DeepAI AI Chat
Log In Sign Up

Learning To Find Shortest Collision-Free Paths From Images

by   Michal Pándy, et al.

Motion planning is a fundamental problem in robotics and machine perception. Sampling-based planners find accurate solutions by exhaustively exploring the space, but are inefficient and tend to produce jerky motions. Optimization and learning-based planners are more efficient and produce smooth trajectories. However, a significant hurdle that these approaches face is constructing a differentiable cost function that simultaneously minimizes path length and avoids collisions. These two objectives are conflicting by nature – path length is continuous and well-behaved, but collisions are discrete non-differentiable events. Reconciling these terms has been a significant challenge in optimization-based motion planning. The main contribution of this paper is a novel cost function that guarantees collision-free shortest paths are found at its minimum. We show that our approach works seamlessly with RGBD input and predicts high-quality paths in 2D, 3D, and 6 DoF robotic manipulator settings. Our method also reduces training and inference time compared to existing approaches, in some cases by orders of magnitude.


page 6

page 7

page 17


Cost-to-Go Function Generating Networks for High Dimensional Motion Planning

This paper presents c2g-HOF networks which learn to generate cost-to-go ...

Posterior Sampling for Anytime Motion Planning on Graphs with Expensive-to-Evaluate Edges

Collision checking is a computational bottleneck in motion planning, req...

A Survey of Asymptotically Optimal Sampling-based Motion Planning Methods

Motion planning is a fundamental problem in autonomous robotics. It requ...

A Little More, a Lot Better: Improving Path Quality by a Simple Path Merging Algorithm

Sampling-based motion planners are an effective means for generating col...

Non-Trivial Query Sampling For Efficient Learning To Plan

In recent years, learning-based approaches have revolutionized motion pl...

Geometry-Aware Coverage Path Planning for Depowdering on Complex 3D Surfaces

This paper presents a new approach to obtaining nearly complete coverage...

Differentiable Collision Detection: a Randomized Smoothing Approach

Collision detection appears as a canonical operation in a large range of...