DeepAI
Log In Sign Up

Parallelised Diffeomorphic Sampling-based Motion Planning

08/26/2021
by   Tin Lai, et al.
0

We propose Parallelised Diffeomorphic Sampling-based Motion Planning (PDMP). PDMP is a novel parallelised framework that uses bijective and differentiable mappings, or diffeomorphisms, to transform sampling distributions of sampling-based motion planners, in a manner akin to normalising flows. Unlike normalising flow models which use invertible neural network structures to represent these diffeomorphisms, we develop them from gradient information of desired costs, and encode desirable behaviour, such as obstacle avoidance. These transformed sampling distributions can then be used for sampling-based motion planning. A particular example is when we wish to imbue the sampling distribution with knowledge of the environment geometry, such that drawn samples are less prone to be in collisions. To this end, we propose to learn a continuous occupancy representation from environment occupancy data, such that gradients of the representation defines a valid diffeomorphism and is amenable to fast parallel evaluation. We use this to "morph" the sampling distribution to draw far fewer collision-prone samples. PDMP is able to leverage gradient information of costs, to inject specifications, in a manner similar to optimisation-based motion planning methods, but relies on drawing from a sampling distribution, retaining the tendency to find more global solutions, thereby bridging the gap between trajectory optimisation and sampling-based planning methods.

READ FULL TEXT
12/01/2020

Learning Sampling Distributions for Efficient High-Dimensional Motion Planning

Robot motion planning involves computing a sequence of valid robot confi...
08/25/2020

Learning Obstacle Representations for Neural Motion Planning

Motion planning and obstacle avoidance is a key challenge in robotics ap...
05/03/2022

Sampling-free obstacle gradients and reactive planning in Neural Radiance Fields (NeRF)

This work investigates the use of Neural implicit representations, speci...
10/21/2020

Learning to Plan Optimally with Flow-based Motion Planner

Sampling-based motion planning is the predominant paradigm in many real-...
10/15/2021

sbp-env: Sampling-based Motion Planners' Testing Environment

Sampling-based motion planners' testing environment (sbp-env) is a full ...
04/14/2022

Approximating Constraint Manifolds Using Generative Models for Sampling-Based Constrained Motion Planning

Sampling-based motion planning under task constraints is challenging bec...
11/13/2020

Joint Sampling and Trajectory Optimization over Graphs for Online Motion Planning

Among the most prevailing motion planning techniques, sampling and traje...