Log In Sign Up

Neural Manipulation Planning on Constraint Manifolds

by   Ahmed H. Qureshi, et al.

The presence of task constraints imposes a significant challenge to motion planning. Despite all recent advancements, existing algorithms are still computationally expensive for most planning problems. In this paper, we present Constrained Motion Planning Networks (CoMPNet), the first neural planner for multimodal kinematic constraints. Our approach comprises the following components: i) constraint and environment perception encoders; ii) neural robot configuration generator that outputs configurations on/near the constraint manifold(s), and iii) a bidirectional planning algorithm that takes the generated configurations to create a feasible robot motion trajectory. We show that CoMPNet solves practical motion planning tasks involving both unconstrained and constrained problems. Furthermore, it generalizes to new unseen locations of the objects, i.e., not seen during training, in the given environments with high success rates. When compared to the state-of-the-art constrained motion planning algorithms, CoMPNet outperforms by order of magnitude improvement in computational speed with a significantly lower variance.


page 1

page 3

page 5

page 6


Constrained Motion Planning Networks X

Constrained motion planning is a challenging field of research, aiming f...

Deep Neural Networks for Swept Volume Prediction Between Configurations

Swept Volume (SV), the volume displaced by an object when it is moving a...

Learning Equality Constraints for Motion Planning on Manifolds

Constrained robot motion planning is a widely used technique to solve co...

Robot Motion Planning as Video Prediction: A Spatio-Temporal Neural Network-based Motion Planner

Neural network (NN)-based methods have emerged as an attractive approach...

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

Kinodynamic Motion Planning (KMP) is to find a robot motion subject to c...

LTO: Lazy Trajectory Optimization with Graph-Search Planning for High DOF Robots in Cluttered Environments

Although Trajectory Optimization (TO) is one of the most powerful motion...

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

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