L4KDE: Learning for KinoDynamic Tree Expansion

by   Tin Lai, et al.

We present the Learning for KinoDynamic Tree Expansion (L4KDE) method for kinodynamic planning. Tree-based planning approaches, such as rapidly exploring random tree (RRT), are the dominant approach to finding globally optimal plans in continuous state-space motion planning. Central to these approaches is tree-expansion, the procedure in which new nodes are added into an ever-expanding tree. We study the kinodynamic variants of tree-based planning, where we have known system dynamics and kinematic constraints. In the interest of quickly selecting nodes to connect newly sampled coordinates, existing methods typically cannot optimise to find nodes which have low cost to transition to sampled coordinates. Instead they use metrics like Euclidean distance between coordinates as a heuristic for selecting candidate nodes to connect to the search tree. We propose L4KDE to address this issue. L4KDE uses a neural network to predict transition costs between queried states, which can be efficiently computed in batch, providing much higher quality estimates of transition cost compared to commonly used heuristics while maintaining almost-surely asymptotic optimality guarantee. We empirically demonstrate the significant performance improvement provided by L4KDE on a variety of challenging system dynamics, with the ability to generalise across different instances of the same model class, and in conjunction with a suite of modern tree-based motion planners.


page 1

page 2

page 3

page 4


Sampling-based optimal kinodynamic planning with motion primitives

This paper proposes a novel sampling-based motion planner, which integra...

Length of a Full Steiner Tree as a Function of Terminal Coordinates

Given the coordinates of the terminals {(x_j,y_j)}_j=1^n of the full Euc...

Hierarchical Annotated Skeleton-Guided Tree-based Motion Planning

We present a hierarchical tree-based motion planning strategy, HAS-RRT, ...

Bidirectional Sampling Based Search Without Two Point Boundary Value Solution

Bidirectional path and motion planning approaches decrease planning time...

Relevant Region Sampling Strategy with Adaptive Heuristic Estimation for Asymptotically Optimal Motion Planning

The sampling-based motion planning algorithms can solve the motion plann...

RRT-CoLearn: towards kinodynamic planning without numerical trajectory optimization

Sampling-based kinodynamic planners, such as Rapidly-exploring Random Tr...

Consensus Maximization Tree Search Revisited

Consensus maximization is widely used for robust fitting in computer vis...

Please sign up or login with your details

Forgot password? Click here to reset