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

01/17/2021
by   Linjun Li, et al.
0

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.

READ FULL TEXT
research
10/17/2020

Constrained Motion Planning Networks X

Constrained motion planning is a challenging field of research, aiming f...
research
07/13/2019

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

This paper describes Motion Planning Networks (MPNet), a computationally...
research
08/09/2020

Neural Manipulation Planning on Constraint Manifolds

The presence of task constraints imposes a significant challenge to moti...
research
09/06/2022

Adaptive Complexity Model Predictive Control

This work introduces a formulation of model predictive control (MPC) whi...
research
07/26/2021

The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts

Many multi-robot planning problems are burdened by the curse of dimensio...
research
07/22/2019

LEGO: Leveraging Experience in Roadmap Generation for Sampling-Based Planning

We consider the problem of leveraging prior experience to generate roadm...
research
09/30/2022

NTFields: Neural Time Fields for Physics-Informed Robot Motion Planning

Neural Motion Planners (NMPs) have emerged as a promising tool for solvi...

Please sign up or login with your details

Forgot password? Click here to reset