Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Safe Interval Randomized Path Planning For Manipulators

Nuraddin Kerimov, Aleksandr Onegin, Konstantin Yakovlev

TL;DR

The paper addresses safe path planning for high DoF robotic manipulators in environments with known moving obstacles by introducing SI-RRT, which integrates bidirectional RRT-Connect with safe interval path planning (SIPP). The method represents states as (configuration, safe interval) and uses wait-and-go actions to respect obstacle motion, supported by efficient safe-interval computation. Empirical results show SI-RRT achieves higher success rates and faster runtimes than state-of-the-art space-time planners like ST-RRT* and DRGBT, especially as obstacle count grows, and can handle hundreds of dynamic obstacles within a 20-second horizon. The work demonstrates the practical impact of combining safe intervals with sampling-based planning for reliable manipulation in dynamic scenes, with code publicly available for replication and extension.

Abstract

Planning safe paths in 3D workspace for high DoF robotic systems, such as manipulators, is a challenging problem, especially when the environment is populated with the dynamic obstacles that need to be avoided. In this case the time dimension should be taken into account that further increases the complexity of planning. To mitigate this issue we suggest to combine safe-interval path planning (a prominent technique in heuristic search) with the randomized planning, specifically, with the bidirectional rapidly-exploring random trees (RRT-Connect) - a fast and efficient algorithm for high-dimensional planning. Leveraging a dedicated technique of fast computation of the safe intervals we end up with an efficient planner dubbed SI-RRT. We compare it with the state of the art and show that SI-RRT consistently outperforms the competitors both in runtime and solution cost. Our implementation of SI-RRT is publicly available at https://github.com/PathPlanning/ManipulationPlanning-SI-RRT

Safe Interval Randomized Path Planning For Manipulators

TL;DR

The paper addresses safe path planning for high DoF robotic manipulators in environments with known moving obstacles by introducing SI-RRT, which integrates bidirectional RRT-Connect with safe interval path planning (SIPP). The method represents states as (configuration, safe interval) and uses wait-and-go actions to respect obstacle motion, supported by efficient safe-interval computation. Empirical results show SI-RRT achieves higher success rates and faster runtimes than state-of-the-art space-time planners like ST-RRT* and DRGBT, especially as obstacle count grows, and can handle hundreds of dynamic obstacles within a 20-second horizon. The work demonstrates the practical impact of combining safe intervals with sampling-based planning for reliable manipulation in dynamic scenes, with code publicly available for replication and extension.

Abstract

Planning safe paths in 3D workspace for high DoF robotic systems, such as manipulators, is a challenging problem, especially when the environment is populated with the dynamic obstacles that need to be avoided. In this case the time dimension should be taken into account that further increases the complexity of planning. To mitigate this issue we suggest to combine safe-interval path planning (a prominent technique in heuristic search) with the randomized planning, specifically, with the bidirectional rapidly-exploring random trees (RRT-Connect) - a fast and efficient algorithm for high-dimensional planning. Leveraging a dedicated technique of fast computation of the safe intervals we end up with an efficient planner dubbed SI-RRT. We compare it with the state of the art and show that SI-RRT consistently outperforms the competitors both in runtime and solution cost. Our implementation of SI-RRT is publicly available at https://github.com/PathPlanning/ManipulationPlanning-SI-RRT
Paper Structure (5 sections, 5 figures, 1 algorithm)

This paper contains 5 sections, 5 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. Problem statement
  3. Method
  4. Experiments
  5. Conclusion

Figures (5)

  • Figure 1: A problem we are interested in -- path planning for a manipulator in the presence of moving obstacles whose trajectories are known (accurately predicted).
  • Figure 2: Trimming the wait action in a constructed path.
  • Figure 3: Success rate of the evaluated planners.
  • Figure 4: Runtime of SI-RRT and ST-RRT* on the instances that were successfully solved by both of them.
  • Figure 5: Solution quality (time when the manipulator arrives at the goal configuration) of ST-RRT* and SI-RRT.