Traversability-aware path planning in dynamic environments

TL;DR

This paper introduces Traversability-aware FMM, a path planning method for dynamic environments that minimizes obstacle risk and goal deviation by assessing region traversability, demonstrated through simulations and real-world tests.

Contribution

It presents a novel traversability-aware path planning approach that effectively avoids crowded regions in dynamic environments, improving safety and efficiency.

Findings

Enhanced safety by avoiding obstacle-dense regions

Reduced unnecessary goal deviations

Effective in both simulated and real-world scenarios

Abstract

Planning in environments with moving obstacles remains a significant challenge in robotics. While many works focus on navigation and path planning in obstacle-dense spaces, traversing such congested regions is often avoidable by selecting alternative routes. This paper presents Traversability-aware FMM (Tr-FMM), a path planning method that computes paths in dynamic environments, avoiding crowded regions. The method operates in two steps: first, it discretizes the environment, identifying regions and their distribution; second, it computes the traversability of regions, aiming to minimize both obstacle risks and goal deviation. The path is then computed by propagating the wavefront through regions with higher traversability. Simulated and real-world experiments demonstrate that the approach enhances significant safety by keeping the robot away from regions with obstacles while reducing unnecessary deviations from the goal.