AM-RRT*: Informed Sampling-based Planning with Assisting Metric

  title={AM-RRT*: Informed Sampling-based Planning with Assisting Metric},
  author={Daniel W. Armstrong and Andr'e Jonasson},
  journal={2021 IEEE International Conference on Robotics and Automation (ICRA)},
  • D. Armstrong, Andr'e Jonasson
  • Published 28 October 2020
  • Computer Science
  • 2021 IEEE International Conference on Robotics and Automation (ICRA)
In this paper, we present a new algorithm that extends RRT* and RT-RRT* for online path planning in complex, dynamic environments. Sampling-based approaches often perform poorly in environments with narrow passages, a feature common to many indoor applications of mobile robots as well as computer games. Our method extends RRT-based sampling methods to enable the use of an assisting distance metric to improve performance in environments with obstacles. This assisting metric, which can be any… 

Figures from this paper

Trajectory Planner CDT-RRT* for Car-Like Mobile Robots toward Narrow and Cluttered Environments
A trajectory planner for car-like robots on the basis of the Dual-Tree RRT, which utilizes two tree structures in order to generate fast-growing trajectories under the kinodynamic constraints of robots.


RT-RRT*: a real-time path planning algorithm based on RRT*
A novel algorithm for real-time path-planning in a dynamic environment such as a computer game by introducing an online tree rewiring strategy that allows the tree root to move with the agent without discarding previously sampled paths.
Distance Metric Learning for RRT-Based Motion Planning for Wheeled Mobile Robots
A learning approach to compute the distance metric for RRT-based planners is introduced by exploiting a novel extend function which solves the two-point boundary value problem for wheeled mobile robots and training a nonlinear parametric model that achieves good performances in regression and ranking tests.
Sampling-based algorithms for optimal motion planning
The main contribution of the paper is the introduction of new algorithms, namely, PRM and RRT*, which are provably asymptotically optimal, i.e. such that the cost of the returned solution converges almost surely to the optimum.
Motion planning with diffusion maps
Many robotic applications require repeated, on-demand motion planning in mapped environments. In addition, the presence of other dynamic agents, such as people, often induces frequent, dynamic
Real-time heuristic search for motion planning with dynamic obstacles
Extensions to a leading planner for high-dimensional spaces that allow it to guarantee real-time performance, and extensions to aLeading real- time planner, LSS-LRTA ∗ , that succeed in dynamic motion planning.
Informed RRT*: Optimal sampling-based path planning focused via direct sampling of an admissible ellipsoidal heuristic
Optimal RRTs (RRT*s) extend R RTs to the problem of finding the optimal solution, but in doing so asymptotically find the optimal path from the initial state to every state in the planning domain.
Rapidly-exploring random trees : a new tool for path planning
We introduce the concept of a Rapidly-exploring Random Tree (RRT) as a randomized data structure that is designed for a broad class of path planning problems. While they share many of the bene cial
High quality navigation in computer games
A critical evaluation of literature on robot path planning in Dynamic environment
This study presents a comprehensive survey of the various techniques that have been proposed in robot Path Planning in dynamic environments, including a classification of the approaches and identify their methods.
Bounds on tracking error using closed-loop rapidly-exploring random trees
This paper shows that under certain assumptions, the recently proposed closed-loop RRT algorithm can be used to accurately track a trajectory with known error bounds and robust feasibility guarantees, without the need for replanning.