Sampling heuristics for optimal motion planning in high dimensions

Abstract

We present a sampling-based motion planner that improves the performance of the probabilistically optimal RRT* planning algorithm. Experiments demonstrate that our planner finds a fast initial path and decreases the cost of this path iteratively. We identify and address the limitations of RRT* in high-dimensional configuration spaces. We introduce a sampling bias to facilitate and accelerate cost decrease in these spaces and a simple node-rejection criteria to increase efficiency. Finally, we incorporate an existing bi-directional approach to search which decreases the time to find an initial path. We analyze our planner on a simple 2D navigation problem in detail to show its properties and test it on a difficult 7D manipulation problem to show its effectiveness. Our results consistently demonstrate improved performance over RRT*.

Optimal Path Planning using RRT* based Approaches: A Survey and Future Directions

“…This is due to the fact that managing non-holonomic constraints using connect heuristic of bidirectional tree does not guarantee the connection of both trees [57]. Therefore bidirectional variants of RRT* are considered suitable only for holonomic robots [57,58].…”

“…An asymptotic optimal variant of RRT* [4] and RRTconnect [11] called Bidirectional RRT* (B-RRT*) was proposed by Akgun and Stilman [58]. It showed empirical results indicating fast convergence and path refinement using sample rejection with an admissible heuristic.…”

“…Recently, Yi et al [45] presented Homotopy-Aware RRT* (HARRT*) based on bidirectional RRT* [58]. HARRT* is inspired with the idea of homotopy, i.e., to plan path from one topological space to another by human intervention.…”

Sampling-Based Motion Planning Algorithms for Replanning and Spatial Load Balancing

“…Akgun et al [1] uses local biasing to choose the sampling point based upon the current best path to the goal. The RRT*-Smart in [22] finds an initial path to the goal, then it optimizes it using first a smoothing technique, and then it further shapes it by biasing sampling to balls around the nodes in the optimized path.…”

Goal Directed Approach to Autonomous Motion Planning for Unmanned Vehicles

“…A bias towards the goal 4 is usually added by giving an increased probability to the goal states which tends to increase the rate of convergence of the planner. Shaping the probability distribution function 5 which is used to generate random samples to grow a tree has shown improvements in the rate of convergence of the path planner 6 . The negative side of increasing the bias is that like randomised potential field it becomes too greedy also leading to local minima problem 7 .…”