Waypoint Planning Networks

@article{Toma2021WaypointPN,
  title={Waypoint Planning Networks},
  author={Alexandru Toma and Hussein Ali Jaafar and Hao-Ya Hsueh and Stephen James and Daniel Lenton and Ronald Clark and Sajad Saeedi},
  journal={2021 18th Conference on Robots and Vision (CRV)},
  year={2021},
  pages={87-94}
}
With the recent advances in machine learning, path planning algorithms are also evolving; however, the learned path planning algorithms often have difficulty competing with success rates of classic algorithms. We propose waypoint planning networks (WPN), a hybrid algorithm based on LSTMs with a local kernel—a classic algorithm such as A*, and a global kernel using a learned algorithm. WPN produces a more computationally efficient and robust solution. We compare WPN against A*, as well as… 
2 Citations
PathBench: A Benchmarking Platform for Classical and Learned Path Planning Algorithms
TLDR
The benchmarking capability of PathBench is demonstrated by comparing implemented classical and learned algorithms for metrics, such as path length, success rate, computational time and path deviation, on built-in PathBench maps and external path planning environments from video games and real world databases.
Systematic comparison of path planning algorithms using PathBench
TLDR
The benchmarking ability of PathBench is explored in this paper by comparing algorithms across five different hardware systems and three different map types, including built-in PathBench maps, video game maps, and maps from real world databases.

References

SHOWING 1-10 OF 51 REFERENCES
HouseExpo: A Large-scale 2D Indoor Layout Dataset for Learning-based Algorithms on Mobile Robots
TLDR
HouseExpo is built, a large-scale indoor layout dataset containing 35, 126 2D floor plans including 252, 550 rooms in total and PseudoSLAM, a lightweight and efficient simulation platform to accelerate the data generation procedure, thereby speeding up the training process.
Robot Path Planning by LSTM Network Under Changing Environment
TLDR
This work proposes a novel robot path planning method that combines the rapidly exploring random tree (RRT) and long short-term memory (LSTM) network, and overcomes the difficulty of general methods with neural networks.
Value Iteration Networks
TLDR
This work introduces the value iteration network (VIN), a fully differentiable neural network with a `planning module' embedded within that shows that by learning an explicit planning computation, VIN policies generalize better to new, unseen domains.
A LSTM Neural Network applied to Mobile Robots Path Planning
TLDR
This paper proposes a Long Short-Term Memory (LSTM) neural network as an online search agent to tackle the problem of mobile robots path planning in unknown environments, meaning that the agent relies only on local map awareness realized with a LRF sensor and relative information between robot and goal position.
Motion Planning Networks
TLDR
This work presents Motion Planning Networks (MPNet), a neural network-based novel planning algorithm that encodes the given workspaces directly from a point cloud measurement and generates the end-to-end collision-free paths for the given start and goal configurations.
Rapidly-exploring random trees : a new tool for path planning
We introduce the concept of a Rapidly-exploring Random Tree (RRT) as a randomized data structure that is designed for a broad class of path planning problems. While they share many of the bene cial
PathBench: A Benchmarking Platform for Classical and Learned Path Planning Algorithms
TLDR
The benchmarking capability of PathBench is demonstrated by comparing implemented classical and learned algorithms for metrics, such as path length, success rate, computational time and path deviation, on built-in PathBench maps and external path planning environments from video games and real world databases.
Dynamically Constrained Motion Planning Networks for Non-Holonomic Robots
TLDR
Dynamic MPNet is described, an extension to Motion Planning Networks, for non-holonomic robots that address the challenge of real-time motion planning using a neural planning approach and modifications to the training and planning networks are proposed.
Neural Manipulation Planning on Constraint Manifolds
TLDR
It is shown that CoMPNet solves practical motion planning tasks involving both unconstrained and constrained problems and generalizes to new unseen locations of the objects, i.e., not seen during training, in the given environments with high success rates.
Neural RRT*: Learning-Based Optimal Path Planning
TLDR
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.
...
...