# L4KDE: Learning for KinoDynamic Tree Expansion

arXiv: https://arxiv.org/abs/2203.00975 · HTML: https://mlsanity.com/paper/2203.00975/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 2 Mar 2022.

## Builds on (most cited first, 11 of 11)

- [Learning Sampling Distributions for Robot Motion Planning](https://mlsanity.com/paper/1709.05448/) (2017)
- [Neural Network with Unbounded Activation Functions is Universal Approximator](https://mlsanity.com/paper/1505.03654/) (2015)
- [Asymptotically Optimal Sampling-based Kinodynamic Planning](https://mlsanity.com/paper/1407.2896/) (2014)
- [Parallelised Diffeomorphic Sampling-based Motion Planning](https://mlsanity.com/paper/2108.11775/) (2021)
- [Experience-Based Planning with Sparse Roadmap Spanners](https://mlsanity.com/paper/1410.1950/) (2014)
- [Asymptotically Optimal Planning by Feasible Kinodynamic Planning in State-Cost Space](https://mlsanity.com/paper/1505.04098/) (2015)
- [Kinodynamic Motion Planning: A Novel Type Of Nonlinear, Passive Damping Forces And Advantages](https://mlsanity.com/paper/1606.09270/) (2016)
- [Balancing Global Exploration and Local-connectivity Exploitation with Rapidly-exploring Random disjointed-Trees](https://mlsanity.com/paper/1810.03749/) (2018)
- [Bayesian Local Sampling-based Planning](https://mlsanity.com/paper/1909.03452/) (2019)
- [An Efficiently Solvable Quadratic Program for Stabilizing Dynamic Locomotion](https://mlsanity.com/paper/1311.1839/) (2013)
- [Rapidly-Exploring Quotient-Space Trees: Motion Planning using Sequential Simplifications](https://mlsanity.com/paper/1906.01350/) (2019)

## Built on by (most cited first, 2 of 2)

- [Real-time Aerial Detection and Reasoning on Embedded-UAVs](https://mlsanity.com/paper/2305.12414/) (2023)
- [Discover Life Skills for Planning with Bandits via Observing and Learning How the World Works](https://mlsanity.com/paper/2207.08130/) (2022)

## Abstract (arXiv)

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 that 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.