Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

InfoFusion Controller: Informed TRRT Star with Mutual Information based on Fusion of Pure Pursuit and MPC for Enhanced Path Planning

Seongjun Choi, Youngbum Kim, Nam Woo Kim, Mansun Shin, Byunggi Chae, Sungjin Lee

TL;DR

The paper addresses the challenge of achieving globally optimal routing while maintaining robust real-time obstacle avoidance in urban autonomous driving. It integrates a global Informed-TRRT* path planner with local MPC and Pure Pursuit controllers, using Mutual Information to adaptively fuse their predictions. Key contributions include an MI-based fusion framework, a concrete combination of MPC and Pure Pursuit for reactive control, and demonstrated improvements in safety, stability, and obstacle avoidance on complex SLAM-generated maps. The approach offers practical potential for real-world deployment, with open-source code provided for reproduction.

Abstract

In this paper, we propose the InfoFusion Controller, an advanced path planning algorithm that integrates both global and local planning strategies to enhance autonomous driving in complex urban environments. The global planner utilizes the informed Theta-Rapidly-exploring Random Tree Star (Informed-TRRT*) algorithm to generate an optimal reference path, while the local planner combines Model Predictive Control (MPC) and Pure Pursuit algorithms. Mutual Information (MI) is employed to fuse the outputs of the MPC and Pure Pursuit controllers, effectively balancing their strengths and compensating for their weaknesses. The proposed method addresses the challenges of navigating in dynamic environments with unpredictable obstacles by reducing uncertainty in local path planning and improving dynamic obstacle avoidance capabilities. Experimental results demonstrate that the InfoFusion Controller outperforms traditional methods in terms of safety, stability, and efficiency across various scenarios, including complex maps generated using SLAM techniques. The code for the InfoFusion Controller is available at https: //github.com/DrawingProcess/InfoFusionController.

InfoFusion Controller: Informed TRRT Star with Mutual Information based on Fusion of Pure Pursuit and MPC for Enhanced Path Planning

TL;DR

The paper addresses the challenge of achieving globally optimal routing while maintaining robust real-time obstacle avoidance in urban autonomous driving. It integrates a global Informed-TRRT* path planner with local MPC and Pure Pursuit controllers, using Mutual Information to adaptively fuse their predictions. Key contributions include an MI-based fusion framework, a concrete combination of MPC and Pure Pursuit for reactive control, and demonstrated improvements in safety, stability, and obstacle avoidance on complex SLAM-generated maps. The approach offers practical potential for real-world deployment, with open-source code provided for reproduction.

Abstract

In this paper, we propose the InfoFusion Controller, an advanced path planning algorithm that integrates both global and local planning strategies to enhance autonomous driving in complex urban environments. The global planner utilizes the informed Theta-Rapidly-exploring Random Tree Star (Informed-TRRT*) algorithm to generate an optimal reference path, while the local planner combines Model Predictive Control (MPC) and Pure Pursuit algorithms. Mutual Information (MI) is employed to fuse the outputs of the MPC and Pure Pursuit controllers, effectively balancing their strengths and compensating for their weaknesses. The proposed method addresses the challenges of navigating in dynamic environments with unpredictable obstacles by reducing uncertainty in local path planning and improving dynamic obstacle avoidance capabilities. Experimental results demonstrate that the InfoFusion Controller outperforms traditional methods in terms of safety, stability, and efficiency across various scenarios, including complex maps generated using SLAM techniques. The code for the InfoFusion Controller is available at https: //github.com/DrawingProcess/InfoFusionController.

Paper Structure

This paper contains 22 sections, 12 equations, 6 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. Methods
  4. Architecture Overview
  5. MPC
  6. Control Optimization
  7. Collision-Free Validation
  8. Selecting the Best Control
  9. Pure Pursuit
  10. Target Selection
  11. Obstacle Avoidance
  12. Path Selection
  13. InfoFusion Controller
  14. MI Calculation
  15. Normalized MI
  16. ...and 7 more sections

Figures (6)

  • Figure 1: Overall Operation of the Proposed Path Planning Algorithm: The diagram illustrates the complete operation of the proposed path planning algorithm, encompassing both the Global Planning and Local Planning stages.
  • Figure 2: Various Level of Map
  • Figure 3: How to generate occupancy map (map_hard): Create a grid map by post-processing the map mapped to SLAM inside the RDSim simulation AuTURBO:2023
  • Figure 4: Compare Overall Performance
  • Figure 5: Compare Safety Performance
  • ...and 1 more figures