Probabilistic Bubble Roadmap
🤖 AI Summary
Traditional sampling-based planners suffer from high computational overhead, non-smooth paths, and poor real-time responsiveness to dynamic obstacle changes. To address these challenges in multi-query path planning for dynamic environments, this paper proposes a dynamic Probabilistic Roadmap (PRM) planner. Our method innovatively integrates a learned Signed Distance Function (SDF) with spherical topological primitives: collision-free “bubbles” generated from the SDF serve as roadmap vertices, edge connectivity is determined via sphere intersection tests, and the graph supports incremental rewiring. In static scenarios, the approach significantly reduces roadmap size, shortens path length, and accelerates planning. In dynamic settings, it enables real-time obstacle detection and online replanning—overcoming the static-environment assumption inherent in conventional sampling-based planners. The result is an efficient, smooth, and adaptive multi-query path planning framework.
Application Category
📝 Abstract
Finding a collision-free path is a fundamental problem in robotics, where the sampling based planners have a long line of success. However, this approach is computationally expensive, due to the frequent use of collision-detection. Furthermore, the produced paths are usually jagged and require further post-processing before they can be tracked. Due to their high computational cost, these planners are usually restricted to static settings, since they are not able to cope with rapid changes in the environment. In our work, we remove this restriction by introducing a learned signed distance function expressed in the configuration space of the robot. The signed distance allows us to form collision-free spherical regions in the configuration space, which we use to suggest a new multi-query path planner that also works in dynamic settings. We propose the probabilistic bubble roadmap planner, which enhances the probabilistic roadmap planner (PRM) by using spheres as vertices and compute the edges by checking for neighboring spheres which intersect. We benchmark our approach in a static setting where we show that we can produce paths that are shorter than the paths produced by the PRM, while having a smaller sized roadmap and finding the paths faster. Finally, we show that we can rapidly rewire the graph in the case of new obstacles introduced at run time and therefore produce paths in the case of moving obstacles.
Problem
Research questions and friction points this paper is trying to address.
Reducing computational cost in path planning
Enabling path planning in dynamic environments
Improving path smoothness in robotics navigation
Innovation
Methods, ideas, or system contributions that make the work stand out.
Learned signed distance function
Multi-query path planner
Probabilistic bubble roadmap
🔎 Similar Papers
No similar papers found.
