# MPC-MPNet: Model-Predictive Motion Planning Networks for Fast, Near-Optimal Planning under Kinodynamic Constraints

arXiv: https://arxiv.org/abs/2101.06798 · HTML: https://mlsanity.com/paper/2101.06798/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 17 Jan 2021.

## Builds on (most cited first, 16 of 16)

- [Generative Adversarial Networks: An Overview](https://mlsanity.com/paper/1710.07035/) (2017)
- [Learning Sampling Distributions for Robot Motion Planning](https://mlsanity.com/paper/1709.05448/) (2017)
- [Motion Planning Networks](https://mlsanity.com/paper/1806.05767/) (2018)
- [Deep Drone Acrobatics](https://mlsanity.com/paper/2006.05768/) (2020)
- [Motion Planning Networks: Bridging the Gap Between Learning-based and Classical Motion Planners](https://mlsanity.com/paper/1907.06013/) (2019)
- [Robot Motion Planning in Learned Latent Spaces](https://mlsanity.com/paper/1807.10366/) (2018)
- [RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators from RL Policies](https://mlsanity.com/paper/1907.04799/) (2019)
- [Asymptotically Optimal Sampling-based Kinodynamic Planning](https://mlsanity.com/paper/1407.2896/) (2014)
- [Neural Manipulation Planning on Constraint Manifolds](https://mlsanity.com/paper/2008.03787/) (2020)
- [Dynamically Constrained Motion Planning Networks for Non-Holonomic Robots](https://mlsanity.com/paper/2008.05112/) (2020)
- [Kinodynamic Motion Planning: A Novel Type Of Nonlinear, Passive Damping Forces And Advantages](https://mlsanity.com/paper/1606.09270/) (2016)
- [Sampling-based optimal kinodynamic planning with motion primitives](https://mlsanity.com/paper/1809.02399/) (2018)
- [Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path](https://mlsanity.com/paper/2003.01641/) (2020)
- [Deep Reactive Planning in Dynamic Environments](https://mlsanity.com/paper/2011.00155/) (2020)
- [RRT-CoLearn: towards kinodynamic planning without numerical trajectory optimization](https://mlsanity.com/paper/1710.10122/) (2017)
- [Analysis of Asymptotically Optimal Sampling-based Motion Planning Algorithms for Lipschitz Continuous Dynamical Systems](https://mlsanity.com/paper/1405.2872/) (2014)

## Built on by (most cited first, 8 of 8)

- [Variational Inference MPC using Normalizing Flows and Out-of-Distribution Projection](https://mlsanity.com/paper/2205.04667/) (2022)
- [NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning](https://mlsanity.com/paper/2403.06828/) (2024)
- [Motion Planning Transformers: A Motion Planning Framework for Mobile Robots](https://mlsanity.com/paper/2106.02791/) (2021)
- [Fast Kinodynamic Planning on the Constraint Manifold with Deep Neural Networks](https://mlsanity.com/paper/2301.04330/) (2023)
- [Learning Sampling Dictionaries for Efficient and Generalizable Robot Motion Planning with Transformers](https://mlsanity.com/paper/2306.00851/) (2023)
- [Model-free Neural Lyapunov Control for Safe Robot Navigation](https://mlsanity.com/paper/2203.01190/) (2022)
- [A Survey on the Integration of Machine Learning with Sampling-based Motion Planning](https://mlsanity.com/paper/2211.08368/) (2022)
- [R×R: Rapid eXploration for Reinforcement Learning via Sampling-based Reset Distributions and Imitation Pre-training](https://mlsanity.com/paper/2401.15484/) (2024)

## Abstract (arXiv)

Kinodynamic Motion Planning (KMP) is to find a robot motion subject to concurrent kinematics and dynamics constraints. To date, quite a few methods solve KMP problems and those that exist struggle to find near-optimal solutions and exhibit high computational complexity as the planning space dimensionality increases. To address these challenges, we present a scalable, imitation learning-based, Model-Predictive Motion Planning Networks framework that quickly finds near-optimal path solutions with worst-case theoretical guarantees under kinodynamic constraints for practical underactuated systems. Our framework introduces two algorithms built on a neural generator, discriminator, and a parallelizable Model Predictive Controller (MPC). The generator outputs various informed states towards the given target, and the discriminator selects the best possible subset from them for the extension. The MPC locally connects the selected informed states while satisfying the given constraints leading to feasible, near-optimal solutions. We evaluate our algorithms on a range of cluttered, kinodynamically constrained, and underactuated planning problems with results indicating significant improvements in computation times, path qualities, and success rates over existing methods.