Motion Planning by Learning the Solution Manifold in Trajectory Optimization
This addresses the limitation of existing methods that only produce finite solutions, potentially improving motion planning for robotics by enabling more flexible and diverse path generation.
The paper tackles the problem of non-convex trajectory optimization in motion planning, where diverse solutions exist, by learning an infinite set of solutions through latent representations, resulting in a model that generates homotopic collision-free trajectories.
The objective function used in trajectory optimization is often non-convex and can have an infinite set of local optima. In such cases, there are diverse solutions to perform a given task. Although there are a few methods to find multiple solutions for motion planning, they are limited to generating a finite set of solutions. To address this issue, we presents an optimization method that learns an infinite set of solutions in trajectory optimization. In our framework, diverse solutions are obtained by learning latent representations of solutions. Our approach can be interpreted as training a deep generative model of collision-free trajectories for motion planning. The experimental results indicate that the trained model represents an infinite set of homotopic solutions for motion planning problems.