional Gaussian-Prioritized Spanning Tree (BiasSpan) in solving this non-monotonic multi-criteria route planning problem given constraints including range, must-visit vertices, and the number of recommended vertices.

Graph Neural Networks for Decentralized Multi-Robot Path Planning

A combined model is proposed that automatically synthesizes local communication and decision-making policies for robots navigating in constrained workspaces that shows its capability to generalize to previously unseen cases.

Learning-based Preference Prediction for Constrained Multi-Criteria Path-Planning

This work leverages knowledge acquired through offline simulations by training a neural network model to predict the uncertain criterion and integrates this model inside a path-planner which can solve problems online.

Learning Scheduling Policies for Multi-Robot Coordination With Graph Attention Networks

This work develops a novel graph attention network-based scheduler to automatically learn features of scheduling problems towards generating high-quality solutions, which significantly outperforms prior state-of-the-art, approximate methods.

Neural RRT*: Learning-Based Optimal Path Planning

A novel optimal path planning algorithm based on the convolutional neural network (CNN), namely the neural RRT* (NRRT*), which utilizes a nonuniform sampling distribution generated from a CNN model and achieves better performance.

A Gaussian-Prioritized Approach for Deploying Additional Route on Existing Mass Transportation with Neural-Network-Based Passenger Flow Inference

Gaussian mixture model is employed to propose a target-prioritized searching algorithm called Multi-Source Bidirectional Gaussian-Prioritized Spanning Tree (BiasSpan) in solving this non-monotonic multicriteria route planning problem given constraints including range, must-visit vertices, and the number of recommended vertices.
...