Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Real-time Motion Planning for autonomous vehicles in dynamic environments

Mohammad Dehghani Tezerjani, Dominic Carrillo, Deyuan Qu, Sudip Dhakal, Amir Mirzaeinia, Qing Yang

TL;DR

The paper addresses real-time trajectory planning for autonomous vehicles in dynamic environments with moving obstacles. It proposes a hierarchical planning framework that combines a global planner based on an enhanced $A^*$ with gradient-descent refinement and a local planner using the time elastic band, augmented by moving obstacle detection and Kalman-filter-based dynamics. A novel trajectory density concept adjusts time intervals to increase waypoint density in high-curvature regions, balancing accuracy and computation. Experimental results across static and dynamic obstacle scenarios demonstrate real-time performance, smoother trajectories, and robust obstacle handling, supporting safer and more efficient autonomous navigation in dynamic settings.

Abstract

Recent advancements in self-driving car technologies have enabled them to navigate autonomously through various environments. However, one of the critical challenges in autonomous vehicle operation is trajectory planning, especially in dynamic environments with moving obstacles. This research aims to tackle this challenge by proposing a robust algorithm tailored for autonomous cars operating in dynamic environments with moving obstacles. The algorithm introduces two main innovations. Firstly, it defines path density by adjusting the number of waypoints along the trajectory, optimizing their distribution for accuracy in curved areas and reducing computational complexity in straight sections. Secondly, it integrates hierarchical motion planning algorithms, combining global planning with an enhanced $A^*$ graph-based method and local planning using the time elastic band algorithm with moving obstacle detection considering different motion models. The proposed algorithm is adaptable for different vehicle types and mobile robots, making it versatile for real-world applications. Simulation results demonstrate its effectiveness across various conditions, promising safer and more efficient navigation for autonomous vehicles in dynamic environments. These modifications significantly improve trajectory planning capabilities, addressing a crucial aspect of autonomous vehicle technology.

Real-time Motion Planning for autonomous vehicles in dynamic environments

TL;DR

The paper addresses real-time trajectory planning for autonomous vehicles in dynamic environments with moving obstacles. It proposes a hierarchical planning framework that combines a global planner based on an enhanced with gradient-descent refinement and a local planner using the time elastic band, augmented by moving obstacle detection and Kalman-filter-based dynamics. A novel trajectory density concept adjusts time intervals to increase waypoint density in high-curvature regions, balancing accuracy and computation. Experimental results across static and dynamic obstacle scenarios demonstrate real-time performance, smoother trajectories, and robust obstacle handling, supporting safer and more efficient autonomous navigation in dynamic settings.

Abstract

Recent advancements in self-driving car technologies have enabled them to navigate autonomously through various environments. However, one of the critical challenges in autonomous vehicle operation is trajectory planning, especially in dynamic environments with moving obstacles. This research aims to tackle this challenge by proposing a robust algorithm tailored for autonomous cars operating in dynamic environments with moving obstacles. The algorithm introduces two main innovations. Firstly, it defines path density by adjusting the number of waypoints along the trajectory, optimizing their distribution for accuracy in curved areas and reducing computational complexity in straight sections. Secondly, it integrates hierarchical motion planning algorithms, combining global planning with an enhanced graph-based method and local planning using the time elastic band algorithm with moving obstacle detection considering different motion models. The proposed algorithm is adaptable for different vehicle types and mobile robots, making it versatile for real-world applications. Simulation results demonstrate its effectiveness across various conditions, promising safer and more efficient navigation for autonomous vehicles in dynamic environments. These modifications significantly improve trajectory planning capabilities, addressing a crucial aspect of autonomous vehicle technology.
Paper Structure (17 sections, 14 equations, 5 figures, 2 tables, 2 algorithms)

This paper contains 17 sections, 14 equations, 5 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Methodology
  3. Proposed algorithm for global planning
  4. $A^*$ planner
  5. Gradient descent method
  6. Proposed algorithm for local planning
  7. Setting the trajectory density
  8. Obstacle dynamics in local planning
  9. Experiments
  10. First scenario: The obstacle moves at a constant speed in the vertical (y) direction
  11. Second scenario: The obstacle moves at a constant speed in the vertical (x) direction
  12. Third scenario: The obstacle moves with a constant acceleration
  13. Motion planning in the presence of moving obstacles
  14. First test: Static obstacles
  15. Second scenario: moving obstacles at a constant speed
  16. ...and 2 more sections

Figures (5)

  • Figure 1: Calculation of path curvature
  • Figure 2: Comparison of path planning with a) descent gradient and b) normal $A^*$
  • Figure 3: a) normal path planning b) considering density in the bends along the path
  • Figure 4: (a) Path planning in the presence of an obstacle moving in the y direction (b) Evaluation of the Kalman filter for the moving obstacle in the y direction (c) moving obstacle in the x direction (d) Kalman filter for the moving obstacle with constan (e) moving obstacle with different constant accelerations (f) Evaluation of the Kalman filter for an accelerated moving obstacle
  • Figure 5: (a) Two-dimensional position over time, perspective view, from above, from the front, and from the left in the presence of static obstacles (b) in the presence of constant speed obstacles (c) in the presence of constant acceleration obstacles