Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Modified RRT* for Path Planning in Autonomous Driving

Sugirtha T, Pranav S, Nitin Benjamin Dasiah, Sridevi M

TL;DR

The paper tackles path planning for autonomous driving in complex, cluttered environments by introducing a two-stage AD-RRT* approach that combines A* global routing with an angle-bounded local search to bound sampling and accelerate convergence. The method uses A* to compute a global path and guides a constrained RRT* search with an angle derived from the global path, including a bounded-sampling strategy, connectivity region, and standard RRT* operations (nearest, steer, collision check, near, insert, rewire) with a dynamic angle expansion when necessary. It reports faster convergence, fewer nodes, and lower path costs than base RRT* across six obstacle-density CARLA scenarios, validated through simulations and visual results. The work highlights practical benefits for real-time autonomous driving and outlines future work to extend to dynamic environments and further optimizations.

Abstract

Essential tasks in autonomous driving includes environment perception, detection and tracking, path planning and action control. This paper focus on path planning, which is one of the challenging task as it needs to find optimal path in highly complex and dynamic environments. Usually, a driving scenario has large number of obstacles in their route. In this paper, we propose a two-stage path planning algorithm named Angle-based Directed Rapidly exploring Random Trees (AD-RRT*) to address the problem of optimal path in complex environment. The proposed algorithm uses A* algorithm for global path planning and modifies RRT* to bound the samples using angle. The efficiency of the proposed algorithm is evaluated through experiments in different scenarios based on the location and number of obstacles. The proposed algorithm showed higher rate of convergence with reduced time and less number of nodes than the base RRT* algorithm.

Modified RRT* for Path Planning in Autonomous Driving

TL;DR

The paper tackles path planning for autonomous driving in complex, cluttered environments by introducing a two-stage AD-RRT* approach that combines A* global routing with an angle-bounded local search to bound sampling and accelerate convergence. The method uses A* to compute a global path and guides a constrained RRT* search with an angle derived from the global path, including a bounded-sampling strategy, connectivity region, and standard RRT* operations (nearest, steer, collision check, near, insert, rewire) with a dynamic angle expansion when necessary. It reports faster convergence, fewer nodes, and lower path costs than base RRT* across six obstacle-density CARLA scenarios, validated through simulations and visual results. The work highlights practical benefits for real-time autonomous driving and outlines future work to extend to dynamic environments and further optimizations.

Abstract

Essential tasks in autonomous driving includes environment perception, detection and tracking, path planning and action control. This paper focus on path planning, which is one of the challenging task as it needs to find optimal path in highly complex and dynamic environments. Usually, a driving scenario has large number of obstacles in their route. In this paper, we propose a two-stage path planning algorithm named Angle-based Directed Rapidly exploring Random Trees (AD-RRT*) to address the problem of optimal path in complex environment. The proposed algorithm uses A* algorithm for global path planning and modifies RRT* to bound the samples using angle. The efficiency of the proposed algorithm is evaluated through experiments in different scenarios based on the location and number of obstacles. The proposed algorithm showed higher rate of convergence with reduced time and less number of nodes than the base RRT* algorithm.
Paper Structure (6 sections, 3 equations, 6 figures, 1 table)

This paper contains 6 sections, 3 equations, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Proposed Work
  4. Experimental results and Analysis
  5. Conclusion
  6. Acknowledgement

Figures (6)

  • Figure 1: Tree expansion process of RRT* Karaman2011SamplingbasedAF
  • Figure 2: Rewiring Process of RRT* Karaman2011SamplingbasedAF. (a) Finding near vertices (b) Selection of best parent (c) cost check (d) rewiring with minimum cost
  • Figure 3: Lane changing maneuver mashadi2014global
  • Figure 4: General pipeline of autonomous driving tasks [focus on Decision making task]
  • Figure 5: Visual results of Path planning for Scenarios S1, S2, S3, S4, S5 and S6. (a) and (b) under each scenario denotes the intermediate and final step in path planning.
  • ...and 1 more figures