Improved Soft Duplicate Detection in Search-Based Motion Planning

TL;DR

This paper enhances soft duplicate detection in search-based motion planning by introducing a kinodynamically informed metric that better distinguishes duplicate states considering robot dynamics and successor similarity.

Contribution

It proposes a novel kinodynamically informed metric called subtree overlap, improving duplicate detection in continuous, dynamic-constrained motion planning.

Findings

The new metric better identifies duplicate states in kinodynamic planning.

Improved detection reduces local minima trapping in search algorithms.

Results show enhanced planning efficiency and success rates.

Abstract

Search-based techniques have shown great success in motion planning problems such as robotic navigation by discretizing the state space and precomputing motion primitives. However in domains with complex dynamic constraints, constructing motion primitives in a discretized state space is non-trivial. This requires operating in continuous space which can be challenging for search-based planners as they can get stuck in local minima regions. Previous work on planning in continuous spaces introduced soft duplicate detection which requires search to compute the duplicity of a state with respect to previously seen states to avoid exploring states that are likely to be duplicates, especially in local minima regions. They propose a simple metric utilizing the euclidean distance between states, and proximity to obstacles to compute the duplicity. In this paper, we improve upon this metric by introducing a kinodynamically informed metric, subtree overlap, between two states as the similarity between their successors that can be reached within a fixed time horizon using kinodynamic motion primitives. This captures the intuition that, due to robot dynamics, duplicate states can be far in euclidean distance and result in very similar successor states, while non-duplicate states can be close and result in widely different successors.